haylan/LLM-Server
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity
Files
main
LLM-Server/llmserver.log
T
haylan e5cc2a6360 docs(research): add qwen3.8-27b decode speed analysis 
- Add research note on decode tokens/s versus context depth for Qwen3.8-27B + DFlash2 on the R9700
- Covers draft length (5, not 7), acceptance falling with depth, bandwidth ceiling, and an ordered experiment plan. Proposals only, nothing applied
- Index the note in docs/research/README.md
- Also stages .serena/ project config and llmserver.log
2026-11-11 16:51:45 +01:00

10001 lines
1.4 MiB
Plaintext
Raw Permalink Blame History

llama-server | 10917.47.315.926 I slot print_timing: id 1 | task 2762467 | total time = 55819.47 ms / 50285 tokens
llama-server | 10917.47.315.927 I slot print_timing: id 1 | task 2762467 | graphs reused = 2675696
llama-server | 10917.47.315.930 I slot print_timing: id 1 | task 2762467 | draft acceptance = 0.44762 ( 47 accepted / 105 generated), mean len = 3.24
llama-server | 10917.47.317.208 I slot release: id 1 | task 2762467 | stop processing: n_tokens = 50284, truncated = 0
llama-server | 10917.48.340.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 655024431012
llama-server | 10917.48.341.522 I slot launch_slot_: id 0 | task 2762516 | processing task, is_child = 0
llama-server | 10917.48.343.815 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2265.612 MiB)
llama-server | 10917.55.258.187 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.79 s / 1282.43 tokens per second
llama-server | 10917.57.107.864 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.63 s / 1235.84 tokens per second
llama-server | 10917.58.989.370 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.50 s / 1204.17 tokens per second
llama-server | 10918.00.917.492 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.43 s / 1178.64 tokens per second
llama-server | 10918.02.878.012 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.37 s / 1158.83 tokens per second
llama-server | 10918.04.877.194 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 16384, progress = 0.33, t = 14.36 s / 1140.84 tokens per second
llama-server | 10918.06.914.648 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 18432, progress = 0.37, t = 16.39 s / 1124.60 tokens per second
llama-server | 10918.08.988.829 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 20480, progress = 0.41, t = 18.46 s / 1109.67 tokens per second
llama-server | 10918.11.104.024 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 22528, progress = 0.45, t = 20.56 s / 1095.74 tokens per second
llama-server | 10918.13.273.486 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 24576, progress = 0.49, t = 22.71 s / 1082.25 tokens per second
llama-server | 10918.15.467.285 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 26624, progress = 0.53, t = 24.90 s / 1069.10 tokens per second
llama-server | 10918.17.697.833 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 28672, progress = 0.57, t = 27.12 s / 1057.06 tokens per second
llama-server | 10918.19.969.848 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 30720, progress = 0.61, t = 29.38 s / 1045.56 tokens per second
llama-server | 10918.22.306.074 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 32768, progress = 0.65, t = 31.68 s / 1034.37 tokens per second
llama-server | 10918.24.639.416 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 34816, progress = 0.69, t = 34.04 s / 1022.80 tokens per second
llama-server | 10918.27.015.390 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 36864, progress = 0.73, t = 36.40 s / 1012.71 tokens per second
llama-server | 10918.29.420.253 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 38912, progress = 0.77, t = 38.80 s / 1002.82 tokens per second
llama-server | 10918.31.878.511 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 40960, progress = 0.81, t = 41.24 s / 993.32 tokens per second
llama-server | 10918.34.355.289 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 43008, progress = 0.85, t = 43.72 s / 983.73 tokens per second
llama-server | 10918.36.868.918 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 45056, progress = 0.90, t = 46.22 s / 974.77 tokens per second
llama-server | 10918.39.418.707 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 47104, progress = 0.94, t = 48.76 s / 965.97 tokens per second
llama-server | 10918.42.024.820 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 49152, progress = 0.98, t = 51.34 s / 957.40 tokens per second
llama-server | 10918.42.925.700 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 49813, progress = 0.99, t = 52.74 s / 944.58 tokens per second
llama-server | 10918.43.666.633 I slot print_timing: id 0 | task 2762516 | prompt processing, n_tokens = 50325, progress = 1.00, t = 53.11 s / 947.64 tokens per second
llama-server | 10918.47.044.625 I slot print_timing: id 0 | task 2762516 | prompt eval time = 53937.63 ms / 50329 tokens ( 1.07 ms per token, 933.10 tokens per second)
llama-server | 10918.47.044.629 I slot print_timing: id 0 | task 2762516 | eval time = 3185.56 ms / 99 tokens ( 32.51 ms per token, 30.76 tokens per second)
llama-server | 10918.47.044.630 I slot print_timing: id 0 | task 2762516 | total time = 57123.18 ms / 50428 tokens
llama-server | 10918.47.044.631 I slot print_timing: id 0 | task 2762516 | graphs reused = 2675729
llama-server | 10918.47.044.636 I slot print_timing: id 0 | task 2762516 | draft acceptance = 0.37647 ( 64 accepted / 170 generated), mean len = 2.88
llama-server | 10918.47.045.964 I slot release: id 0 | task 2762516 | stop processing: n_tokens = 50427, truncated = 0
llama-server | 10918.47.971.050 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 655083157260
llama-server | 10918.47.971.669 I slot launch_slot_: id 1 | task 2762578 | processing task, is_child = 0
llama-server | 10918.47.974.064 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2334.503 MiB)
llama-server | 10918.55.463.837 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.79 s / 1282.28 tokens per second
llama-server | 10918.57.315.476 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.63 s / 1235.95 tokens per second
llama-server | 10918.59.196.681 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.51 s / 1203.83 tokens per second
llama-server | 10919.01.127.071 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 12288, progress = 0.25, t = 10.43 s / 1178.29 tokens per second
llama-server | 10919.03.084.060 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 14336, progress = 0.29, t = 12.38 s / 1158.40 tokens per second
llama-server | 10919.05.081.434 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 16384, progress = 0.33, t = 14.36 s / 1140.90 tokens per second
llama-server | 10919.07.119.207 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 18432, progress = 0.37, t = 16.39 s / 1124.62 tokens per second
llama-server | 10919.09.193.011 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 20480, progress = 0.41, t = 18.45 s / 1109.79 tokens per second
llama-server | 10919.11.307.339 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 22528, progress = 0.45, t = 20.56 s / 1095.89 tokens per second
llama-server | 10919.13.477.241 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 24576, progress = 0.49, t = 22.70 s / 1082.41 tokens per second
llama-server | 10919.15.670.669 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 26624, progress = 0.53, t = 24.90 s / 1069.22 tokens per second
llama-server | 10919.17.901.946 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 28672, progress = 0.57, t = 27.12 s / 1057.18 tokens per second
llama-server | 10919.20.165.692 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 30720, progress = 0.61, t = 29.38 s / 1045.68 tokens per second
llama-server | 10919.22.507.960 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 32768, progress = 0.65, t = 31.67 s / 1034.75 tokens per second
llama-server | 10919.24.843.135 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 34816, progress = 0.69, t = 34.04 s / 1022.89 tokens per second
llama-server | 10919.27.220.564 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 36864, progress = 0.74, t = 36.40 s / 1012.78 tokens per second
llama-server | 10919.29.624.527 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 38912, progress = 0.78, t = 38.80 s / 1002.86 tokens per second
llama-server | 10919.32.080.617 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 40960, progress = 0.82, t = 41.23 s / 993.43 tokens per second
llama-server | 10919.34.555.369 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 43008, progress = 0.86, t = 43.71 s / 983.86 tokens per second
llama-server | 10919.37.067.583 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 45056, progress = 0.90, t = 46.22 s / 974.92 tokens per second
llama-server | 10919.39.615.899 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 47104, progress = 0.94, t = 48.76 s / 966.14 tokens per second
llama-server | 10919.42.222.356 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 49152, progress = 0.98, t = 51.33 s / 957.56 tokens per second
llama-server | 10919.42.861.382 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 49608, progress = 0.99, t = 52.11 s / 951.94 tokens per second
llama-server | 10919.43.607.796 I slot print_timing: id 1 | task 2762578 | prompt processing, n_tokens = 50120, progress = 1.00, t = 52.84 s / 948.57 tokens per second
llama-server | 10919.45.424.668 I slot print_timing: id 1 | task 2762578 | prompt eval time = 53672.51 ms / 50124 tokens ( 1.07 ms per token, 933.89 tokens per second)
llama-server | 10919.45.424.671 I slot print_timing: id 1 | task 2762578 | eval time = 1624.93 ms / 78 tokens ( 21.10 ms per token, 47.39 tokens per second)
llama-server | 10919.45.424.672 I slot print_timing: id 1 | task 2762578 | total time = 55297.44 ms / 50202 tokens
llama-server | 10919.45.424.673 I slot print_timing: id 1 | task 2762578 | graphs reused = 2675744
llama-server | 10919.45.424.676 I slot print_timing: id 1 | task 2762578 | draft acceptance = 0.70588 ( 60 accepted / 85 generated), mean len = 4.53
llama-server | 10919.45.426.050 I slot release: id 1 | task 2762578 | stop processing: n_tokens = 50201, truncated = 0
llama-server | 10919.46.452.836 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 655142886017
llama-server | 10919.46.453.569 I slot launch_slot_: id 0 | task 2762623 | processing task, is_child = 0
llama-server | 10919.46.455.810 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2257.831 MiB)
llama-server | 10919.53.775.400 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.79 s / 1281.94 tokens per second
llama-server | 10919.55.626.805 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.64 s / 1233.92 tokens per second
llama-server | 10919.57.507.768 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 10240, progress = 0.21, t = 8.52 s / 1202.35 tokens per second
llama-server | 10919.59.431.398 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 12288, progress = 0.25, t = 10.43 s / 1177.99 tokens per second
llama-server | 10920.01.386.759 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 14336, progress = 0.29, t = 12.38 s / 1158.35 tokens per second
llama-server | 10920.03.383.071 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 16384, progress = 0.33, t = 14.36 s / 1140.94 tokens per second
llama-server | 10920.05.415.838 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 18432, progress = 0.37, t = 16.39 s / 1124.82 tokens per second
llama-server | 10920.07.488.860 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 20480, progress = 0.41, t = 18.45 s / 1110.11 tokens per second
llama-server | 10920.09.601.761 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 22528, progress = 0.45, t = 20.55 s / 1096.26 tokens per second
llama-server | 10920.11.768.543 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 24576, progress = 0.49, t = 22.70 s / 1082.87 tokens per second
llama-server | 10920.13.959.073 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 26624, progress = 0.53, t = 24.89 s / 1069.79 tokens per second
llama-server | 10920.16.186.941 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 28672, progress = 0.57, t = 27.11 s / 1057.77 tokens per second
llama-server | 10920.18.460.164 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 30720, progress = 0.62, t = 29.36 s / 1046.29 tokens per second
llama-server | 10920.20.793.826 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 32768, progress = 0.66, t = 31.66 s / 1035.00 tokens per second
llama-server | 10920.23.126.937 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 34816, progress = 0.70, t = 34.02 s / 1023.44 tokens per second
llama-server | 10920.25.499.020 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 36864, progress = 0.74, t = 36.38 s / 1013.30 tokens per second
llama-server | 10920.27.905.351 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 38912, progress = 0.78, t = 38.78 s / 1003.43 tokens per second
llama-server | 10920.30.362.052 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 40960, progress = 0.82, t = 41.21 s / 993.91 tokens per second
llama-server | 10920.32.838.473 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 43008, progress = 0.86, t = 43.69 s / 984.29 tokens per second
llama-server | 10920.35.356.073 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 45056, progress = 0.90, t = 46.20 s / 975.31 tokens per second
llama-server | 10920.37.903.721 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 47104, progress = 0.94, t = 48.74 s / 966.40 tokens per second
llama-server | 10920.40.508.009 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 49152, progress = 0.99, t = 51.32 s / 957.85 tokens per second
llama-server | 10920.40.862.592 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 49351, progress = 0.99, t = 52.09 s / 947.39 tokens per second
llama-server | 10920.41.598.940 I slot print_timing: id 0 | task 2762623 | prompt processing, n_tokens = 49863, progress = 1.00, t = 52.53 s / 949.17 tokens per second
llama-server | 10920.44.984.327 I slot print_timing: id 0 | task 2762623 | n_gen = 100, tg = 30.99 t/s, tg_3s = 31.30 t/s
llama-server | 10920.48.053.772 I slot print_timing: id 0 | task 2762623 | n_gen = 186, tg = 29.53 t/s, tg_3s = 28.02 t/s
llama-server | 10920.51.130.404 I slot print_timing: id 0 | task 2762623 | n_gen = 309, tg = 32.97 t/s, tg_3s = 39.98 t/s
llama-server | 10920.54.138.797 I slot print_timing: id 0 | task 2762623 | n_gen = 448, tg = 36.20 t/s, tg_3s = 46.20 t/s
llama-server | 10920.57.216.396 I slot print_timing: id 0 | task 2762623 | n_gen = 535, tg = 34.61 t/s, tg_3s = 28.27 t/s
llama-server | 10921.00.220.883 I slot print_timing: id 0 | task 2762623 | n_gen = 635, tg = 34.40 t/s, tg_3s = 33.28 t/s
llama-server | 10921.03.298.256 I slot print_timing: id 0 | task 2762623 | n_gen = 724, tg = 33.61 t/s, tg_3s = 28.92 t/s
llama-server | 10921.06.377.471 I slot print_timing: id 0 | task 2762623 | n_gen = 800, tg = 32.50 t/s, tg_3s = 24.68 t/s
llama-server | 10921.09.388.235 I slot print_timing: id 0 | task 2762623 | n_gen = 881, tg = 31.89 t/s, tg_3s = 26.90 t/s
llama-server | 10921.12.469.118 I slot print_timing: id 0 | task 2762623 | n_gen = 959, tg = 31.23 t/s, tg_3s = 25.32 t/s
llama-server | 10921.15.558.351 I slot print_timing: id 0 | task 2762623 | n_gen = 1070, tg = 31.66 t/s, tg_3s = 35.93 t/s
llama-server | 10921.18.581.060 I slot print_timing: id 0 | task 2762623 | n_gen = 1175, tg = 31.91 t/s, tg_3s = 34.74 t/s
llama-server | 10921.20.179.947 I slot print_timing: id 0 | task 2762623 | prompt eval time = 53360.17 ms / 49867 tokens ( 1.07 ms per token, 934.54 tokens per second)
llama-server | 10921.20.179.954 I slot print_timing: id 0 | task 2762623 | eval time = 38390.42 ms / 1239 tokens ( 31.01 ms per token, 32.25 tokens per second)
llama-server | 10921.20.179.955 I slot print_timing: id 0 | task 2762623 | total time = 91750.59 ms / 51106 tokens
llama-server | 10921.20.179.956 I slot print_timing: id 0 | task 2762623 | graphs reused = 2676148
llama-server | 10921.20.179.960 I slot print_timing: id 0 | task 2762623 | draft acceptance = 0.40390 ( 828 accepted / 2050 generated), mean len = 3.02
llama-server | 10921.20.181.217 I slot release: id 0 | task 2762623 | stop processing: n_tokens = 51105, truncated = 0
llama-server | 10921.21.252.307 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 655201266102
llama-server | 10921.21.252.931 I slot launch_slot_: id 1 | task 2763061 | processing task, is_child = 0
llama-server | 10921.21.255.262 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2240.908 MiB)
llama-server | 10921.28.237.120 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.81 s / 1277.67 tokens per second
llama-server | 10921.30.090.127 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.65 s / 1231.93 tokens per second
llama-server | 10921.31.975.760 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.53 s / 1200.60 tokens per second
llama-server | 10921.33.907.435 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.45 s / 1175.71 tokens per second
llama-server | 10921.35.873.312 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.40 s / 1155.75 tokens per second
llama-server | 10921.37.880.252 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.40 s / 1137.96 tokens per second
llama-server | 10921.39.921.340 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 18432, progress = 0.37, t = 16.44 s / 1121.49 tokens per second
llama-server | 10921.42.000.379 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 20480, progress = 0.41, t = 18.50 s / 1106.76 tokens per second
llama-server | 10921.44.116.624 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 22528, progress = 0.45, t = 20.61 s / 1093.10 tokens per second
llama-server | 10921.46.285.901 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 24576, progress = 0.49, t = 22.76 s / 1079.90 tokens per second
llama-server | 10921.48.487.511 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 26624, progress = 0.53, t = 24.95 s / 1066.93 tokens per second
llama-server | 10921.50.719.217 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 28672, progress = 0.57, t = 27.18 s / 1054.82 tokens per second
llama-server | 10921.52.984.135 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 30720, progress = 0.61, t = 29.44 s / 1043.46 tokens per second
llama-server | 10921.55.319.613 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 32768, progress = 0.65, t = 31.73 s / 1032.69 tokens per second
llama-server | 10921.57.654.206 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 34816, progress = 0.69, t = 34.09 s / 1021.20 tokens per second
llama-server | 10922.00.027.780 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 36864, progress = 0.73, t = 36.46 s / 1011.19 tokens per second
llama-server | 10922.02.433.425 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 38912, progress = 0.77, t = 38.85 s / 1001.49 tokens per second
llama-server | 10922.04.893.375 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 40960, progress = 0.81, t = 41.29 s / 992.08 tokens per second
llama-server | 10922.07.372.132 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 43008, progress = 0.85, t = 43.77 s / 982.50 tokens per second
llama-server | 10922.09.888.288 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 45056, progress = 0.89, t = 46.28 s / 973.56 tokens per second
llama-server | 10922.12.438.121 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 47104, progress = 0.93, t = 48.82 s / 964.84 tokens per second
llama-server | 10922.15.043.876 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 49152, progress = 0.97, t = 51.40 s / 956.33 tokens per second
llama-server | 10922.16.078.820 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 49904, progress = 0.99, t = 52.79 s / 945.26 tokens per second
llama-server | 10922.16.815.357 I slot print_timing: id 1 | task 2763061 | prompt processing, n_tokens = 50416, progress = 1.00, t = 53.29 s / 946.01 tokens per second
llama-server | 10922.20.075.027 I slot print_timing: id 1 | task 2763061 | n_gen = 111, tg = 36.32 t/s, tg_3s = 36.64 t/s
llama-server | 10922.23.156.250 I slot print_timing: id 1 | task 2763061 | n_gen = 209, tg = 34.04 t/s, tg_3s = 31.81 t/s
llama-server | 10922.26.159.504 I slot print_timing: id 1 | task 2763061 | n_gen = 275, tg = 30.07 t/s, tg_3s = 21.98 t/s
llama-server | 10922.29.249.699 I slot print_timing: id 1 | task 2763061 | n_gen = 381, tg = 31.14 t/s, tg_3s = 34.30 t/s
llama-server | 10922.32.332.101 I slot print_timing: id 1 | task 2763061 | n_gen = 455, tg = 29.70 t/s, tg_3s = 24.01 t/s
llama-server | 10922.35.431.918 I slot print_timing: id 1 | task 2763061 | n_gen = 527, tg = 28.61 t/s, tg_3s = 23.23 t/s
llama-server | 10922.38.520.512 I slot print_timing: id 1 | task 2763061 | n_gen = 604, tg = 28.08 t/s, tg_3s = 24.93 t/s
llama-server | 10922.41.520.541 I slot print_timing: id 1 | task 2763061 | n_gen = 704, tg = 28.72 t/s, tg_3s = 33.33 t/s
llama-server | 10922.44.531.586 I slot print_timing: id 1 | task 2763061 | n_gen = 780, tg = 28.34 t/s, tg_3s = 25.24 t/s
llama-server | 10922.47.537.913 I slot print_timing: id 1 | task 2763061 | n_gen = 888, tg = 29.09 t/s, tg_3s = 35.92 t/s
llama-server | 10922.48.575.802 I slot print_timing: id 1 | task 2763061 | prompt eval time = 54162.42 ms / 50420 tokens ( 1.07 ms per token, 930.90 tokens per second)
llama-server | 10922.48.575.806 I slot print_timing: id 1 | task 2763061 | eval time = 31529.76 ms / 940 tokens ( 33.58 ms per token, 29.78 tokens per second)
llama-server | 10922.48.575.806 I slot print_timing: id 1 | task 2763061 | total time = 85692.18 ms / 51360 tokens
llama-server | 10922.48.575.807 I slot print_timing: id 1 | task 2763061 | graphs reused = 2676479
llama-server | 10922.48.575.810 I slot print_timing: id 1 | task 2763061 | draft acceptance = 0.35952 ( 604 accepted / 1680 generated), mean len = 2.80
llama-server | 10922.48.577.077 I slot release: id 1 | task 2763061 | stop processing: n_tokens = 51360, truncated = 0
llama-server | 10922.49.686.560 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 655296021269
llama-server | 10922.49.687.052 I slot launch_slot_: id 0 | task 2763425 | processing task, is_child = 0
llama-server | 10922.49.689.409 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2245.662 MiB)
llama-server | 10922.54.704.946 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 4096, progress = 0.08, t = 3.00 s / 1364.43 tokens per second
llama-server | 10922.56.522.436 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.81 s / 1277.58 tokens per second
llama-server | 10922.58.376.687 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.65 s / 1231.19 tokens per second
llama-server | 10923.00.263.264 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.53 s / 1199.83 tokens per second
llama-server | 10923.02.200.733 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.46 s / 1174.49 tokens per second
llama-server | 10923.04.168.096 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.42 s / 1154.63 tokens per second
llama-server | 10923.06.171.445 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.41 s / 1136.91 tokens per second
llama-server | 10923.08.210.925 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 18432, progress = 0.36, t = 16.44 s / 1120.94 tokens per second
llama-server | 10923.10.289.095 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 20480, progress = 0.40, t = 18.51 s / 1106.34 tokens per second
llama-server | 10923.12.408.005 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 22528, progress = 0.44, t = 20.62 s / 1092.64 tokens per second
llama-server | 10923.14.579.614 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 24576, progress = 0.48, t = 22.77 s / 1079.31 tokens per second
llama-server | 10923.16.775.776 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 26624, progress = 0.52, t = 24.97 s / 1066.40 tokens per second
llama-server | 10923.19.007.425 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 28672, progress = 0.56, t = 27.19 s / 1054.57 tokens per second
llama-server | 10923.21.275.010 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 30720, progress = 0.60, t = 29.45 s / 1043.21 tokens per second
llama-server | 10923.23.610.172 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 32768, progress = 0.64, t = 31.74 s / 1032.39 tokens per second
llama-server | 10923.25.944.597 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 34816, progress = 0.68, t = 34.10 s / 1020.98 tokens per second
llama-server | 10923.28.316.664 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 36864, progress = 0.72, t = 36.46 s / 1011.03 tokens per second
llama-server | 10923.30.723.842 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 38912, progress = 0.76, t = 38.86 s / 1001.29 tokens per second
llama-server | 10923.33.180.748 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 40960, progress = 0.80, t = 41.29 s / 991.91 tokens per second
llama-server | 10923.35.657.178 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 43008, progress = 0.84, t = 43.78 s / 982.43 tokens per second
llama-server | 10923.38.173.317 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 45056, progress = 0.88, t = 46.28 s / 973.56 tokens per second
llama-server | 10923.40.722.751 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 47104, progress = 0.92, t = 48.83 s / 964.75 tokens per second
llama-server | 10923.43.330.467 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 49152, progress = 0.96, t = 51.40 s / 956.28 tokens per second
llama-server | 10923.45.234.321 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 50606, progress = 0.99, t = 53.42 s / 947.41 tokens per second
llama-server | 10923.45.996.457 I slot print_timing: id 0 | task 2763425 | prompt processing, n_tokens = 51118, progress = 1.00, t = 54.17 s / 943.61 tokens per second
llama-server | 10923.50.200.452 I slot print_timing: id 0 | task 2763425 | n_gen = 100, tg = 24.95 t/s, tg_3s = 25.20 t/s
llama-server | 10923.53.294.895 I slot print_timing: id 0 | task 2763425 | n_gen = 197, tg = 27.75 t/s, tg_3s = 31.35 t/s
llama-server | 10923.56.299.789 I slot print_timing: id 0 | task 2763425 | n_gen = 323, tg = 31.99 t/s, tg_3s = 41.93 t/s
llama-server | 10923.56.693.174 I slot print_timing: id 0 | task 2763425 | prompt eval time = 55066.91 ms / 51122 tokens ( 1.08 ms per token, 928.36 tokens per second)
llama-server | 10923.56.693.177 I slot print_timing: id 0 | task 2763425 | eval time = 10460.52 ms / 345 tokens ( 30.41 ms per token, 32.89 tokens per second)
llama-server | 10923.56.693.178 I slot print_timing: id 0 | task 2763425 | total time = 65527.43 ms / 51467 tokens
llama-server | 10923.56.693.178 I slot print_timing: id 0 | task 2763425 | graphs reused = 2676587
llama-server | 10923.56.693.182 I slot print_timing: id 0 | task 2763425 | draft acceptance = 0.41982 ( 233 accepted / 555 generated), mean len = 3.10
llama-server | 10923.56.694.685 I slot release: id 0 | task 2763425 | stop processing: n_tokens = 51466, truncated = 0
llama-server | 10924.14.447.923 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 655384417129
llama-server | 10924.14.448.534 I slot launch_slot_: id 1 | task 2763564 | processing task, is_child = 0
llama-server | 10924.14.452.062 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2238.148 MiB)
llama-server | 10924.21.742.548 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.74 s / 1296.59 tokens per second
llama-server | 10924.23.568.014 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.56 s / 1249.70 tokens per second
llama-server | 10924.25.428.629 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.41 s / 1217.91 tokens per second
llama-server | 10924.27.327.317 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.30 s / 1193.27 tokens per second
llama-server | 10924.29.264.212 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.22 s / 1172.70 tokens per second
llama-server | 10924.31.243.982 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.19 s / 1154.56 tokens per second
llama-server | 10924.33.261.295 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 18432, progress = 0.36, t = 16.20 s / 1137.69 tokens per second
llama-server | 10924.35.321.858 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 20480, progress = 0.40, t = 18.25 s / 1122.17 tokens per second
llama-server | 10924.37.423.093 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 22528, progress = 0.44, t = 20.34 s / 1107.61 tokens per second
llama-server | 10924.39.581.395 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 24576, progress = 0.48, t = 22.48 s / 1093.46 tokens per second
llama-server | 10924.41.764.902 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 26624, progress = 0.52, t = 24.66 s / 1079.64 tokens per second
llama-server | 10924.43.987.782 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 28672, progress = 0.56, t = 26.87 s / 1066.91 tokens per second
llama-server | 10924.46.245.722 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 30720, progress = 0.60, t = 29.12 s / 1054.79 tokens per second
llama-server | 10924.48.574.808 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 32768, progress = 0.64, t = 31.41 s / 1043.32 tokens per second
llama-server | 10924.50.904.317 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 34816, progress = 0.68, t = 33.76 s / 1031.17 tokens per second
llama-server | 10924.53.272.526 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 36864, progress = 0.72, t = 36.12 s / 1020.56 tokens per second
llama-server | 10924.55.678.022 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 38912, progress = 0.76, t = 38.52 s / 1010.26 tokens per second
llama-server | 10924.58.135.226 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 40960, progress = 0.80, t = 40.95 s / 1000.26 tokens per second
llama-server | 10925.00.610.077 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 43008, progress = 0.84, t = 43.43 s / 990.24 tokens per second
llama-server | 10925.03.120.310 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 45056, progress = 0.88, t = 45.93 s / 980.92 tokens per second
llama-server | 10925.05.665.874 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 47104, progress = 0.92, t = 48.47 s / 971.81 tokens per second
llama-server | 10925.08.269.312 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 49152, progress = 0.96, t = 51.04 s / 962.96 tokens per second
llama-server | 10925.10.434.920 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 50804, progress = 0.99, t = 53.67 s / 946.59 tokens per second
llama-server | 10925.11.181.632 I slot print_timing: id 1 | task 2763564 | prompt processing, n_tokens = 51316, progress = 1.00, t = 54.07 s / 948.99 tokens per second
llama-server | 10925.14.579.665 I slot print_timing: id 1 | task 2763564 | n_gen = 100, tg = 30.93 t/s, tg_3s = 31.24 t/s
llama-server | 10925.17.591.441 I slot print_timing: id 1 | task 2763564 | n_gen = 190, tg = 30.42 t/s, tg_3s = 29.88 t/s
llama-server | 10925.20.594.887 I slot print_timing: id 1 | task 2763564 | n_gen = 287, tg = 31.03 t/s, tg_3s = 32.30 t/s
llama-server | 10925.23.688.715 I slot print_timing: id 1 | task 2763564 | n_gen = 381, tg = 30.87 t/s, tg_3s = 30.38 t/s
llama-server | 10925.26.704.299 I slot print_timing: id 1 | task 2763564 | n_gen = 453, tg = 29.49 t/s, tg_3s = 23.88 t/s
llama-server | 10925.29.713.971 I slot print_timing: id 1 | task 2763564 | n_gen = 548, tg = 29.83 t/s, tg_3s = 31.56 t/s
llama-server | 10925.32.719.265 I slot print_timing: id 1 | task 2763564 | n_gen = 639, tg = 29.90 t/s, tg_3s = 30.28 t/s
llama-server | 10925.35.747.826 I slot print_timing: id 1 | task 2763564 | n_gen = 724, tg = 29.67 t/s, tg_3s = 28.07 t/s
llama-server | 10925.38.760.809 I slot print_timing: id 1 | task 2763564 | n_gen = 818, tg = 29.84 t/s, tg_3s = 31.20 t/s
llama-server | 10925.41.788.652 I slot print_timing: id 1 | task 2763564 | n_gen = 929, tg = 30.52 t/s, tg_3s = 36.66 t/s
llama-server | 10925.44.806.615 I slot print_timing: id 1 | task 2763564 | n_gen = 1024, tg = 30.60 t/s, tg_3s = 31.48 t/s
llama-server | 10925.47.833.383 I slot print_timing: id 1 | task 2763564 | n_gen = 1123, tg = 30.78 t/s, tg_3s = 32.71 t/s
llama-server | 10925.50.868.241 I slot print_timing: id 1 | task 2763564 | n_gen = 1210, tg = 30.62 t/s, tg_3s = 28.67 t/s
llama-server | 10925.53.890.994 I slot print_timing: id 1 | task 2763564 | n_gen = 1297, tg = 30.49 t/s, tg_3s = 28.78 t/s
llama-server | 10925.56.920.402 I slot print_timing: id 1 | task 2763564 | n_gen = 1409, tg = 30.92 t/s, tg_3s = 36.97 t/s
llama-server | 10925.59.964.772 I slot print_timing: id 1 | task 2763564 | n_gen = 1506, tg = 30.98 t/s, tg_3s = 31.86 t/s
llama-server | 10926.02.992.895 I slot print_timing: id 1 | task 2763564 | n_gen = 1595, tg = 30.88 t/s, tg_3s = 29.39 t/s
llama-server | 10926.06.040.584 I slot print_timing: id 1 | task 2763564 | n_gen = 1688, tg = 30.86 t/s, tg_3s = 30.51 t/s
llama-server | 10926.09.077.219 I slot print_timing: id 1 | task 2763564 | n_gen = 1785, tg = 30.92 t/s, tg_3s = 31.94 t/s
llama-server | 10926.12.108.469 I slot print_timing: id 1 | task 2763564 | n_gen = 1866, tg = 30.71 t/s, tg_3s = 26.72 t/s
llama-server | 10926.15.162.028 I slot print_timing: id 1 | task 2763564 | n_gen = 1981, tg = 31.04 t/s, tg_3s = 37.66 t/s
llama-server | 10926.18.195.415 I slot print_timing: id 1 | task 2763564 | n_gen = 2056, tg = 30.76 t/s, tg_3s = 24.72 t/s
llama-server | 10926.21.229.870 I slot print_timing: id 1 | task 2763564 | n_gen = 2133, tg = 30.52 t/s, tg_3s = 25.38 t/s
llama-server | 10926.24.283.626 I slot print_timing: id 1 | task 2763564 | n_gen = 2224, tg = 30.49 t/s, tg_3s = 29.80 t/s
llama-server | 10926.27.324.493 I slot print_timing: id 1 | task 2763564 | n_gen = 2317, tg = 30.50 t/s, tg_3s = 30.58 t/s
llama-server | 10926.30.370.419 I slot print_timing: id 1 | task 2763564 | n_gen = 2399, tg = 30.36 t/s, tg_3s = 26.92 t/s
llama-server | 10926.33.431.911 I slot print_timing: id 1 | task 2763564 | n_gen = 2492, tg = 30.36 t/s, tg_3s = 30.38 t/s
llama-server | 10926.35.149.727 I slot print_timing: id 1 | task 2763564 | prompt eval time = 54916.31 ms / 51320 tokens ( 1.07 ms per token, 934.51 tokens per second)
llama-server | 10926.35.149.731 I slot print_timing: id 1 | task 2763564 | eval time = 83770.47 ms / 2570 tokens ( 32.61 ms per token, 30.67 tokens per second)
llama-server | 10926.35.149.731 I slot print_timing: id 1 | task 2763564 | total time = 138686.78 ms / 53890 tokens
llama-server | 10926.35.149.732 I slot print_timing: id 1 | task 2763564 | graphs reused = 2677461
llama-server | 10926.35.149.734 I slot print_timing: id 1 | task 2763564 | draft acceptance = 0.38056 ( 1684 accepted / 4425 generated), mean len = 2.90
llama-server | 10926.35.151.358 I slot release: id 1 | task 2763564 | stop processing: n_tokens = 53889, truncated = 0
llama-server | 10926.46.426.872 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 655452534737
llama-server | 10926.46.427.334 I slot launch_slot_: id 0 | task 2764477 | processing task, is_child = 0
llama-server | 10926.46.430.741 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2268.205 MiB)
llama-server | 10926.53.636.321 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.78 s / 1285.98 tokens per second
llama-server | 10926.55.471.108 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.60 s / 1240.44 tokens per second
llama-server | 10926.57.340.978 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.47 s / 1209.42 tokens per second
llama-server | 10926.59.250.611 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.37 s / 1185.44 tokens per second
llama-server | 10927.01.198.389 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.30 s / 1165.12 tokens per second
llama-server | 10927.03.188.556 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.28 s / 1147.28 tokens per second
llama-server | 10927.05.216.072 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 18432, progress = 0.36, t = 16.30 s / 1130.70 tokens per second
llama-server | 10927.07.284.390 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 20480, progress = 0.40, t = 18.36 s / 1115.52 tokens per second
llama-server | 10927.09.393.933 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 22528, progress = 0.44, t = 20.46 s / 1101.28 tokens per second
llama-server | 10927.11.560.209 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 24576, progress = 0.48, t = 22.60 s / 1087.38 tokens per second
llama-server | 10927.13.749.551 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 26624, progress = 0.52, t = 24.79 s / 1073.89 tokens per second
llama-server | 10927.15.975.138 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 28672, progress = 0.56, t = 27.01 s / 1061.60 tokens per second
llama-server | 10927.18.236.043 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 30720, progress = 0.60, t = 29.26 s / 1049.87 tokens per second
llama-server | 10927.20.568.044 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 32768, progress = 0.64, t = 31.55 s / 1038.68 tokens per second
llama-server | 10927.22.900.209 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 34816, progress = 0.68, t = 33.91 s / 1026.81 tokens per second
llama-server | 10927.25.270.782 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 36864, progress = 0.72, t = 36.27 s / 1016.48 tokens per second
llama-server | 10927.27.675.083 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 38912, progress = 0.76, t = 38.66 s / 1006.44 tokens per second
llama-server | 10927.30.133.048 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 40960, progress = 0.80, t = 41.09 s / 996.72 tokens per second
llama-server | 10927.32.611.197 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 43008, progress = 0.84, t = 43.58 s / 986.86 tokens per second
llama-server | 10927.35.127.103 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 45056, progress = 0.88, t = 46.09 s / 977.65 tokens per second
llama-server | 10927.37.675.612 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 47104, progress = 0.92, t = 48.63 s / 968.68 tokens per second
llama-server | 10927.40.281.504 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 49152, progress = 0.95, t = 51.20 s / 959.94 tokens per second
llama-server | 10927.42.654.092 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 50955, progress = 0.99, t = 53.83 s / 946.51 tokens per second
llama-server | 10927.43.406.571 I slot print_timing: id 0 | task 2764477 | prompt processing, n_tokens = 51467, progress = 1.00, t = 54.44 s / 945.35 tokens per second
llama-server | 10927.44.888.126 I slot print_timing: id 0 | task 2764477 | prompt eval time = 55331.00 ms / 51471 tokens ( 1.07 ms per token, 930.24 tokens per second)
llama-server | 10927.44.888.129 I slot print_timing: id 0 | task 2764477 | eval time = 1241.98 ms / 53 tokens ( 23.88 ms per token, 41.87 tokens per second)
llama-server | 10927.44.888.130 I slot print_timing: id 0 | task 2764477 | total time = 56572.98 ms / 51524 tokens
llama-server | 10927.44.888.130 I slot print_timing: id 0 | task 2764477 | graphs reused = 2677473
llama-server | 10927.44.888.134 I slot print_timing: id 0 | task 2764477 | draft acceptance = 0.61538 ( 40 accepted / 65 generated), mean len = 4.08
llama-server | 10927.44.889.457 I slot release: id 0 | task 2764477 | stop processing: n_tokens = 51524, truncated = 0
llama-server | 10927.45.867.576 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 655610991411
llama-server | 10927.45.868.068 I slot launch_slot_: id 1 | task 2764518 | processing task, is_child = 0
llama-server | 10927.45.870.362 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2276.683 MiB)
llama-server | 10927.51.311.368 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 4096, progress = 0.08, t = 3.00 s / 1364.95 tokens per second
llama-server | 10927.53.124.895 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.80 s / 1278.76 tokens per second
llama-server | 10927.54.977.823 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.64 s / 1233.22 tokens per second
llama-server | 10927.56.860.690 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.52 s / 1201.59 tokens per second
llama-server | 10927.58.792.064 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.45 s / 1176.38 tokens per second
llama-server | 10928.00.752.431 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.39 s / 1156.63 tokens per second
llama-server | 10928.02.751.931 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.38 s / 1139.15 tokens per second
llama-server | 10928.04.790.080 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 18432, progress = 0.36, t = 16.41 s / 1123.00 tokens per second
llama-server | 10928.06.868.302 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 20480, progress = 0.40, t = 18.48 s / 1108.20 tokens per second
llama-server | 10928.08.984.549 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 22528, progress = 0.44, t = 20.59 s / 1094.36 tokens per second
llama-server | 10928.11.154.230 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 24576, progress = 0.48, t = 22.73 s / 1080.99 tokens per second
llama-server | 10928.13.349.975 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 26624, progress = 0.52, t = 24.93 s / 1067.93 tokens per second
llama-server | 10928.15.581.153 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 28672, progress = 0.56, t = 27.15 s / 1055.93 tokens per second
llama-server | 10928.17.846.114 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 30720, progress = 0.60, t = 29.41 s / 1044.54 tokens per second
llama-server | 10928.20.181.276 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 32768, progress = 0.64, t = 31.70 s / 1033.63 tokens per second
llama-server | 10928.22.514.267 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 34816, progress = 0.68, t = 34.06 s / 1022.15 tokens per second
llama-server | 10928.24.886.639 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 36864, progress = 0.72, t = 36.42 s / 1012.11 tokens per second
llama-server | 10928.27.291.879 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 38912, progress = 0.76, t = 38.82 s / 1002.36 tokens per second
llama-server | 10928.29.750.784 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 40960, progress = 0.79, t = 41.25 s / 992.89 tokens per second
llama-server | 10928.32.226.607 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 43008, progress = 0.83, t = 43.74 s / 983.31 tokens per second
llama-server | 10928.34.739.053 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 45056, progress = 0.87, t = 46.24 s / 974.41 tokens per second
llama-server | 10928.37.288.106 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 47104, progress = 0.91, t = 48.78 s / 965.64 tokens per second
llama-server | 10928.39.896.687 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 49152, progress = 0.95, t = 51.36 s / 957.07 tokens per second
llama-server | 10928.42.365.919 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 51013, progress = 0.99, t = 53.99 s / 944.87 tokens per second
llama-server | 10928.43.123.518 I slot print_timing: id 1 | task 2764518 | prompt processing, n_tokens = 51525, progress = 1.00, t = 54.69 s / 942.05 tokens per second
llama-server | 10928.46.391.139 I slot print_timing: id 1 | task 2764518 | n_gen = 132, tg = 43.25 t/s, tg_3s = 43.58 t/s
llama-server | 10928.48.386.963 I slot print_timing: id 1 | task 2764518 | prompt eval time = 55587.75 ms / 51529 tokens ( 1.08 ms per token, 926.98 tokens per second)
llama-server | 10928.48.386.966 I slot print_timing: id 1 | task 2764518 | eval time = 5024.42 ms / 242 tokens ( 20.85 ms per token, 47.97 tokens per second)
llama-server | 10928.48.386.967 I slot print_timing: id 1 | task 2764518 | total time = 60612.18 ms / 51771 tokens
llama-server | 10928.48.386.967 I slot print_timing: id 1 | task 2764518 | graphs reused = 2677524
llama-server | 10928.48.386.970 I slot print_timing: id 1 | task 2764518 | draft acceptance = 0.70943 ( 188 accepted / 265 generated), mean len = 4.55
llama-server | 10928.48.388.319 I slot release: id 1 | task 2764518 | stop processing: n_tokens = 51770, truncated = 0
llama-server | 10928.50.903.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 655680729509
llama-server | 10928.50.904.528 I slot launch_slot_: id 0 | task 2764599 | processing task, is_child = 0
llama-server | 10928.50.906.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2280.208 MiB)
llama-server | 10928.57.914.810 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.78 s / 1284.21 tokens per second
llama-server | 10928.59.763.178 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.62 s / 1237.66 tokens per second
llama-server | 10929.01.640.829 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.49 s / 1205.46 tokens per second
llama-server | 10929.03.563.336 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.41 s / 1180.70 tokens per second
llama-server | 10929.05.522.699 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.35 s / 1160.57 tokens per second
llama-server | 10929.07.521.011 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.34 s / 1142.41 tokens per second
llama-server | 10929.09.556.874 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 18432, progress = 0.36, t = 16.37 s / 1126.08 tokens per second
llama-server | 10929.11.630.910 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 20480, progress = 0.40, t = 18.43 s / 1110.94 tokens per second
llama-server | 10929.13.744.052 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 22528, progress = 0.44, t = 20.54 s / 1097.03 tokens per second
llama-server | 10929.15.914.139 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 24576, progress = 0.48, t = 22.68 s / 1083.51 tokens per second
llama-server | 10929.18.107.820 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 26624, progress = 0.52, t = 24.88 s / 1070.11 tokens per second
llama-server | 10929.20.338.002 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 28672, progress = 0.56, t = 27.10 s / 1057.98 tokens per second
llama-server | 10929.22.601.933 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 30720, progress = 0.60, t = 29.36 s / 1046.46 tokens per second
llama-server | 10929.24.937.992 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 32768, progress = 0.64, t = 31.65 s / 1035.42 tokens per second
llama-server | 10929.27.276.957 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 34816, progress = 0.68, t = 34.01 s / 1023.70 tokens per second
llama-server | 10929.29.649.806 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 36864, progress = 0.72, t = 36.37 s / 1013.46 tokens per second
llama-server | 10929.32.055.213 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 38912, progress = 0.76, t = 38.77 s / 1003.58 tokens per second
llama-server | 10929.34.512.493 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 40960, progress = 0.80, t = 41.21 s / 994.05 tokens per second
llama-server | 10929.37.000.270 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 43008, progress = 0.84, t = 43.69 s / 984.39 tokens per second
llama-server | 10929.39.515.669 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 45056, progress = 0.88, t = 46.21 s / 975.12 tokens per second
llama-server | 10929.42.063.696 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 47104, progress = 0.92, t = 48.75 s / 966.33 tokens per second
llama-server | 10929.44.669.889 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 49152, progress = 0.96, t = 51.32 s / 957.73 tokens per second
llama-server | 10929.46.951.342 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 50870, progress = 0.99, t = 53.95 s / 942.88 tokens per second
llama-server | 10929.47.697.732 I slot print_timing: id 0 | task 2764599 | prompt processing, n_tokens = 51382, progress = 1.00, t = 54.47 s / 943.33 tokens per second
llama-server | 10929.50.924.943 I slot print_timing: id 0 | task 2764599 | n_gen = 107, tg = 34.96 t/s, tg_3s = 35.28 t/s
llama-server | 10929.52.804.689 I slot print_timing: id 0 | task 2764599 | prompt eval time = 55307.60 ms / 51386 tokens ( 1.08 ms per token, 929.09 tokens per second)
llama-server | 10929.52.804.692 I slot print_timing: id 0 | task 2764599 | eval time = 4911.98 ms / 210 tokens ( 23.50 ms per token, 42.55 tokens per second)
llama-server | 10929.52.804.692 I slot print_timing: id 0 | task 2764599 | total time = 60219.57 ms / 51596 tokens
llama-server | 10929.52.804.693 I slot print_timing: id 0 | task 2764599 | graphs reused = 2677574
llama-server | 10929.52.804.696 I slot print_timing: id 0 | task 2764599 | draft acceptance = 0.60385 ( 157 accepted / 260 generated), mean len = 4.02
llama-server | 10929.52.806.021 I slot release: id 0 | task 2764599 | stop processing: n_tokens = 51595, truncated = 0
llama-server | 10930.07.770.926 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 655744228371
llama-server | 10930.07.771.820 I slot launch_slot_: id 1 | task 2764679 | processing task, is_child = 0
llama-server | 10930.07.776.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2360.770 MiB)
llama-server | 10930.14.685.408 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.73 s / 1297.61 tokens per second
llama-server | 10930.16.512.026 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.55 s / 1250.58 tokens per second
llama-server | 10930.18.378.046 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.40 s / 1218.42 tokens per second
llama-server | 10930.20.276.995 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.30 s / 1193.15 tokens per second
llama-server | 10930.22.214.992 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.23 s / 1172.45 tokens per second
llama-server | 10930.24.194.132 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.19 s / 1154.33 tokens per second
llama-server | 10930.26.212.007 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 18432, progress = 0.36, t = 16.20 s / 1137.48 tokens per second
llama-server | 10930.28.271.114 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 20480, progress = 0.40, t = 18.25 s / 1122.09 tokens per second
llama-server | 10930.30.373.443 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 22528, progress = 0.44, t = 20.34 s / 1107.49 tokens per second
llama-server | 10930.32.530.486 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 24576, progress = 0.48, t = 22.48 s / 1093.33 tokens per second
llama-server | 10930.34.711.515 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 26624, progress = 0.52, t = 24.66 s / 1079.62 tokens per second
llama-server | 10930.36.932.444 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 28672, progress = 0.56, t = 26.87 s / 1067.03 tokens per second
llama-server | 10930.39.185.381 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 30720, progress = 0.59, t = 29.12 s / 1055.11 tokens per second
llama-server | 10930.41.511.528 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 32768, progress = 0.63, t = 31.40 s / 1043.67 tokens per second
llama-server | 10930.43.839.091 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 34816, progress = 0.67, t = 33.75 s / 1031.58 tokens per second
llama-server | 10930.46.204.189 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 36864, progress = 0.71, t = 36.11 s / 1021.01 tokens per second
llama-server | 10930.48.603.655 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 38912, progress = 0.75, t = 38.50 s / 1010.77 tokens per second
llama-server | 10930.51.057.884 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 40960, progress = 0.79, t = 40.92 s / 1000.86 tokens per second
llama-server | 10930.53.531.012 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 43008, progress = 0.83, t = 43.41 s / 990.84 tokens per second
llama-server | 10930.56.039.238 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 45056, progress = 0.87, t = 45.90 s / 981.53 tokens per second
llama-server | 10930.58.584.484 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 47104, progress = 0.91, t = 48.44 s / 972.38 tokens per second
llama-server | 10931.01.188.047 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 49152, progress = 0.95, t = 51.01 s / 963.51 tokens per second
llama-server | 10931.03.782.415 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 51139, progress = 0.99, t = 53.64 s / 953.32 tokens per second
llama-server | 10931.04.535.456 I slot print_timing: id 1 | task 2764679 | prompt processing, n_tokens = 51651, progress = 1.00, t = 54.48 s / 948.16 tokens per second
llama-server | 10931.07.757.587 I slot print_timing: id 1 | task 2764679 | n_gen = 101, tg = 33.01 t/s, tg_3s = 33.33 t/s
llama-server | 10931.10.849.238 I slot print_timing: id 1 | task 2764679 | n_gen = 195, tg = 31.69 t/s, tg_3s = 30.40 t/s
llama-server | 10931.13.937.756 I slot print_timing: id 1 | task 2764679 | n_gen = 296, tg = 32.03 t/s, tg_3s = 32.70 t/s
llama-server | 10931.16.947.009 I slot print_timing: id 1 | task 2764679 | n_gen = 387, tg = 31.59 t/s, tg_3s = 30.24 t/s
llama-server | 10931.20.040.202 I slot print_timing: id 1 | task 2764679 | n_gen = 468, tg = 30.50 t/s, tg_3s = 26.19 t/s
llama-server | 10931.23.046.292 I slot print_timing: id 1 | task 2764679 | n_gen = 557, tg = 30.35 t/s, tg_3s = 29.61 t/s
llama-server | 10931.26.075.016 I slot print_timing: id 1 | task 2764679 | n_gen = 660, tg = 30.87 t/s, tg_3s = 34.01 t/s
llama-server | 10931.29.078.225 I slot print_timing: id 1 | task 2764679 | n_gen = 720, tg = 29.53 t/s, tg_3s = 19.98 t/s
llama-server | 10931.32.095.538 I slot print_timing: id 1 | task 2764679 | n_gen = 818, tg = 29.85 t/s, tg_3s = 32.48 t/s
llama-server | 10931.35.129.026 I slot print_timing: id 1 | task 2764679 | n_gen = 920, tg = 30.23 t/s, tg_3s = 33.62 t/s
llama-server | 10931.38.144.969 I slot print_timing: id 1 | task 2764679 | n_gen = 1009, tg = 30.16 t/s, tg_3s = 29.51 t/s
llama-server | 10931.41.181.408 I slot print_timing: id 1 | task 2764679 | n_gen = 1097, tg = 30.07 t/s, tg_3s = 28.98 t/s
llama-server | 10931.44.202.138 I slot print_timing: id 1 | task 2764679 | n_gen = 1177, tg = 29.79 t/s, tg_3s = 26.48 t/s
llama-server | 10931.47.222.066 I slot print_timing: id 1 | task 2764679 | n_gen = 1261, tg = 29.65 t/s, tg_3s = 27.82 t/s
llama-server | 10931.50.261.897 I slot print_timing: id 1 | task 2764679 | n_gen = 1360, tg = 29.85 t/s, tg_3s = 32.57 t/s
llama-server | 10931.53.290.720 I slot print_timing: id 1 | task 2764679 | n_gen = 1458, tg = 30.00 t/s, tg_3s = 32.36 t/s
llama-server | 10931.56.314.986 I slot print_timing: id 1 | task 2764679 | n_gen = 1552, tg = 30.07 t/s, tg_3s = 31.08 t/s
llama-server | 10931.58.611.803 I slot print_timing: id 1 | task 2764679 | prompt eval time = 55316.80 ms / 51655 tokens ( 1.07 ms per token, 933.80 tokens per second)
llama-server | 10931.58.611.806 I slot print_timing: id 1 | task 2764679 | eval time = 53883.83 ms / 1652 tokens ( 32.64 ms per token, 30.64 tokens per second)
llama-server | 10931.58.611.806 I slot print_timing: id 1 | task 2764679 | total time = 109200.63 ms / 53307 tokens
llama-server | 10931.58.611.807 I slot print_timing: id 1 | task 2764679 | graphs reused = 2678137
llama-server | 10931.58.611.810 I slot print_timing: id 1 | task 2764679 | draft acceptance = 0.37828 ( 1080 accepted / 2855 generated), mean len = 2.89
llama-server | 10931.58.613.144 I slot release: id 1 | task 2764679 | stop processing: n_tokens = 53306, truncated = 0
llama-server | 10931.59.819.501 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 655808646073
llama-server | 10931.59.820.433 I slot launch_slot_: id 0 | task 2765278 | processing task, is_child = 0
llama-server | 10931.59.822.822 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2282.136 MiB)
llama-server | 10932.07.424.991 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.80 s / 1279.32 tokens per second
llama-server | 10932.09.284.034 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.64 s / 1232.97 tokens per second
llama-server | 10932.11.172.179 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.53 s / 1200.44 tokens per second
llama-server | 10932.13.098.710 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.45 s / 1176.20 tokens per second
llama-server | 10932.15.071.839 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.41 s / 1154.84 tokens per second
llama-server | 10932.17.075.660 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 16384, progress = 0.31, t = 14.40 s / 1137.47 tokens per second
llama-server | 10932.19.120.683 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 18432, progress = 0.35, t = 16.44 s / 1121.40 tokens per second
llama-server | 10932.21.202.202 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 20480, progress = 0.39, t = 18.51 s / 1106.34 tokens per second
llama-server | 10932.23.327.682 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 22528, progress = 0.43, t = 20.62 s / 1092.54 tokens per second
llama-server | 10932.25.499.413 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 24576, progress = 0.47, t = 22.78 s / 1078.91 tokens per second
llama-server | 10932.27.694.243 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 26624, progress = 0.51, t = 24.97 s / 1066.06 tokens per second
llama-server | 10932.29.926.359 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 28672, progress = 0.55, t = 27.20 s / 1054.21 tokens per second
llama-server | 10932.32.191.746 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 30720, progress = 0.59, t = 29.46 s / 1042.91 tokens per second
llama-server | 10932.34.528.118 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 32768, progress = 0.63, t = 31.75 s / 1032.16 tokens per second
llama-server | 10932.36.865.350 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 34816, progress = 0.67, t = 34.11 s / 1020.72 tokens per second
llama-server | 10932.39.239.313 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 36864, progress = 0.71, t = 36.47 s / 1010.71 tokens per second
llama-server | 10932.41.646.027 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 38912, progress = 0.75, t = 38.87 s / 1001.01 tokens per second
llama-server | 10932.44.106.525 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 40960, progress = 0.79, t = 41.31 s / 991.61 tokens per second
llama-server | 10932.46.586.108 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 43008, progress = 0.83, t = 43.79 s / 982.04 tokens per second
llama-server | 10932.49.099.533 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 45056, progress = 0.86, t = 46.30 s / 973.17 tokens per second
llama-server | 10932.51.648.098 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 47104, progress = 0.90, t = 48.84 s / 964.47 tokens per second
llama-server | 10932.54.255.579 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 49152, progress = 0.94, t = 51.41 s / 955.99 tokens per second
llama-server | 10932.56.875.992 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 51200, progress = 0.98, t = 54.05 s / 947.30 tokens per second
llama-server | 10932.57.435.095 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 51579, progress = 0.99, t = 54.82 s / 940.95 tokens per second
llama-server | 10932.58.190.015 I slot print_timing: id 0 | task 2765278 | prompt processing, n_tokens = 52091, progress = 1.00, t = 55.46 s / 939.22 tokens per second
llama-server | 10933.00.857.676 I slot print_timing: id 0 | task 2765278 | prompt eval time = 56313.39 ms / 52095 tokens ( 1.08 ms per token, 925.09 tokens per second)
llama-server | 10933.00.857.679 I slot print_timing: id 0 | task 2765278 | eval time = 2468.03 ms / 92 tokens ( 27.12 ms per token, 36.87 tokens per second)
llama-server | 10933.00.857.680 I slot print_timing: id 0 | task 2765278 | total time = 58781.42 ms / 52187 tokens
llama-server | 10933.00.857.681 I slot print_timing: id 0 | task 2765278 | graphs reused = 2678162
llama-server | 10933.00.857.684 I slot print_timing: id 0 | task 2765278 | draft acceptance = 0.50000 ( 65 accepted / 130 generated), mean len = 3.50
llama-server | 10933.00.859.039 I slot release: id 0 | task 2765278 | stop processing: n_tokens = 52186, truncated = 0
llama-server | 10933.01.836.849 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 655934453196
llama-server | 10933.01.837.471 I slot launch_slot_: id 1 | task 2765333 | processing task, is_child = 0
llama-server | 10933.01.839.831 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2290.315 MiB)
llama-server | 10933.09.253.355 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.79 s / 1281.90 tokens per second
llama-server | 10933.11.105.075 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.63 s / 1235.33 tokens per second
llama-server | 10933.12.999.944 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.52 s / 1201.56 tokens per second
llama-server | 10933.14.918.691 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.43 s / 1177.85 tokens per second
llama-server | 10933.16.874.507 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 14336, progress = 0.27, t = 12.38 s / 1158.10 tokens per second
llama-server | 10933.18.874.206 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 16384, progress = 0.31, t = 14.36 s / 1140.62 tokens per second
llama-server | 10933.20.909.369 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 18432, progress = 0.35, t = 16.39 s / 1124.30 tokens per second
llama-server | 10933.22.983.888 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 20480, progress = 0.39, t = 18.46 s / 1109.57 tokens per second
llama-server | 10933.25.098.036 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 22528, progress = 0.43, t = 20.56 s / 1095.71 tokens per second
llama-server | 10933.27.266.044 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 24576, progress = 0.47, t = 22.71 s / 1082.27 tokens per second
llama-server | 10933.29.457.151 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 26624, progress = 0.51, t = 24.90 s / 1069.25 tokens per second
llama-server | 10933.31.684.086 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 28672, progress = 0.55, t = 27.12 s / 1057.31 tokens per second
llama-server | 10933.33.945.672 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 30720, progress = 0.59, t = 29.37 s / 1045.90 tokens per second
llama-server | 10933.36.286.616 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 32768, progress = 0.63, t = 31.66 s / 1035.04 tokens per second
llama-server | 10933.38.620.858 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 34816, progress = 0.67, t = 34.03 s / 1023.16 tokens per second
llama-server | 10933.40.991.536 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 36864, progress = 0.71, t = 36.39 s / 1013.09 tokens per second
llama-server | 10933.43.397.499 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 38912, progress = 0.75, t = 38.79 s / 1003.26 tokens per second
llama-server | 10933.45.855.429 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 40960, progress = 0.78, t = 41.22 s / 993.74 tokens per second
llama-server | 10933.48.334.016 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 43008, progress = 0.82, t = 43.70 s / 984.08 tokens per second
llama-server | 10933.50.848.717 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 45056, progress = 0.86, t = 46.21 s / 975.06 tokens per second
llama-server | 10933.53.397.206 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 47104, progress = 0.90, t = 48.75 s / 966.26 tokens per second
llama-server | 10933.56.002.583 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 49152, progress = 0.94, t = 51.32 s / 957.69 tokens per second
llama-server | 10933.58.620.929 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 51200, progress = 0.98, t = 53.96 s / 948.93 tokens per second
llama-server | 10933.59.281.196 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 51696, progress = 0.99, t = 54.72 s / 944.67 tokens per second
llama-server | 10934.00.034.015 I slot print_timing: id 1 | task 2765333 | prompt processing, n_tokens = 52208, progress = 1.00, t = 55.47 s / 941.23 tokens per second
llama-server | 10934.04.167.753 I slot print_timing: id 1 | task 2765333 | n_gen = 100, tg = 25.45 t/s, tg_3s = 25.71 t/s
llama-server | 10934.06.614.509 I slot print_timing: id 1 | task 2765333 | prompt eval time = 56363.48 ms / 52212 tokens ( 1.08 ms per token, 926.34 tokens per second)
llama-server | 10934.06.614.512 I slot print_timing: id 1 | task 2765333 | eval time = 6336.14 ms / 176 tokens ( 36.21 ms per token, 27.62 tokens per second)
llama-server | 10934.06.614.512 I slot print_timing: id 1 | task 2765333 | total time = 62699.62 ms / 52388 tokens
llama-server | 10934.06.614.513 I slot print_timing: id 1 | task 2765333 | graphs reused = 2678227
llama-server | 10934.06.614.516 I slot print_timing: id 1 | task 2765333 | draft acceptance = 0.32239 ( 108 accepted / 335 generated), mean len = 2.61
llama-server | 10934.06.615.898 I slot release: id 1 | task 2765333 | stop processing: n_tokens = 52387, truncated = 0
llama-server | 10934.07.705.196 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 655996699091
llama-server | 10934.07.705.943 I slot launch_slot_: id 0 | task 2765429 | processing task, is_child = 0
llama-server | 10934.07.709.105 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2284.497 MiB)
llama-server | 10934.14.663.351 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.79 s / 1281.65 tokens per second
llama-server | 10934.16.514.271 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.63 s / 1235.05 tokens per second
llama-server | 10934.18.396.373 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.51 s / 1203.41 tokens per second
llama-server | 10934.20.322.695 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 12288, progress = 0.23, t = 10.43 s / 1178.47 tokens per second
llama-server | 10934.22.284.862 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 14336, progress = 0.27, t = 12.37 s / 1158.47 tokens per second
llama-server | 10934.24.286.472 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 16384, progress = 0.31, t = 14.37 s / 1140.46 tokens per second
llama-server | 10934.26.322.062 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 18432, progress = 0.35, t = 16.40 s / 1124.18 tokens per second
llama-server | 10934.28.408.757 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 20480, progress = 0.39, t = 18.46 s / 1109.30 tokens per second
llama-server | 10934.30.525.392 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 22528, progress = 0.43, t = 20.58 s / 1094.85 tokens per second
llama-server | 10934.32.694.768 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 24576, progress = 0.47, t = 22.72 s / 1081.46 tokens per second
llama-server | 10934.34.887.898 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 26624, progress = 0.51, t = 24.92 s / 1068.41 tokens per second
llama-server | 10934.37.119.177 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 28672, progress = 0.55, t = 27.14 s / 1056.45 tokens per second
llama-server | 10934.39.385.348 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 30720, progress = 0.59, t = 29.40 s / 1044.96 tokens per second
llama-server | 10934.41.720.740 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 32768, progress = 0.63, t = 31.69 s / 1034.00 tokens per second
llama-server | 10934.44.055.854 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 34816, progress = 0.67, t = 34.05 s / 1022.43 tokens per second
llama-server | 10934.46.427.956 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 36864, progress = 0.70, t = 36.41 s / 1012.37 tokens per second
llama-server | 10934.48.836.380 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 38912, progress = 0.74, t = 38.81 s / 1002.53 tokens per second
llama-server | 10934.51.297.622 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 40960, progress = 0.78, t = 41.25 s / 993.00 tokens per second
llama-server | 10934.53.776.665 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 43008, progress = 0.82, t = 43.74 s / 983.35 tokens per second
llama-server | 10934.56.291.858 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 45056, progress = 0.86, t = 46.24 s / 974.35 tokens per second
llama-server | 10934.58.840.975 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 47104, progress = 0.90, t = 48.78 s / 965.58 tokens per second
llama-server | 10935.01.448.713 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 49152, progress = 0.94, t = 51.36 s / 957.02 tokens per second
llama-server | 10935.04.069.795 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 51200, progress = 0.98, t = 53.99 s / 948.28 tokens per second
llama-server | 10935.04.940.782 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 51822, progress = 0.99, t = 55.39 s / 935.66 tokens per second
llama-server | 10935.05.690.924 I slot print_timing: id 0 | task 2765429 | prompt processing, n_tokens = 52334, progress = 1.00, t = 55.72 s / 939.25 tokens per second
llama-server | 10935.09.290.655 I slot print_timing: id 0 | task 2765429 | n_gen = 100, tg = 29.12 t/s, tg_3s = 29.41 t/s
llama-server | 10935.12.323.455 I slot print_timing: id 0 | task 2765429 | n_gen = 210, tg = 32.49 t/s, tg_3s = 36.27 t/s
llama-server | 10935.15.334.273 I slot print_timing: id 0 | task 2765429 | n_gen = 294, tg = 31.03 t/s, tg_3s = 27.90 t/s
llama-server | 10935.18.362.660 I slot print_timing: id 0 | task 2765429 | n_gen = 404, tg = 32.31 t/s, tg_3s = 36.32 t/s
llama-server | 10935.21.387.558 I slot print_timing: id 0 | task 2765429 | n_gen = 490, tg = 31.56 t/s, tg_3s = 28.43 t/s
llama-server | 10935.24.400.755 I slot print_timing: id 0 | task 2765429 | n_gen = 561, tg = 30.25 t/s, tg_3s = 23.56 t/s
llama-server | 10935.27.417.832 I slot print_timing: id 0 | task 2765429 | n_gen = 648, tg = 30.06 t/s, tg_3s = 28.84 t/s
llama-server | 10935.30.454.583 I slot print_timing: id 0 | task 2765429 | n_gen = 723, tg = 29.39 t/s, tg_3s = 24.70 t/s
llama-server | 10935.33.479.176 I slot print_timing: id 0 | task 2765429 | n_gen = 796, tg = 28.82 t/s, tg_3s = 24.14 t/s
llama-server | 10935.36.499.027 I slot print_timing: id 0 | task 2765429 | n_gen = 871, tg = 28.42 t/s, tg_3s = 24.84 t/s
llama-server | 10935.38.602.424 I slot print_timing: id 0 | task 2765429 | prompt eval time = 56566.43 ms / 52338 tokens ( 1.08 ms per token, 925.25 tokens per second)
llama-server | 10935.38.602.428 I slot print_timing: id 0 | task 2765429 | eval time = 32711.33 ms / 965 tokens ( 33.93 ms per token, 29.47 tokens per second)
llama-server | 10935.38.602.428 I slot print_timing: id 0 | task 2765429 | total time = 89277.76 ms / 53303 tokens
llama-server | 10935.38.602.429 I slot print_timing: id 0 | task 2765429 | graphs reused = 2678568
llama-server | 10935.38.602.431 I slot print_timing: id 0 | task 2765429 | draft acceptance = 0.35723 ( 618 accepted / 1730 generated), mean len = 2.79
llama-server | 10935.38.603.801 I slot release: id 0 | task 2765429 | stop processing: n_tokens = 53302, truncated = 0
llama-server | 10935.39.807.555 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 656062455950
llama-server | 10935.39.808.079 I slot launch_slot_: id 1 | task 2765804 | processing task, is_child = 0
llama-server | 10935.39.810.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2341.386 MiB)
llama-server | 10935.47.387.596 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.80 s / 1279.02 tokens per second
llama-server | 10935.49.242.826 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.65 s / 1232.81 tokens per second
llama-server | 10935.51.130.360 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.53 s / 1200.85 tokens per second
llama-server | 10935.53.064.852 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 12288, progress = 0.23, t = 10.45 s / 1175.37 tokens per second
llama-server | 10935.55.025.711 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 14336, progress = 0.27, t = 12.41 s / 1155.54 tokens per second
llama-server | 10935.57.028.099 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 16384, progress = 0.31, t = 14.40 s / 1138.08 tokens per second
llama-server | 10935.59.067.257 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 18432, progress = 0.35, t = 16.43 s / 1121.97 tokens per second
llama-server | 10936.01.147.685 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 20480, progress = 0.39, t = 18.50 s / 1107.30 tokens per second
llama-server | 10936.03.266.055 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 22528, progress = 0.43, t = 20.60 s / 1093.35 tokens per second
llama-server | 10936.05.439.820 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 24576, progress = 0.47, t = 22.76 s / 1079.91 tokens per second
llama-server | 10936.07.635.373 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 26624, progress = 0.51, t = 24.96 s / 1066.83 tokens per second
llama-server | 10936.09.866.025 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 28672, progress = 0.55, t = 27.18 s / 1055.07 tokens per second
llama-server | 10936.12.130.089 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 30720, progress = 0.59, t = 29.43 s / 1043.74 tokens per second
llama-server | 10936.14.468.359 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 32768, progress = 0.62, t = 31.72 s / 1032.91 tokens per second
llama-server | 10936.16.803.389 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 34816, progress = 0.66, t = 34.09 s / 1021.37 tokens per second
llama-server | 10936.19.176.899 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 36864, progress = 0.70, t = 36.45 s / 1011.35 tokens per second
llama-server | 10936.21.585.297 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 38912, progress = 0.74, t = 38.85 s / 1001.58 tokens per second
llama-server | 10936.24.044.383 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 40960, progress = 0.78, t = 41.29 s / 992.11 tokens per second
llama-server | 10936.26.522.540 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 43008, progress = 0.82, t = 43.77 s / 982.58 tokens per second
llama-server | 10936.29.038.609 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 45056, progress = 0.86, t = 46.28 s / 973.65 tokens per second
llama-server | 10936.31.590.325 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 47104, progress = 0.90, t = 48.82 s / 964.87 tokens per second
llama-server | 10936.34.198.421 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 49152, progress = 0.94, t = 51.40 s / 956.31 tokens per second
llama-server | 10936.36.823.076 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 51200, progress = 0.98, t = 54.03 s / 947.60 tokens per second
llama-server | 10936.37.842.311 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 51918, progress = 0.99, t = 55.43 s / 936.67 tokens per second
llama-server | 10936.38.595.734 I slot print_timing: id 1 | task 2765804 | prompt processing, n_tokens = 52430, progress = 1.00, t = 55.91 s / 937.76 tokens per second
llama-server | 10936.41.842.366 I slot print_timing: id 1 | task 2765804 | n_gen = 101, tg = 32.82 t/s, tg_3s = 33.14 t/s
llama-server | 10936.44.855.130 I slot print_timing: id 1 | task 2765804 | n_gen = 183, tg = 30.03 t/s, tg_3s = 27.22 t/s
llama-server | 10936.47.872.853 I slot print_timing: id 1 | task 2765804 | n_gen = 286, tg = 31.40 t/s, tg_3s = 34.13 t/s
llama-server | 10936.50.912.003 I slot print_timing: id 1 | task 2765804 | n_gen = 391, tg = 32.19 t/s, tg_3s = 34.55 t/s
llama-server | 10936.53.930.909 I slot print_timing: id 1 | task 2765804 | n_gen = 484, tg = 31.91 t/s, tg_3s = 30.81 t/s
llama-server | 10936.56.963.597 I slot print_timing: id 1 | task 2765804 | n_gen = 573, tg = 31.48 t/s, tg_3s = 29.35 t/s
llama-server | 10936.59.991.387 I slot print_timing: id 1 | task 2765804 | n_gen = 676, tg = 31.85 t/s, tg_3s = 34.02 t/s
llama-server | 10937.03.022.133 I slot print_timing: id 1 | task 2765804 | n_gen = 805, tg = 33.19 t/s, tg_3s = 42.56 t/s
llama-server | 10937.06.072.682 I slot print_timing: id 1 | task 2765804 | n_gen = 923, tg = 33.80 t/s, tg_3s = 38.68 t/s
llama-server | 10937.09.101.532 I slot print_timing: id 1 | task 2765804 | n_gen = 1016, tg = 33.49 t/s, tg_3s = 30.70 t/s
llama-server | 10937.12.148.240 I slot print_timing: id 1 | task 2765804 | n_gen = 1094, tg = 32.77 t/s, tg_3s = 25.60 t/s
llama-server | 10937.15.188.751 I slot print_timing: id 1 | task 2765804 | n_gen = 1176, tg = 32.29 t/s, tg_3s = 26.97 t/s
llama-server | 10937.18.232.487 I slot print_timing: id 1 | task 2765804 | n_gen = 1296, tg = 32.84 t/s, tg_3s = 39.43 t/s
llama-server | 10937.21.286.625 I slot print_timing: id 1 | task 2765804 | n_gen = 1373, tg = 32.29 t/s, tg_3s = 25.21 t/s
llama-server | 10937.24.337.107 I slot print_timing: id 1 | task 2765804 | n_gen = 1499, tg = 32.89 t/s, tg_3s = 41.30 t/s
llama-server | 10937.27.407.151 I slot print_timing: id 1 | task 2765804 | n_gen = 1604, tg = 32.98 t/s, tg_3s = 34.20 t/s
llama-server | 10937.30.466.239 I slot print_timing: id 1 | task 2765804 | n_gen = 1723, tg = 33.33 t/s, tg_3s = 38.90 t/s
llama-server | 10937.33.517.995 I slot print_timing: id 1 | task 2765804 | n_gen = 1810, tg = 33.06 t/s, tg_3s = 28.51 t/s
llama-server | 10937.36.587.554 I slot print_timing: id 1 | task 2765804 | n_gen = 1903, tg = 32.91 t/s, tg_3s = 30.30 t/s
llama-server | 10937.39.644.551 I slot print_timing: id 1 | task 2765804 | n_gen = 2028, tg = 33.31 t/s, tg_3s = 40.89 t/s
llama-server | 10937.42.720.922 I slot print_timing: id 1 | task 2765804 | n_gen = 2135, tg = 33.38 t/s, tg_3s = 34.78 t/s
llama-server | 10937.45.778.224 I slot print_timing: id 1 | task 2765804 | n_gen = 2239, tg = 33.41 t/s, tg_3s = 34.02 t/s
llama-server | 10937.48.834.767 I slot print_timing: id 1 | task 2765804 | n_gen = 2334, tg = 33.31 t/s, tg_3s = 31.08 t/s
llama-server | 10937.51.911.518 I slot print_timing: id 1 | task 2765804 | n_gen = 2428, tg = 33.19 t/s, tg_3s = 30.55 t/s
llama-server | 10937.54.966.415 I slot print_timing: id 1 | task 2765804 | n_gen = 2500, tg = 32.81 t/s, tg_3s = 23.57 t/s
llama-server | 10937.58.025.534 I slot print_timing: id 1 | task 2765804 | n_gen = 2583, tg = 32.59 t/s, tg_3s = 27.13 t/s
llama-server | 10938.01.108.388 I slot print_timing: id 1 | task 2765804 | n_gen = 2691, tg = 32.68 t/s, tg_3s = 35.03 t/s
llama-server | 10938.04.174.418 I slot print_timing: id 1 | task 2765804 | n_gen = 2788, tg = 32.64 t/s, tg_3s = 31.64 t/s
llama-server | 10938.07.259.686 I slot print_timing: id 1 | task 2765804 | n_gen = 2893, tg = 32.69 t/s, tg_3s = 34.03 t/s
llama-server | 10938.10.333.984 I slot print_timing: id 1 | task 2765804 | n_gen = 3021, tg = 32.99 t/s, tg_3s = 41.64 t/s
llama-server | 10938.13.425.653 I slot print_timing: id 1 | task 2765804 | n_gen = 3131, tg = 33.08 t/s, tg_3s = 35.58 t/s
llama-server | 10938.16.499.802 I slot print_timing: id 1 | task 2765804 | n_gen = 3226, tg = 33.01 t/s, tg_3s = 30.90 t/s
llama-server | 10938.19.579.590 I slot print_timing: id 1 | task 2765804 | n_gen = 3341, tg = 33.14 t/s, tg_3s = 37.34 t/s
llama-server | 10938.22.668.792 I slot print_timing: id 1 | task 2765804 | n_gen = 3428, tg = 32.99 t/s, tg_3s = 28.16 t/s
llama-server | 10938.25.743.673 I slot print_timing: id 1 | task 2765804 | n_gen = 3524, tg = 32.94 t/s, tg_3s = 31.22 t/s
llama-server | 10938.28.824.786 I slot print_timing: id 1 | task 2765804 | n_gen = 3622, tg = 32.91 t/s, tg_3s = 31.81 t/s
llama-server | 10938.31.834.854 I slot print_timing: id 1 | task 2765804 | n_gen = 3751, tg = 33.17 t/s, tg_3s = 42.86 t/s
llama-server | 10938.34.911.933 I slot print_timing: id 1 | task 2765804 | n_gen = 3835, tg = 33.02 t/s, tg_3s = 27.30 t/s
llama-server | 10938.37.912.258 I slot print_timing: id 1 | task 2765804 | n_gen = 3922, tg = 32.92 t/s, tg_3s = 29.00 t/s
llama-server | 10938.41.004.262 I slot print_timing: id 1 | task 2765804 | n_gen = 4019, tg = 32.88 t/s, tg_3s = 31.37 t/s
llama-server | 10938.44.094.319 I slot print_timing: id 1 | task 2765804 | n_gen = 4112, tg = 32.81 t/s, tg_3s = 30.10 t/s
llama-server | 10938.47.190.400 I slot print_timing: id 1 | task 2765804 | n_gen = 4186, tg = 32.59 t/s, tg_3s = 23.90 t/s
llama-server | 10938.50.286.779 I slot print_timing: id 1 | task 2765804 | n_gen = 4294, tg = 32.65 t/s, tg_3s = 34.88 t/s
llama-server | 10938.53.377.555 I slot print_timing: id 1 | task 2765804 | n_gen = 4395, tg = 32.65 t/s, tg_3s = 32.68 t/s
llama-server | 10938.56.385.994 I slot print_timing: id 1 | task 2765804 | n_gen = 4481, tg = 32.56 t/s, tg_3s = 28.59 t/s
llama-server | 10938.59.477.972 I slot print_timing: id 1 | task 2765804 | n_gen = 4576, tg = 32.52 t/s, tg_3s = 30.72 t/s
llama-server | 10939.01.413.328 I slot print_timing: id 1 | task 2765804 | prompt eval time = 56758.37 ms / 52434 tokens ( 1.08 ms per token, 923.81 tokens per second)
llama-server | 10939.01.413.332 I slot print_timing: id 1 | task 2765804 | eval time = 142617.94 ms / 4639 tokens ( 30.75 ms per token, 32.52 tokens per second)
llama-server | 10939.01.413.332 I slot print_timing: id 1 | task 2765804 | total time = 199376.31 ms / 57073 tokens
llama-server | 10939.01.413.333 I slot print_timing: id 1 | task 2765804 | graphs reused = 2680038
llama-server | 10939.01.413.336 I slot print_timing: id 1 | task 2765804 | draft acceptance = 0.42310 ( 3150 accepted / 7445 generated), mean len = 3.12
llama-server | 10939.01.414.701 I slot release: id 1 | task 2765804 | stop processing: n_tokens = 57073, truncated = 0
llama-server | 10939.02.562.980 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 656154443853
llama-server | 10939.02.563.547 I slot launch_slot_: id 0 | task 2767322 | processing task, is_child = 0
llama-server | 10939.02.566.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2304.147 MiB)
llama-server | 10939.08.334.225 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.61 tokens per second
llama-server | 10939.10.151.563 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1276.30 tokens per second
llama-server | 10939.12.010.727 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.66 s / 1230.77 tokens per second
llama-server | 10939.13.898.132 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.54 s / 1198.87 tokens per second
llama-server | 10939.15.824.466 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.46 s / 1174.96 tokens per second
llama-server | 10939.17.801.839 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.43 s / 1153.65 tokens per second
llama-server | 10939.19.817.510 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.42 s / 1136.26 tokens per second
llama-server | 10939.21.860.122 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 18432, progress = 0.42, t = 16.46 s / 1119.51 tokens per second
llama-server | 10939.23.941.674 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.54 s / 1104.88 tokens per second
llama-server | 10939.26.062.851 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.64 s / 1091.21 tokens per second
llama-server | 10939.28.235.520 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 24576, progress = 0.56, t = 22.80 s / 1078.00 tokens per second
llama-server | 10939.30.435.364 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 26624, progress = 0.61, t = 25.00 s / 1065.12 tokens per second
llama-server | 10939.32.670.486 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.22 s / 1053.16 tokens per second
llama-server | 10939.34.937.023 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 30720, progress = 0.71, t = 29.48 s / 1041.93 tokens per second
llama-server | 10939.37.274.483 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 32768, progress = 0.75, t = 31.78 s / 1031.23 tokens per second
llama-server | 10939.39.615.484 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 34816, progress = 0.80, t = 34.14 s / 1019.78 tokens per second
llama-server | 10939.41.992.906 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 36864, progress = 0.85, t = 36.51 s / 1009.72 tokens per second
llama-server | 10939.44.400.446 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 38912, progress = 0.89, t = 38.91 s / 1000.02 tokens per second
llama-server | 10939.46.859.231 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 40960, progress = 0.94, t = 41.34 s / 990.70 tokens per second
llama-server | 10939.49.340.201 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 43008, progress = 0.99, t = 43.83 s / 981.21 tokens per second
llama-server | 10939.49.473.559 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 43042, progress = 0.99, t = 44.56 s / 965.98 tokens per second
llama-server | 10939.50.189.520 I slot print_timing: id 0 | task 2767322 | prompt processing, n_tokens = 43554, progress = 1.00, t = 44.78 s / 972.60 tokens per second
llama-server | 10939.53.693.983 I slot print_timing: id 0 | task 2767322 | n_gen = 100, tg = 30.27 t/s, tg_3s = 30.58 t/s
llama-server | 10939.56.780.816 I slot print_timing: id 0 | task 2767322 | n_gen = 229, tg = 35.86 t/s, tg_3s = 41.79 t/s
llama-server | 10939.59.854.149 I slot print_timing: id 0 | task 2767322 | n_gen = 355, tg = 37.54 t/s, tg_3s = 41.00 t/s
llama-server | 10940.02.923.708 I slot print_timing: id 0 | task 2767322 | n_gen = 452, tg = 36.08 t/s, tg_3s = 31.60 t/s
llama-server | 10940.06.011.831 I slot print_timing: id 0 | task 2767322 | n_gen = 531, tg = 34.00 t/s, tg_3s = 25.58 t/s
llama-server | 10940.09.099.914 I slot print_timing: id 0 | task 2767322 | n_gen = 685, tg = 36.62 t/s, tg_3s = 49.87 t/s
llama-server | 10940.12.112.820 I slot print_timing: id 0 | task 2767322 | n_gen = 820, tg = 37.76 t/s, tg_3s = 44.81 t/s
llama-server | 10940.15.193.566 I slot print_timing: id 0 | task 2767322 | n_gen = 932, tg = 37.59 t/s, tg_3s = 36.35 t/s
llama-server | 10940.18.284.434 I slot print_timing: id 0 | task 2767322 | n_gen = 1015, tg = 36.40 t/s, tg_3s = 26.85 t/s
llama-server | 10940.21.368.660 I slot print_timing: id 0 | task 2767322 | n_gen = 1109, tg = 35.81 t/s, tg_3s = 30.48 t/s
llama-server | 10940.24.453.033 I slot print_timing: id 0 | task 2767322 | n_gen = 1206, tg = 35.41 t/s, tg_3s = 31.45 t/s
llama-server | 10940.27.458.619 I slot print_timing: id 0 | task 2767322 | n_gen = 1279, tg = 34.51 t/s, tg_3s = 24.29 t/s
llama-server | 10940.30.547.711 I slot print_timing: id 0 | task 2767322 | n_gen = 1389, tg = 34.59 t/s, tg_3s = 35.61 t/s
llama-server | 10940.33.571.014 I slot print_timing: id 0 | task 2767322 | n_gen = 1509, tg = 34.95 t/s, tg_3s = 39.69 t/s
llama-server | 10940.36.659.185 I slot print_timing: id 0 | task 2767322 | n_gen = 1578, tg = 34.11 t/s, tg_3s = 22.34 t/s
llama-server | 10940.39.661.053 I slot print_timing: id 0 | task 2767322 | n_gen = 1659, tg = 33.67 t/s, tg_3s = 26.98 t/s
llama-server | 10940.42.662.693 I slot print_timing: id 0 | task 2767322 | n_gen = 1734, tg = 33.17 t/s, tg_3s = 24.99 t/s
llama-server | 10940.45.683.524 I slot print_timing: id 0 | task 2767322 | n_gen = 1820, tg = 32.92 t/s, tg_3s = 28.47 t/s
llama-server | 10940.48.688.295 I slot print_timing: id 0 | task 2767322 | n_gen = 1904, tg = 32.66 t/s, tg_3s = 27.96 t/s
llama-server | 10940.51.701.278 I slot print_timing: id 0 | task 2767322 | n_gen = 2010, tg = 32.79 t/s, tg_3s = 35.18 t/s
llama-server | 10940.54.726.849 I slot print_timing: id 0 | task 2767322 | n_gen = 2086, tg = 32.42 t/s, tg_3s = 25.12 t/s
llama-server | 10940.57.741.649 I slot print_timing: id 0 | task 2767322 | n_gen = 2210, tg = 32.81 t/s, tg_3s = 41.13 t/s
llama-server | 10941.00.778.496 I slot print_timing: id 0 | task 2767322 | n_gen = 2308, tg = 32.79 t/s, tg_3s = 32.27 t/s
llama-server | 10941.03.801.745 I slot print_timing: id 0 | task 2767322 | n_gen = 2420, tg = 32.97 t/s, tg_3s = 37.05 t/s
llama-server | 10941.06.842.978 I slot print_timing: id 0 | task 2767322 | n_gen = 2534, tg = 33.15 t/s, tg_3s = 37.48 t/s
llama-server | 10941.09.865.580 I slot print_timing: id 0 | task 2767322 | n_gen = 2632, tg = 33.12 t/s, tg_3s = 32.42 t/s
llama-server | 10941.12.890.872 I slot print_timing: id 0 | task 2767322 | n_gen = 2717, tg = 32.93 t/s, tg_3s = 28.10 t/s
llama-server | 10941.15.926.804 I slot print_timing: id 0 | task 2767322 | n_gen = 2797, tg = 32.70 t/s, tg_3s = 26.35 t/s
llama-server | 10941.18.950.721 I slot print_timing: id 0 | task 2767322 | n_gen = 2868, tg = 32.39 t/s, tg_3s = 23.48 t/s
llama-server | 10941.21.973.610 I slot print_timing: id 0 | task 2767322 | n_gen = 2952, tg = 32.23 t/s, tg_3s = 27.79 t/s
llama-server | 10941.25.023.062 I slot print_timing: id 0 | task 2767322 | n_gen = 3039, tg = 32.11 t/s, tg_3s = 28.53 t/s
llama-server | 10941.28.050.084 I slot print_timing: id 0 | task 2767322 | n_gen = 3131, tg = 32.06 t/s, tg_3s = 30.39 t/s
llama-server | 10941.31.083.306 I slot print_timing: id 0 | task 2767322 | n_gen = 3229, tg = 32.07 t/s, tg_3s = 32.31 t/s
llama-server | 10941.34.129.716 I slot print_timing: id 0 | task 2767322 | n_gen = 3320, tg = 32.00 t/s, tg_3s = 29.87 t/s
llama-server | 10941.37.164.618 I slot print_timing: id 0 | task 2767322 | n_gen = 3412, tg = 31.96 t/s, tg_3s = 30.31 t/s
llama-server | 10941.40.198.238 I slot print_timing: id 0 | task 2767322 | n_gen = 3503, tg = 31.90 t/s, tg_3s = 30.00 t/s
llama-server | 10941.43.248.798 I slot print_timing: id 0 | task 2767322 | n_gen = 3597, tg = 31.87 t/s, tg_3s = 30.81 t/s
llama-server | 10941.46.286.417 I slot print_timing: id 0 | task 2767322 | n_gen = 3689, tg = 31.83 t/s, tg_3s = 30.29 t/s
llama-server | 10941.49.323.807 I slot print_timing: id 0 | task 2767322 | n_gen = 3784, tg = 31.82 t/s, tg_3s = 31.28 t/s
llama-server | 10941.52.377.920 I slot print_timing: id 0 | task 2767322 | n_gen = 3867, tg = 31.70 t/s, tg_3s = 27.18 t/s
llama-server | 10941.55.418.086 I slot print_timing: id 0 | task 2767322 | n_gen = 3957, tg = 31.65 t/s, tg_3s = 29.60 t/s
llama-server | 10941.58.467.155 I slot print_timing: id 0 | task 2767322 | n_gen = 4062, tg = 31.72 t/s, tg_3s = 34.44 t/s
llama-server | 10942.01.530.994 I slot print_timing: id 0 | task 2767322 | prompt eval time = 45631.49 ms / 43558 tokens ( 1.05 ms per token, 954.56 tokens per second)
llama-server | 10942.01.530.997 I slot print_timing: id 0 | task 2767322 | eval time = 131107.40 ms / 4163 tokens ( 31.50 ms per token, 31.74 tokens per second)
llama-server | 10942.01.530.998 I slot print_timing: id 0 | task 2767322 | total time = 176738.89 ms / 47721 tokens
llama-server | 10942.01.530.999 I slot print_timing: id 0 | task 2767322 | graphs reused = 2681454
llama-server | 10942.01.531.002 I slot print_timing: id 0 | task 2767322 | draft acceptance = 0.38102 ( 2730 accepted / 7165 generated), mean len = 2.91
llama-server | 10942.01.532.336 I slot release: id 0 | task 2767322 | stop processing: n_tokens = 47721, truncated = 0
llama-server | 10942.02.827.417 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 656357254753
llama-server | 10942.02.827.875 I slot launch_slot_: id 1 | task 2768780 | processing task, is_child = 0
llama-server | 10942.02.830.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2310.830 MiB)
llama-server | 10942.07.846.392 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.70 tokens per second
llama-server | 10942.09.667.264 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1276.12 tokens per second
llama-server | 10942.11.521.966 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.66 s / 1229.69 tokens per second
llama-server | 10942.13.409.760 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.54 s / 1198.59 tokens per second
llama-server | 10942.15.337.056 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.46 s / 1174.86 tokens per second
llama-server | 10942.17.322.681 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.43 s / 1153.26 tokens per second
llama-server | 10942.19.329.909 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.43 s / 1135.42 tokens per second
llama-server | 10942.21.371.312 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 18432, progress = 0.43, t = 16.47 s / 1119.40 tokens per second
llama-server | 10942.23.450.813 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.54 s / 1104.92 tokens per second
llama-server | 10942.25.570.375 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.64 s / 1091.32 tokens per second
llama-server | 10942.27.744.940 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 24576, progress = 0.57, t = 22.80 s / 1078.10 tokens per second
llama-server | 10942.29.942.927 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 26624, progress = 0.62, t = 25.00 s / 1065.12 tokens per second
llama-server | 10942.32.177.571 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.22 s / 1053.30 tokens per second
llama-server | 10942.34.444.411 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 30720, progress = 0.71, t = 29.48 s / 1042.05 tokens per second
llama-server | 10942.36.782.018 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 32768, progress = 0.76, t = 31.77 s / 1031.30 tokens per second
llama-server | 10942.39.121.650 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 34816, progress = 0.81, t = 34.14 s / 1019.85 tokens per second
llama-server | 10942.41.498.690 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 36864, progress = 0.85, t = 36.51 s / 1009.83 tokens per second
llama-server | 10942.43.908.992 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 38912, progress = 0.90, t = 38.91 s / 1000.08 tokens per second
llama-server | 10942.46.371.114 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 40960, progress = 0.95, t = 41.35 s / 990.69 tokens per second
llama-server | 10942.48.423.805 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 42614, progress = 0.99, t = 43.83 s / 972.23 tokens per second
llama-server | 10942.49.135.543 I slot print_timing: id 1 | task 2768780 | prompt processing, n_tokens = 43126, progress = 1.00, t = 44.22 s / 975.21 tokens per second
llama-server | 10942.52.756.488 I slot print_timing: id 1 | task 2768780 | n_gen = 100, tg = 28.86 t/s, tg_3s = 29.15 t/s
llama-server | 10942.55.830.753 I slot print_timing: id 1 | task 2768780 | n_gen = 209, tg = 31.98 t/s, tg_3s = 35.46 t/s
llama-server | 10942.58.892.179 I slot print_timing: id 1 | task 2768780 | n_gen = 310, tg = 32.30 t/s, tg_3s = 32.99 t/s
llama-server | 10943.01.966.143 I slot print_timing: id 1 | task 2768780 | n_gen = 408, tg = 32.20 t/s, tg_3s = 31.88 t/s
llama-server | 10943.05.032.039 I slot print_timing: id 1 | task 2768780 | n_gen = 515, tg = 32.73 t/s, tg_3s = 34.90 t/s
llama-server | 10943.08.097.129 I slot print_timing: id 1 | task 2768780 | n_gen = 621, tg = 33.03 t/s, tg_3s = 34.58 t/s
llama-server | 10943.11.183.965 I slot print_timing: id 1 | task 2768780 | n_gen = 734, tg = 33.53 t/s, tg_3s = 36.61 t/s
llama-server | 10943.14.258.208 I slot print_timing: id 1 | task 2768780 | n_gen = 849, tg = 34.01 t/s, tg_3s = 37.41 t/s
llama-server | 10943.17.262.401 I slot print_timing: id 1 | task 2768780 | n_gen = 966, tg = 34.54 t/s, tg_3s = 38.95 t/s
llama-server | 10943.20.347.390 I slot print_timing: id 1 | task 2768780 | n_gen = 1082, tg = 34.85 t/s, tg_3s = 37.60 t/s
llama-server | 10943.23.357.375 I slot print_timing: id 1 | task 2768780 | n_gen = 1203, tg = 35.32 t/s, tg_3s = 40.20 t/s
llama-server | 10943.26.446.041 I slot print_timing: id 1 | task 2768780 | n_gen = 1340, tg = 36.07 t/s, tg_3s = 44.36 t/s
llama-server | 10943.29.460.704 I slot print_timing: id 1 | task 2768780 | n_gen = 1452, tg = 36.15 t/s, tg_3s = 37.15 t/s
llama-server | 10943.32.548.360 I slot print_timing: id 1 | task 2768780 | n_gen = 1537, tg = 35.54 t/s, tg_3s = 27.53 t/s
llama-server | 10943.35.636.843 I slot print_timing: id 1 | task 2768780 | n_gen = 1632, tg = 35.22 t/s, tg_3s = 30.76 t/s
llama-server | 10943.38.654.669 I slot print_timing: id 1 | task 2768780 | n_gen = 1729, tg = 35.03 t/s, tg_3s = 32.14 t/s
llama-server | 10943.41.665.167 I slot print_timing: id 1 | task 2768780 | n_gen = 1844, tg = 35.21 t/s, tg_3s = 38.20 t/s
llama-server | 10943.44.685.813 I slot print_timing: id 1 | task 2768780 | n_gen = 1966, tg = 35.50 t/s, tg_3s = 40.39 t/s
llama-server | 10943.47.693.106 I slot print_timing: id 1 | task 2768780 | n_gen = 2089, tg = 35.77 t/s, tg_3s = 40.90 t/s
llama-server | 10943.50.695.903 I slot print_timing: id 1 | task 2768780 | n_gen = 2178, tg = 35.47 t/s, tg_3s = 29.64 t/s
llama-server | 10943.53.726.563 I slot print_timing: id 1 | task 2768780 | n_gen = 2287, tg = 35.50 t/s, tg_3s = 35.97 t/s
llama-server | 10943.56.735.664 I slot print_timing: id 1 | task 2768780 | n_gen = 2394, tg = 35.50 t/s, tg_3s = 35.56 t/s
llama-server | 10943.56.919.397 I slot print_timing: id 1 | task 2768780 | prompt eval time = 45023.07 ms / 43130 tokens ( 1.04 ms per token, 957.95 tokens per second)
llama-server | 10943.56.919.400 I slot print_timing: id 1 | task 2768780 | eval time = 67593.40 ms / 2405 tokens ( 28.12 ms per token, 35.57 tokens per second)
llama-server | 10943.56.919.400 I slot print_timing: id 1 | task 2768780 | total time = 112616.48 ms / 45535 tokens
llama-server | 10943.56.919.401 I slot print_timing: id 1 | task 2768780 | graphs reused = 2682188
llama-server | 10943.56.919.404 I slot print_timing: id 1 | task 2768780 | draft acceptance = 0.44651 ( 1661 accepted / 3720 generated), mean len = 3.23
llama-server | 10943.56.920.729 I slot release: id 1 | task 2768780 | stop processing: n_tokens = 45535, truncated = 0
llama-server | 10943.58.136.411 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 656537372389
llama-server | 10943.58.136.930 I slot launch_slot_: id 0 | task 2769548 | processing task, is_child = 0
llama-server | 10943.58.139.149 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2341.253 MiB)
llama-server | 10944.03.615.656 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.00 s / 1363.36 tokens per second
llama-server | 10944.05.432.880 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1277.11 tokens per second
llama-server | 10944.07.294.734 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.66 s / 1230.91 tokens per second
llama-server | 10944.09.184.605 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.54 s / 1198.42 tokens per second
llama-server | 10944.11.120.198 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.47 s / 1173.37 tokens per second
llama-server | 10944.13.088.206 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 14336, progress = 0.34, t = 12.43 s / 1153.64 tokens per second
llama-server | 10944.15.096.055 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 16384, progress = 0.39, t = 14.42 s / 1135.92 tokens per second
llama-server | 10944.17.139.094 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 18432, progress = 0.43, t = 16.46 s / 1119.69 tokens per second
llama-server | 10944.19.234.222 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 20480, progress = 0.48, t = 18.53 s / 1105.12 tokens per second
llama-server | 10944.21.355.686 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 22528, progress = 0.53, t = 20.66 s / 1090.63 tokens per second
llama-server | 10944.23.532.213 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 24576, progress = 0.58, t = 22.81 s / 1077.40 tokens per second
llama-server | 10944.25.730.118 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 26624, progress = 0.63, t = 25.01 s / 1064.48 tokens per second
llama-server | 10944.27.964.939 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 28672, progress = 0.67, t = 27.24 s / 1052.76 tokens per second
llama-server | 10944.30.231.253 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 30720, progress = 0.72, t = 29.50 s / 1041.51 tokens per second
llama-server | 10944.32.570.005 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 32768, progress = 0.77, t = 31.79 s / 1030.81 tokens per second
llama-server | 10944.34.906.592 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 34816, progress = 0.82, t = 34.15 s / 1019.42 tokens per second
llama-server | 10944.37.284.509 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 36864, progress = 0.87, t = 36.52 s / 1009.50 tokens per second
llama-server | 10944.39.693.251 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 38912, progress = 0.92, t = 38.92 s / 999.78 tokens per second
llama-server | 10944.42.155.554 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 40960, progress = 0.96, t = 41.36 s / 990.40 tokens per second
llama-server | 10944.43.477.662 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 42005, progress = 0.99, t = 43.26 s / 971.01 tokens per second
llama-server | 10944.44.184.716 I slot print_timing: id 0 | task 2769548 | prompt processing, n_tokens = 42517, progress = 1.00, t = 43.50 s / 977.37 tokens per second
llama-server | 10944.47.492.299 I slot print_timing: id 0 | task 2769548 | n_gen = 132, tg = 42.65 t/s, tg_3s = 42.97 t/s
llama-server | 10944.50.087.488 I slot print_timing: id 0 | task 2769548 | prompt eval time = 44345.61 ms / 42521 tokens ( 1.04 ms per token, 958.85 tokens per second)
llama-server | 10944.50.087.491 I slot print_timing: id 0 | task 2769548 | eval time = 5667.02 ms / 216 tokens ( 26.36 ms per token, 37.94 tokens per second)
llama-server | 10944.50.087.492 I slot print_timing: id 0 | task 2769548 | total time = 50012.63 ms / 42737 tokens
llama-server | 10944.50.087.492 I slot print_timing: id 0 | task 2769548 | graphs reused = 2682250
llama-server | 10944.50.087.495 I slot print_timing: id 0 | task 2769548 | draft acceptance = 0.48571 ( 153 accepted / 315 generated), mean len = 3.43
llama-server | 10944.50.088.760 I slot release: id 0 | task 2769548 | stop processing: n_tokens = 42737, truncated = 0
llama-server | 10944.51.080.798 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 656652760781
llama-server | 10944.51.081.319 I slot launch_slot_: id 1 | task 2769635 | processing task, is_child = 0
llama-server | 10944.51.083.327 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2466.634 MiB)
llama-server | 10944.56.362.109 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.00 s / 1365.15 tokens per second
llama-server | 10944.58.177.258 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1278.31 tokens per second
llama-server | 10945.00.026.581 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.65 s / 1232.66 tokens per second
llama-server | 10945.01.913.587 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.52 s / 1201.69 tokens per second
llama-server | 10945.03.846.090 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.45 s / 1176.10 tokens per second
llama-server | 10945.05.805.739 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.40 s / 1156.21 tokens per second
llama-server | 10945.07.806.737 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.39 s / 1138.89 tokens per second
llama-server | 10945.09.845.532 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 18432, progress = 0.43, t = 16.42 s / 1122.75 tokens per second
llama-server | 10945.11.922.879 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 20480, progress = 0.48, t = 18.48 s / 1107.95 tokens per second
llama-server | 10945.14.045.670 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.59 s / 1093.98 tokens per second
llama-server | 10945.16.215.502 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 24576, progress = 0.57, t = 22.75 s / 1080.47 tokens per second
llama-server | 10945.18.410.108 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 26624, progress = 0.62, t = 24.94 s / 1067.46 tokens per second
llama-server | 10945.20.643.691 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 28672, progress = 0.67, t = 27.16 s / 1055.53 tokens per second
llama-server | 10945.22.908.446 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 30720, progress = 0.72, t = 29.42 s / 1044.09 tokens per second
llama-server | 10945.25.246.071 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 32768, progress = 0.76, t = 31.71 s / 1033.20 tokens per second
llama-server | 10945.27.582.568 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 34816, progress = 0.81, t = 34.08 s / 1021.66 tokens per second
llama-server | 10945.29.959.111 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 36864, progress = 0.86, t = 36.44 s / 1011.56 tokens per second
llama-server | 10945.32.366.826 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 38912, progress = 0.91, t = 38.84 s / 1001.73 tokens per second
llama-server | 10945.34.826.978 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 40960, progress = 0.95, t = 41.28 s / 992.29 tokens per second
llama-server | 10945.36.626.135 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 42417, progress = 0.99, t = 43.18 s / 982.30 tokens per second
llama-server | 10945.37.351.441 I slot print_timing: id 1 | task 2769635 | prompt processing, n_tokens = 42929, progress = 1.00, t = 43.90 s / 977.81 tokens per second
llama-server | 10945.40.628.600 I slot print_timing: id 1 | task 2769635 | n_gen = 113, tg = 36.31 t/s, tg_3s = 36.63 t/s
llama-server | 10945.43.673.082 I slot print_timing: id 1 | task 2769635 | n_gen = 208, tg = 33.77 t/s, tg_3s = 31.20 t/s
llama-server | 10945.46.722.313 I slot print_timing: id 1 | task 2769635 | n_gen = 324, tg = 35.19 t/s, tg_3s = 38.04 t/s
llama-server | 10945.49.792.269 I slot print_timing: id 1 | task 2769635 | n_gen = 443, tg = 36.09 t/s, tg_3s = 38.76 t/s
llama-server | 10945.52.846.078 I slot print_timing: id 1 | task 2769635 | n_gen = 564, tg = 36.79 t/s, tg_3s = 39.62 t/s
llama-server | 10945.55.923.807 I slot print_timing: id 1 | task 2769635 | n_gen = 658, tg = 35.75 t/s, tg_3s = 30.54 t/s
llama-server | 10945.58.985.416 I slot print_timing: id 1 | task 2769635 | n_gen = 777, tg = 36.19 t/s, tg_3s = 38.87 t/s
llama-server | 10946.02.066.101 I slot print_timing: id 1 | task 2769635 | n_gen = 895, tg = 36.46 t/s, tg_3s = 38.30 t/s
llama-server | 10946.05.133.424 I slot print_timing: id 1 | task 2769635 | n_gen = 1015, tg = 36.75 t/s, tg_3s = 39.12 t/s
llama-server | 10946.08.219.218 I slot print_timing: id 1 | task 2769635 | n_gen = 1128, tg = 36.74 t/s, tg_3s = 36.62 t/s
llama-server | 10946.10.759.539 I slot print_timing: id 1 | task 2769635 | prompt eval time = 44718.38 ms / 42933 tokens ( 1.04 ms per token, 960.08 tokens per second)
llama-server | 10946.10.759.542 I slot print_timing: id 1 | task 2769635 | eval time = 33215.78 ms / 1263 tokens ( 26.32 ms per token, 37.99 tokens per second)
llama-server | 10946.10.759.543 I slot print_timing: id 1 | task 2769635 | total time = 77934.16 ms / 44196 tokens
llama-server | 10946.10.759.543 I slot print_timing: id 1 | task 2769635 | graphs reused = 2682612
llama-server | 10946.10.759.546 I slot print_timing: id 1 | task 2769635 | draft acceptance = 0.48641 ( 895 accepted / 1840 generated), mean len = 3.43
llama-server | 10946.10.760.865 I slot release: id 1 | task 2769635 | stop processing: n_tokens = 44196, truncated = 0
llama-server | 10946.11.854.366 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 656705928812
llama-server | 10946.11.855.008 I slot launch_slot_: id 0 | task 2770027 | processing task, is_child = 0
llama-server | 10946.11.857.081 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2155.691 MiB)
llama-server | 10946.16.778.509 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.00 s / 1364.54 tokens per second
llama-server | 10946.18.596.380 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1277.68 tokens per second
llama-server | 10946.20.450.612 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.65 s / 1231.40 tokens per second
llama-server | 10946.22.343.833 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.53 s / 1199.91 tokens per second
llama-server | 10946.24.270.169 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.46 s / 1175.24 tokens per second
llama-server | 10946.26.241.694 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.42 s / 1154.52 tokens per second
llama-server | 10946.28.248.695 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.41 s / 1136.95 tokens per second
llama-server | 10946.30.290.876 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 18432, progress = 0.42, t = 16.45 s / 1120.70 tokens per second
llama-server | 10946.32.371.168 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.52 s / 1106.03 tokens per second
llama-server | 10946.34.491.548 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.63 s / 1092.21 tokens per second
llama-server | 10946.36.665.597 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 24576, progress = 0.57, t = 22.78 s / 1078.88 tokens per second
llama-server | 10946.38.863.684 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 26624, progress = 0.61, t = 24.98 s / 1065.84 tokens per second
llama-server | 10946.41.098.435 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.20 s / 1053.99 tokens per second
llama-server | 10946.43.364.065 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 30720, progress = 0.71, t = 29.46 s / 1042.70 tokens per second
llama-server | 10946.45.699.675 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 32768, progress = 0.75, t = 31.75 s / 1031.96 tokens per second
llama-server | 10946.48.037.063 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 34816, progress = 0.80, t = 34.12 s / 1020.51 tokens per second
llama-server | 10946.50.412.013 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 36864, progress = 0.85, t = 36.48 s / 1010.51 tokens per second
llama-server | 10946.52.821.096 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 38912, progress = 0.90, t = 38.88 s / 1000.78 tokens per second
llama-server | 10946.55.281.875 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 40960, progress = 0.94, t = 41.32 s / 991.36 tokens per second
llama-server | 10946.57.700.743 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 42901, progress = 0.99, t = 43.80 s / 979.40 tokens per second
llama-server | 10946.58.419.654 I slot print_timing: id 0 | task 2770027 | prompt processing, n_tokens = 43413, progress = 1.00, t = 44.57 s / 974.14 tokens per second
llama-server | 10947.02.170.750 I slot print_timing: id 0 | task 2770027 | n_gen = 101, tg = 28.39 t/s, tg_3s = 28.67 t/s
llama-server | 10947.05.236.986 I slot print_timing: id 0 | task 2770027 | n_gen = 180, tg = 27.17 t/s, tg_3s = 25.76 t/s
llama-server | 10947.08.289.812 I slot print_timing: id 0 | task 2770027 | n_gen = 262, tg = 27.07 t/s, tg_3s = 26.86 t/s
llama-server | 10947.11.362.381 I slot print_timing: id 0 | task 2770027 | n_gen = 371, tg = 29.10 t/s, tg_3s = 35.48 t/s
llama-server | 10947.14.422.594 I slot print_timing: id 0 | task 2770027 | n_gen = 476, tg = 30.11 t/s, tg_3s = 34.31 t/s
llama-server | 10947.17.478.464 I slot print_timing: id 0 | task 2770027 | n_gen = 552, tg = 29.26 t/s, tg_3s = 24.87 t/s
llama-server | 10947.20.564.130 I slot print_timing: id 0 | task 2770027 | n_gen = 650, tg = 29.61 t/s, tg_3s = 31.76 t/s
llama-server | 10947.23.636.994 I slot print_timing: id 0 | task 2770027 | n_gen = 766, tg = 30.61 t/s, tg_3s = 37.75 t/s
llama-server | 10947.26.726.834 I slot print_timing: id 0 | task 2770027 | n_gen = 892, tg = 31.73 t/s, tg_3s = 40.78 t/s
llama-server | 10947.29.803.149 I slot print_timing: id 0 | task 2770027 | n_gen = 984, tg = 31.55 t/s, tg_3s = 29.91 t/s
llama-server | 10947.32.880.407 I slot print_timing: id 0 | task 2770027 | n_gen = 1109, tg = 32.37 t/s, tg_3s = 40.62 t/s
llama-server | 10947.35.882.453 I slot print_timing: id 0 | task 2770027 | n_gen = 1199, tg = 32.17 t/s, tg_3s = 29.98 t/s
llama-server | 10947.38.960.821 I slot print_timing: id 0 | task 2770027 | n_gen = 1301, tg = 32.25 t/s, tg_3s = 33.13 t/s
llama-server | 10947.42.044.098 I slot print_timing: id 0 | task 2770027 | n_gen = 1383, tg = 31.85 t/s, tg_3s = 26.60 t/s
llama-server | 10947.45.051.324 I slot print_timing: id 0 | task 2770027 | n_gen = 1483, tg = 31.94 t/s, tg_3s = 33.25 t/s
llama-server | 10947.48.135.434 I slot print_timing: id 0 | task 2770027 | n_gen = 1577, tg = 31.85 t/s, tg_3s = 30.48 t/s
llama-server | 10947.51.149.128 I slot print_timing: id 0 | task 2770027 | n_gen = 1669, tg = 31.77 t/s, tg_3s = 30.53 t/s
llama-server | 10947.54.232.656 I slot print_timing: id 0 | task 2770027 | n_gen = 1752, tg = 31.50 t/s, tg_3s = 26.92 t/s
llama-server | 10947.57.316.574 I slot print_timing: id 0 | task 2770027 | n_gen = 1845, tg = 31.43 t/s, tg_3s = 30.16 t/s
llama-server | 10948.00.334.067 I slot print_timing: id 0 | task 2770027 | n_gen = 1944, tg = 31.50 t/s, tg_3s = 32.81 t/s
llama-server | 10948.03.341.978 I slot print_timing: id 0 | task 2770027 | n_gen = 2044, tg = 31.58 t/s, tg_3s = 33.25 t/s
llama-server | 10948.06.351.657 I slot print_timing: id 0 | task 2770027 | n_gen = 2150, tg = 31.74 t/s, tg_3s = 35.22 t/s
llama-server | 10948.09.378.106 I slot print_timing: id 0 | task 2770027 | n_gen = 2240, tg = 31.66 t/s, tg_3s = 29.74 t/s
llama-server | 10948.12.386.692 I slot print_timing: id 0 | task 2770027 | n_gen = 2324, tg = 31.50 t/s, tg_3s = 27.92 t/s
llama-server | 10948.15.418.445 I slot print_timing: id 0 | task 2770027 | n_gen = 2440, tg = 31.77 t/s, tg_3s = 38.26 t/s
llama-server | 10948.18.434.589 I slot print_timing: id 0 | task 2770027 | n_gen = 2523, tg = 31.61 t/s, tg_3s = 27.52 t/s
llama-server | 10948.21.457.122 I slot print_timing: id 0 | task 2770027 | n_gen = 2627, tg = 31.71 t/s, tg_3s = 34.41 t/s
llama-server | 10948.24.488.746 I slot print_timing: id 0 | task 2770027 | n_gen = 2735, tg = 31.85 t/s, tg_3s = 35.62 t/s
llama-server | 10948.27.505.586 I slot print_timing: id 0 | task 2770027 | n_gen = 2803, tg = 31.53 t/s, tg_3s = 22.54 t/s
llama-server | 10948.30.523.499 I slot print_timing: id 0 | task 2770027 | n_gen = 2885, tg = 31.39 t/s, tg_3s = 27.17 t/s
llama-server | 10948.33.564.606 I slot print_timing: id 0 | task 2770027 | n_gen = 2978, tg = 31.36 t/s, tg_3s = 30.58 t/s
llama-server | 10948.36.590.003 I slot print_timing: id 0 | task 2770027 | n_gen = 3079, tg = 31.43 t/s, tg_3s = 33.38 t/s
llama-server | 10948.39.611.626 I slot print_timing: id 0 | task 2770027 | n_gen = 3169, tg = 31.38 t/s, tg_3s = 29.79 t/s
llama-server | 10948.42.653.281 I slot print_timing: id 0 | task 2770027 | n_gen = 3255, tg = 31.29 t/s, tg_3s = 28.27 t/s
llama-server | 10948.45.682.694 I slot print_timing: id 0 | task 2770027 | n_gen = 3334, tg = 31.14 t/s, tg_3s = 26.08 t/s
llama-server | 10948.48.711.993 I slot print_timing: id 0 | task 2770027 | n_gen = 3428, tg = 31.14 t/s, tg_3s = 31.03 t/s
llama-server | 10948.51.760.964 I slot print_timing: id 0 | task 2770027 | n_gen = 3520, tg = 31.11 t/s, tg_3s = 30.17 t/s
llama-server | 10948.54.791.595 I slot print_timing: id 0 | task 2770027 | n_gen = 3605, tg = 31.03 t/s, tg_3s = 28.05 t/s
llama-server | 10948.57.822.886 I slot print_timing: id 0 | task 2770027 | n_gen = 3687, tg = 30.93 t/s, tg_3s = 27.05 t/s
llama-server | 10949.00.876.090 I slot print_timing: id 0 | task 2770027 | n_gen = 3789, tg = 30.99 t/s, tg_3s = 33.41 t/s
llama-server | 10949.03.916.544 I slot print_timing: id 0 | task 2770027 | n_gen = 3888, tg = 31.03 t/s, tg_3s = 32.56 t/s
llama-server | 10949.06.962.810 I slot print_timing: id 0 | task 2770027 | n_gen = 3953, tg = 30.80 t/s, tg_3s = 21.34 t/s
llama-server | 10949.09.999.518 I slot print_timing: id 0 | task 2770027 | n_gen = 4028, tg = 30.66 t/s, tg_3s = 24.70 t/s
llama-server | 10949.13.038.085 I slot print_timing: id 0 | task 2770027 | n_gen = 4122, tg = 30.66 t/s, tg_3s = 30.94 t/s
llama-server | 10949.16.097.343 I slot print_timing: id 0 | task 2770027 | n_gen = 4214, tg = 30.65 t/s, tg_3s = 30.07 t/s
llama-server | 10949.19.142.565 I slot print_timing: id 0 | task 2770027 | n_gen = 4289, tg = 30.52 t/s, tg_3s = 24.63 t/s
llama-server | 10949.22.187.090 I slot print_timing: id 0 | task 2770027 | n_gen = 4373, tg = 30.46 t/s, tg_3s = 27.59 t/s
llama-server | 10949.25.233.553 I slot print_timing: id 0 | task 2770027 | n_gen = 4443, tg = 30.30 t/s, tg_3s = 22.98 t/s
llama-server | 10949.28.297.477 I slot print_timing: id 0 | task 2770027 | n_gen = 4533, tg = 30.28 t/s, tg_3s = 29.37 t/s
llama-server | 10949.31.342.343 I slot print_timing: id 0 | task 2770027 | n_gen = 4620, tg = 30.25 t/s, tg_3s = 28.57 t/s
llama-server | 10949.34.387.604 I slot print_timing: id 0 | task 2770027 | n_gen = 4696, tg = 30.15 t/s, tg_3s = 24.96 t/s
llama-server | 10949.37.449.671 I slot print_timing: id 0 | task 2770027 | n_gen = 4784, tg = 30.12 t/s, tg_3s = 28.74 t/s
llama-server | 10949.40.499.037 I slot print_timing: id 0 | task 2770027 | n_gen = 4877, tg = 30.13 t/s, tg_3s = 30.50 t/s
llama-server | 10949.41.519.910 I slot print_timing: id 0 | task 2770027 | prompt eval time = 45407.58 ms / 43417 tokens ( 1.05 ms per token, 956.16 tokens per second)
llama-server | 10949.41.519.913 I slot print_timing: id 0 | task 2770027 | eval time = 162871.33 ms / 4930 tokens ( 33.04 ms per token, 30.26 tokens per second)
llama-server | 10949.41.519.914 I slot print_timing: id 0 | task 2770027 | total time = 208278.91 ms / 48347 tokens
llama-server | 10949.41.519.914 I slot print_timing: id 0 | task 2770027 | graphs reused = 2684373
llama-server | 10949.41.519.918 I slot print_timing: id 0 | task 2770027 | draft acceptance = 0.35362 ( 3149 accepted / 8905 generated), mean len = 2.77
llama-server | 10949.41.521.127 I slot release: id 0 | task 2770027 | stop processing: n_tokens = 48347, truncated = 0
llama-server | 10949.42.663.357 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 656786600917
llama-server | 10949.42.663.897 I slot launch_slot_: id 1 | task 2771832 | processing task, is_child = 0
llama-server | 10949.42.666.176 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2083.009 MiB)
llama-server | 10949.47.812.727 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.97 tokens per second
llama-server | 10949.49.629.835 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1276.57 tokens per second
llama-server | 10949.51.484.827 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.66 s / 1230.35 tokens per second
llama-server | 10949.53.372.968 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.54 s / 1199.32 tokens per second
llama-server | 10949.55.311.752 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.47 s / 1173.86 tokens per second
llama-server | 10949.57.280.770 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.42 s / 1154.07 tokens per second
llama-server | 10949.59.285.977 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 16384, progress = 0.37, t = 14.42 s / 1136.22 tokens per second
llama-server | 10950.01.326.845 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 18432, progress = 0.42, t = 16.45 s / 1120.25 tokens per second
llama-server | 10950.03.405.312 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 20480, progress = 0.46, t = 18.52 s / 1105.74 tokens per second
llama-server | 10950.05.525.925 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 22528, progress = 0.51, t = 20.63 s / 1092.09 tokens per second
llama-server | 10950.07.702.744 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 24576, progress = 0.56, t = 22.78 s / 1078.70 tokens per second
llama-server | 10950.09.898.265 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 26624, progress = 0.60, t = 24.98 s / 1065.66 tokens per second
llama-server | 10950.12.132.183 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 28672, progress = 0.65, t = 27.21 s / 1053.86 tokens per second
llama-server | 10950.14.398.336 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 30720, progress = 0.69, t = 29.47 s / 1042.53 tokens per second
llama-server | 10950.16.738.467 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 32768, progress = 0.74, t = 31.76 s / 1031.69 tokens per second
llama-server | 10950.19.079.666 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 34816, progress = 0.79, t = 34.13 s / 1020.22 tokens per second
llama-server | 10950.21.456.373 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 36864, progress = 0.83, t = 36.50 s / 1010.09 tokens per second
llama-server | 10950.23.864.995 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 38912, progress = 0.88, t = 38.90 s / 1000.38 tokens per second
llama-server | 10950.26.332.138 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 40960, progress = 0.93, t = 41.33 s / 991.00 tokens per second
llama-server | 10950.28.813.292 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 43008, progress = 0.97, t = 43.83 s / 981.33 tokens per second
llama-server | 10950.29.745.800 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 43689, progress = 0.99, t = 45.15 s / 967.69 tokens per second
llama-server | 10950.30.462.205 I slot print_timing: id 1 | task 2771832 | prompt processing, n_tokens = 44201, progress = 1.00, t = 45.58 s / 969.81 tokens per second
llama-server | 10950.33.729.085 I slot print_timing: id 1 | task 2771832 | n_gen = 134, tg = 43.99 t/s, tg_3s = 44.31 t/s
llama-server | 10950.36.803.189 I slot print_timing: id 1 | task 2771832 | n_gen = 235, tg = 38.37 t/s, tg_3s = 32.86 t/s
llama-server | 10950.39.869.149 I slot print_timing: id 1 | task 2771832 | n_gen = 322, tg = 35.03 t/s, tg_3s = 28.38 t/s
llama-server | 10950.42.871.425 I slot print_timing: id 1 | task 2771832 | n_gen = 425, tg = 34.85 t/s, tg_3s = 34.31 t/s
llama-server | 10950.45.947.380 I slot print_timing: id 1 | task 2771832 | n_gen = 524, tg = 34.31 t/s, tg_3s = 32.19 t/s
llama-server | 10950.48.954.295 I slot print_timing: id 1 | task 2771832 | n_gen = 620, tg = 33.92 t/s, tg_3s = 31.93 t/s
llama-server | 10950.52.033.475 I slot print_timing: id 1 | task 2771832 | n_gen = 700, tg = 32.77 t/s, tg_3s = 25.98 t/s
llama-server | 10950.55.116.675 I slot print_timing: id 1 | task 2771832 | n_gen = 795, tg = 32.53 t/s, tg_3s = 30.81 t/s
llama-server | 10950.58.133.168 I slot print_timing: id 1 | task 2771832 | n_gen = 890, tg = 32.41 t/s, tg_3s = 31.49 t/s
llama-server | 10951.01.222.548 I slot print_timing: id 1 | task 2771832 | n_gen = 991, tg = 32.44 t/s, tg_3s = 32.69 t/s
llama-server | 10951.04.308.614 I slot print_timing: id 1 | task 2771832 | n_gen = 1070, tg = 31.81 t/s, tg_3s = 25.60 t/s
llama-server | 10951.07.328.168 I slot print_timing: id 1 | task 2771832 | n_gen = 1168, tg = 31.87 t/s, tg_3s = 32.46 t/s
llama-server | 10951.10.339.171 I slot print_timing: id 1 | task 2771832 | n_gen = 1280, tg = 32.27 t/s, tg_3s = 37.20 t/s
llama-server | 10951.13.429.805 I slot print_timing: id 1 | task 2771832 | n_gen = 1359, tg = 31.79 t/s, tg_3s = 25.56 t/s
llama-server | 10951.16.454.112 I slot print_timing: id 1 | task 2771832 | n_gen = 1463, tg = 31.96 t/s, tg_3s = 34.39 t/s
llama-server | 10951.19.470.125 I slot print_timing: id 1 | task 2771832 | n_gen = 1553, tg = 31.83 t/s, tg_3s = 29.84 t/s
llama-server | 10951.22.506.087 I slot print_timing: id 1 | task 2771832 | n_gen = 1679, tg = 32.39 t/s, tg_3s = 41.50 t/s
llama-server | 10951.25.528.467 I slot print_timing: id 1 | task 2771832 | n_gen = 1807, tg = 32.94 t/s, tg_3s = 42.35 t/s
llama-server | 10951.28.575.586 I slot print_timing: id 1 | task 2771832 | n_gen = 1953, tg = 33.73 t/s, tg_3s = 47.91 t/s
llama-server | 10951.29.314.178 I slot print_timing: id 1 | task 2771832 | prompt eval time = 46434.44 ms / 44205 tokens ( 1.05 ms per token, 951.99 tokens per second)
llama-server | 10951.29.314.181 I slot print_timing: id 1 | task 2771832 | eval time = 58608.82 ms / 1998 tokens ( 29.35 ms per token, 34.07 tokens per second)
llama-server | 10951.29.314.182 I slot print_timing: id 1 | task 2771832 | total time = 105043.26 ms / 46203 tokens
llama-server | 10951.29.314.182 I slot print_timing: id 1 | task 2771832 | graphs reused = 2685007
llama-server | 10951.29.314.185 I slot print_timing: id 1 | task 2771832 | draft acceptance = 0.42146 ( 1355 accepted / 3215 generated), mean len = 3.11
llama-server | 10951.29.315.416 I slot release: id 1 | task 2771832 | stop processing: n_tokens = 46203, truncated = 0
llama-server | 10951.46.528.703 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 656997361179
llama-server | 10951.46.529.487 I slot launch_slot_: id 0 | task 2772500 | processing task, is_child = 0
llama-server | 10951.46.533.955 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1989.978 MiB)
llama-server | 10951.53.653.356 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.74 s / 1295.18 tokens per second
llama-server | 10951.55.482.341 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.56 s / 1248.51 tokens per second
llama-server | 10951.57.345.367 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.42 s / 1216.62 tokens per second
llama-server | 10951.59.245.825 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.31 s / 1192.01 tokens per second
llama-server | 10952.01.185.145 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.24 s / 1171.37 tokens per second
llama-server | 10952.03.166.199 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 16384, progress = 0.37, t = 14.21 s / 1153.29 tokens per second
llama-server | 10952.05.185.514 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 18432, progress = 0.41, t = 16.22 s / 1136.49 tokens per second
llama-server | 10952.07.245.408 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 20480, progress = 0.46, t = 18.27 s / 1121.11 tokens per second
llama-server | 10952.09.348.610 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 22528, progress = 0.51, t = 20.36 s / 1106.65 tokens per second
llama-server | 10952.11.507.661 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 24576, progress = 0.55, t = 22.50 s / 1092.48 tokens per second
llama-server | 10952.13.692.328 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 26624, progress = 0.60, t = 24.68 s / 1078.70 tokens per second
llama-server | 10952.15.913.640 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 28672, progress = 0.64, t = 26.89 s / 1066.13 tokens per second
llama-server | 10952.18.168.641 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 30720, progress = 0.69, t = 29.14 s / 1054.21 tokens per second
llama-server | 10952.20.497.124 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 32768, progress = 0.74, t = 31.42 s / 1042.80 tokens per second
llama-server | 10952.22.825.558 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 34816, progress = 0.78, t = 33.78 s / 1030.73 tokens per second
llama-server | 10952.25.192.180 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 36864, progress = 0.83, t = 36.13 s / 1020.18 tokens per second
llama-server | 10952.27.593.994 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 38912, progress = 0.87, t = 38.53 s / 1009.96 tokens per second
llama-server | 10952.30.047.454 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 40960, progress = 0.92, t = 40.96 s / 1000.11 tokens per second
llama-server | 10952.32.523.110 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 43008, progress = 0.97, t = 43.44 s / 990.07 tokens per second
llama-server | 10952.33.859.706 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 44051, progress = 0.99, t = 45.34 s / 971.47 tokens per second
llama-server | 10952.34.580.916 I slot print_timing: id 0 | task 2772500 | prompt processing, n_tokens = 44563, progress = 1.00, t = 45.60 s / 977.34 tokens per second
llama-server | 10952.38.313.625 I slot print_timing: id 0 | task 2772500 | n_gen = 102, tg = 28.54 t/s, tg_3s = 28.82 t/s
llama-server | 10952.41.378.974 I slot print_timing: id 0 | task 2772500 | n_gen = 162, tg = 24.38 t/s, tg_3s = 19.57 t/s
llama-server | 10952.44.444.608 I slot print_timing: id 0 | task 2772500 | n_gen = 231, tg = 23.78 t/s, tg_3s = 22.51 t/s
llama-server | 10952.47.530.997 I slot print_timing: id 0 | task 2772500 | n_gen = 313, tg = 24.46 t/s, tg_3s = 26.57 t/s
llama-server | 10952.50.602.704 I slot print_timing: id 0 | task 2772500 | n_gen = 405, tg = 25.52 t/s, tg_3s = 29.95 t/s
llama-server | 10952.53.617.549 I slot print_timing: id 0 | task 2772500 | prompt eval time = 46404.33 ms / 44567 tokens ( 1.04 ms per token, 960.41 tokens per second)
llama-server | 10952.53.617.553 I slot print_timing: id 0 | task 2772500 | eval time = 18843.28 ms / 516 tokens ( 36.59 ms per token, 27.33 tokens per second)
llama-server | 10952.53.617.553 I slot print_timing: id 0 | task 2772500 | total time = 65247.61 ms / 45083 tokens
llama-server | 10952.53.617.554 I slot print_timing: id 0 | task 2772500 | graphs reused = 2685212
llama-server | 10952.53.617.557 I slot print_timing: id 0 | task 2772500 | draft acceptance = 0.29519 ( 307 accepted / 1040 generated), mean len = 2.48
llama-server | 10952.53.618.866 I slot release: id 0 | task 2772500 | stop processing: n_tokens = 45082, truncated = 0
llama-server | 10952.54.679.110 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 657105155467
llama-server | 10952.54.679.664 I slot launch_slot_: id 1 | task 2772733 | processing task, is_child = 0
llama-server | 10952.54.681.738 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2038.488 MiB)
llama-server | 10952.59.623.715 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.00 s / 1364.39 tokens per second
llama-server | 10953.01.439.551 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1277.81 tokens per second
llama-server | 10953.03.293.647 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.65 s / 1231.47 tokens per second
llama-server | 10953.05.184.987 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.53 s / 1199.97 tokens per second
llama-server | 10953.07.121.827 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.46 s / 1174.21 tokens per second
llama-server | 10953.09.087.441 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.42 s / 1154.60 tokens per second
llama-server | 10953.11.091.177 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 16384, progress = 0.37, t = 14.41 s / 1136.91 tokens per second
llama-server | 10953.13.130.556 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 18432, progress = 0.41, t = 16.44 s / 1120.95 tokens per second
llama-server | 10953.15.213.207 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 20480, progress = 0.46, t = 18.51 s / 1106.30 tokens per second
llama-server | 10953.17.333.482 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 22528, progress = 0.50, t = 20.62 s / 1092.29 tokens per second
llama-server | 10953.19.507.101 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 24576, progress = 0.55, t = 22.78 s / 1079.04 tokens per second
llama-server | 10953.21.703.448 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 26624, progress = 0.60, t = 24.98 s / 1066.02 tokens per second
llama-server | 10953.23.935.940 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 28672, progress = 0.64, t = 27.20 s / 1054.11 tokens per second
llama-server | 10953.26.199.444 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 30720, progress = 0.69, t = 29.45 s / 1042.95 tokens per second
llama-server | 10953.28.535.323 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 32768, progress = 0.73, t = 31.74 s / 1032.26 tokens per second
llama-server | 10953.30.872.134 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 34816, progress = 0.78, t = 34.11 s / 1020.72 tokens per second
llama-server | 10953.33.245.726 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 36864, progress = 0.83, t = 36.47 s / 1010.77 tokens per second
llama-server | 10953.35.653.489 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 38912, progress = 0.87, t = 38.87 s / 1001.03 tokens per second
llama-server | 10953.38.113.198 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 40960, progress = 0.92, t = 41.30 s / 991.66 tokens per second
llama-server | 10953.40.591.909 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 43008, progress = 0.96, t = 43.79 s / 982.10 tokens per second
llama-server | 10953.42.033.595 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 44126, progress = 0.99, t = 45.70 s / 965.51 tokens per second
llama-server | 10953.42.749.762 I slot print_timing: id 1 | task 2772733 | prompt processing, n_tokens = 44638, progress = 1.00, t = 46.05 s / 969.35 tokens per second
llama-server | 10953.46.131.525 I slot print_timing: id 1 | task 2772733 | n_gen = 101, tg = 31.37 t/s, tg_3s = 31.68 t/s
llama-server | 10953.47.692.859 I slot print_timing: id 1 | task 2772733 | prompt eval time = 46859.27 ms / 44642 tokens ( 1.05 ms per token, 952.68 tokens per second)
llama-server | 10953.47.692.862 I slot print_timing: id 1 | task 2772733 | eval time = 4748.77 ms / 191 tokens ( 24.99 ms per token, 40.01 tokens per second)
llama-server | 10953.47.692.863 I slot print_timing: id 1 | task 2772733 | total time = 51608.04 ms / 44833 tokens
llama-server | 10953.47.692.863 I slot print_timing: id 1 | task 2772733 | graphs reused = 2685262
llama-server | 10953.47.692.866 I slot print_timing: id 1 | task 2772733 | draft acceptance = 0.53077 ( 138 accepted / 260 generated), mean len = 3.65
llama-server | 10953.47.694.219 I slot release: id 1 | task 2772733 | stop processing: n_tokens = 44832, truncated = 0
llama-server | 10953.48.774.402 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 657189458918
llama-server | 10953.48.775.144 I slot launch_slot_: id 0 | task 2772810 | processing task, is_child = 0
llama-server | 10953.48.777.326 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2176.504 MiB)
llama-server | 10953.55.612.598 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.80 s / 1280.27 tokens per second
llama-server | 10953.57.462.020 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.64 s / 1233.85 tokens per second
llama-server | 10953.59.345.102 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.51 s / 1202.61 tokens per second
llama-server | 10954.01.273.071 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.43 s / 1177.72 tokens per second
llama-server | 10954.03.237.920 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.38 s / 1157.61 tokens per second
llama-server | 10954.05.238.563 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 16384, progress = 0.37, t = 14.38 s / 1139.64 tokens per second
llama-server | 10954.07.275.159 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 18432, progress = 0.41, t = 16.41 s / 1123.45 tokens per second
llama-server | 10954.09.352.079 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 20480, progress = 0.46, t = 18.47 s / 1108.68 tokens per second
llama-server | 10954.11.468.115 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 22528, progress = 0.50, t = 20.58 s / 1094.80 tokens per second
llama-server | 10954.13.638.871 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 24576, progress = 0.55, t = 22.73 s / 1081.39 tokens per second
llama-server | 10954.15.832.431 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 26624, progress = 0.59, t = 24.93 s / 1068.11 tokens per second
llama-server | 10954.18.063.931 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 28672, progress = 0.64, t = 27.14 s / 1056.31 tokens per second
llama-server | 10954.20.329.610 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 30720, progress = 0.69, t = 29.40 s / 1044.84 tokens per second
llama-server | 10954.22.666.702 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 32768, progress = 0.73, t = 31.69 s / 1033.93 tokens per second
llama-server | 10954.25.002.676 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 34816, progress = 0.78, t = 34.06 s / 1022.30 tokens per second
llama-server | 10954.27.377.235 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 36864, progress = 0.82, t = 36.42 s / 1012.18 tokens per second
llama-server | 10954.29.784.574 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 38912, progress = 0.87, t = 38.82 s / 1002.39 tokens per second
llama-server | 10954.32.243.435 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 40960, progress = 0.92, t = 41.25 s / 992.91 tokens per second
llama-server | 10954.34.721.612 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 43008, progress = 0.96, t = 43.74 s / 983.30 tokens per second
llama-server | 10954.36.307.689 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 44235, progress = 0.99, t = 45.65 s / 969.01 tokens per second
llama-server | 10954.37.029.502 I slot print_timing: id 0 | task 2772810 | prompt processing, n_tokens = 44747, progress = 1.00, t = 46.15 s / 969.67 tokens per second
llama-server | 10954.41.362.363 I slot print_timing: id 0 | task 2772810 | n_gen = 105, tg = 25.41 t/s, tg_3s = 25.66 t/s
llama-server | 10954.44.443.171 I slot print_timing: id 0 | task 2772810 | n_gen = 251, tg = 34.85 t/s, tg_3s = 47.39 t/s
llama-server | 10954.44.805.793 I slot print_timing: id 0 | task 2772810 | prompt eval time = 47002.64 ms / 44751 tokens ( 1.05 ms per token, 952.10 tokens per second)
llama-server | 10954.44.805.796 I slot print_timing: id 0 | task 2772810 | eval time = 7535.68 ms / 270 tokens ( 28.01 ms per token, 35.70 tokens per second)
llama-server | 10954.44.805.796 I slot print_timing: id 0 | task 2772810 | total time = 54538.31 ms / 45021 tokens
llama-server | 10954.44.805.797 I slot print_timing: id 0 | task 2772810 | graphs reused = 2685343
llama-server | 10954.44.805.800 I slot print_timing: id 0 | task 2772810 | draft acceptance = 0.44819 ( 186 accepted / 415 generated), mean len = 3.24
llama-server | 10954.44.807.126 I slot release: id 0 | task 2772810 | stop processing: n_tokens = 45020, truncated = 0
llama-server | 10954.45.795.862 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 657243534271
llama-server | 10954.45.796.590 I slot launch_slot_: id 1 | task 2772918 | processing task, is_child = 0
llama-server | 10954.45.798.628 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2105.219 MiB)
llama-server | 10954.52.831.359 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.80 s / 1280.94 tokens per second
llama-server | 10954.54.679.958 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.63 s / 1234.68 tokens per second
llama-server | 10954.56.567.475 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.51 s / 1203.23 tokens per second
llama-server | 10954.58.497.039 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.43 s / 1177.58 tokens per second
llama-server | 10955.00.456.633 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.39 s / 1157.51 tokens per second
llama-server | 10955.02.457.675 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.37 s / 1139.93 tokens per second
llama-server | 10955.04.493.848 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 18432, progress = 0.41, t = 16.40 s / 1123.78 tokens per second
llama-server | 10955.06.569.523 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.47 s / 1108.89 tokens per second
llama-server | 10955.08.685.481 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 22528, progress = 0.50, t = 20.57 s / 1095.05 tokens per second
llama-server | 10955.10.854.595 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.72 s / 1081.66 tokens per second
llama-server | 10955.13.046.265 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 26624, progress = 0.59, t = 24.91 s / 1068.62 tokens per second
llama-server | 10955.15.275.607 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 28672, progress = 0.63, t = 27.13 s / 1056.72 tokens per second
llama-server | 10955.17.540.106 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 30720, progress = 0.68, t = 29.39 s / 1045.29 tokens per second
llama-server | 10955.19.874.612 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 32768, progress = 0.72, t = 31.68 s / 1034.35 tokens per second
llama-server | 10955.22.209.830 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 34816, progress = 0.77, t = 34.04 s / 1022.73 tokens per second
llama-server | 10955.24.582.954 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 36864, progress = 0.81, t = 36.40 s / 1012.64 tokens per second
llama-server | 10955.26.990.612 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 38912, progress = 0.86, t = 38.80 s / 1002.79 tokens per second
llama-server | 10955.29.451.209 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 40960, progress = 0.90, t = 41.24 s / 993.24 tokens per second
llama-server | 10955.31.932.472 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 43008, progress = 0.95, t = 43.72 s / 983.62 tokens per second
llama-server | 10955.34.242.624 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 44857, progress = 0.99, t = 46.23 s / 970.27 tokens per second
llama-server | 10955.34.977.801 I slot print_timing: id 1 | task 2772918 | prompt processing, n_tokens = 45369, progress = 1.00, t = 46.86 s / 968.10 tokens per second
llama-server | 10955.38.730.484 I slot print_timing: id 1 | task 2772918 | n_gen = 102, tg = 28.39 t/s, tg_3s = 28.67 t/s
llama-server | 10955.41.805.353 I slot print_timing: id 1 | task 2772918 | n_gen = 188, tg = 28.19 t/s, tg_3s = 27.97 t/s
llama-server | 10955.44.818.000 I slot print_timing: id 1 | task 2772918 | n_gen = 295, tg = 30.48 t/s, tg_3s = 35.52 t/s
llama-server | 10955.47.903.211 I slot print_timing: id 1 | task 2772918 | n_gen = 372, tg = 29.14 t/s, tg_3s = 24.96 t/s
llama-server | 10955.50.920.756 I slot print_timing: id 1 | task 2772918 | n_gen = 465, tg = 29.46 t/s, tg_3s = 30.82 t/s
llama-server | 10955.53.928.099 I slot print_timing: id 1 | task 2772918 | n_gen = 566, tg = 30.12 t/s, tg_3s = 33.58 t/s
llama-server | 10955.56.935.503 I slot print_timing: id 1 | task 2772918 | n_gen = 662, tg = 30.37 t/s, tg_3s = 31.92 t/s
llama-server | 10955.59.966.249 I slot print_timing: id 1 | task 2772918 | n_gen = 749, tg = 30.17 t/s, tg_3s = 28.71 t/s
llama-server | 10956.02.983.213 I slot print_timing: id 1 | task 2772918 | n_gen = 856, tg = 30.74 t/s, tg_3s = 35.47 t/s
llama-server | 10956.06.015.654 I slot print_timing: id 1 | task 2772918 | n_gen = 964, tg = 31.22 t/s, tg_3s = 35.61 t/s
llama-server | 10956.09.034.744 I slot print_timing: id 1 | task 2772918 | n_gen = 1067, tg = 31.48 t/s, tg_3s = 34.12 t/s
llama-server | 10956.12.057.504 I slot print_timing: id 1 | task 2772918 | n_gen = 1171, tg = 31.72 t/s, tg_3s = 34.41 t/s
llama-server | 10956.15.097.835 I slot print_timing: id 1 | task 2772918 | n_gen = 1283, tg = 32.11 t/s, tg_3s = 36.84 t/s
llama-server | 10956.17.485.017 I slot print_timing: id 1 | task 2772918 | prompt eval time = 47682.83 ms / 45373 tokens ( 1.05 ms per token, 951.56 tokens per second)
llama-server | 10956.17.485.021 I slot print_timing: id 1 | task 2772918 | eval time = 42312.52 ms / 1367 tokens ( 30.98 ms per token, 32.28 tokens per second)
llama-server | 10956.17.485.021 I slot print_timing: id 1 | task 2772918 | total time = 89995.35 ms / 46740 tokens
llama-server | 10956.17.485.022 I slot print_timing: id 1 | task 2772918 | graphs reused = 2685800
llama-server | 10956.17.485.025 I slot print_timing: id 1 | task 2772918 | draft acceptance = 0.39050 ( 904 accepted / 2315 generated), mean len = 2.95
llama-server | 10956.17.486.397 I slot release: id 1 | task 2772918 | stop processing: n_tokens = 46740, truncated = 0
llama-server | 10956.18.737.994 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 657300647178
llama-server | 10956.18.738.720 I slot launch_slot_: id 0 | task 2773406 | processing task, is_child = 0
llama-server | 10956.18.740.877 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2067.947 MiB)
llama-server | 10956.23.842.965 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.49 tokens per second
llama-server | 10956.25.659.353 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1276.15 tokens per second
llama-server | 10956.27.516.761 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.66 s / 1230.60 tokens per second
llama-server | 10956.29.404.970 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.54 s / 1198.88 tokens per second
llama-server | 10956.31.339.824 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.47 s / 1173.72 tokens per second
llama-server | 10956.33.303.226 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.42 s / 1154.15 tokens per second
llama-server | 10956.35.308.592 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.41 s / 1136.74 tokens per second
llama-server | 10956.37.349.929 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 18432, progress = 0.41, t = 16.45 s / 1120.61 tokens per second
llama-server | 10956.39.429.921 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.52 s / 1105.96 tokens per second
llama-server | 10956.41.551.327 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 22528, progress = 0.50, t = 20.63 s / 1092.14 tokens per second
llama-server | 10956.43.722.906 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.78 s / 1078.90 tokens per second
llama-server | 10956.45.919.068 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 26624, progress = 0.59, t = 24.98 s / 1065.98 tokens per second
llama-server | 10956.48.150.845 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 28672, progress = 0.63, t = 27.20 s / 1054.12 tokens per second
llama-server | 10956.50.416.560 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 30720, progress = 0.68, t = 29.46 s / 1042.87 tokens per second
llama-server | 10956.52.753.134 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 32768, progress = 0.72, t = 31.75 s / 1032.10 tokens per second
llama-server | 10956.55.090.510 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 34816, progress = 0.77, t = 34.11 s / 1020.64 tokens per second
llama-server | 10956.57.465.846 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 36864, progress = 0.81, t = 36.48 s / 1010.61 tokens per second
llama-server | 10956.59.876.797 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 38912, progress = 0.86, t = 38.88 s / 1000.87 tokens per second
llama-server | 10957.02.337.728 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 40960, progress = 0.90, t = 41.31 s / 991.41 tokens per second
llama-server | 10957.04.816.969 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 43008, progress = 0.95, t = 43.80 s / 981.86 tokens per second
llama-server | 10957.07.213.604 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 44900, progress = 0.99, t = 46.31 s / 969.59 tokens per second
llama-server | 10957.07.939.914 I slot print_timing: id 0 | task 2773406 | prompt processing, n_tokens = 45412, progress = 1.00, t = 47.02 s / 965.88 tokens per second
llama-server | 10957.11.598.789 I slot print_timing: id 0 | task 2773406 | n_gen = 101, tg = 28.81 t/s, tg_3s = 29.09 t/s
llama-server | 10957.14.615.758 I slot print_timing: id 0 | task 2773406 | n_gen = 192, tg = 29.44 t/s, tg_3s = 30.16 t/s
llama-server | 10957.17.617.049 I slot print_timing: id 0 | task 2773406 | n_gen = 276, tg = 28.98 t/s, tg_3s = 27.99 t/s
llama-server | 10957.20.619.733 I slot print_timing: id 0 | task 2773406 | n_gen = 368, tg = 29.38 t/s, tg_3s = 30.64 t/s
llama-server | 10957.23.643.880 I slot print_timing: id 0 | task 2773406 | n_gen = 462, tg = 29.71 t/s, tg_3s = 31.08 t/s
llama-server | 10957.26.728.463 I slot print_timing: id 0 | task 2773406 | n_gen = 523, tg = 28.06 t/s, tg_3s = 19.78 t/s
llama-server | 10957.29.816.476 I slot print_timing: id 0 | task 2773406 | n_gen = 593, tg = 27.29 t/s, tg_3s = 22.67 t/s
llama-server | 10957.32.840.619 I slot print_timing: id 0 | task 2773406 | n_gen = 676, tg = 27.31 t/s, tg_3s = 27.45 t/s
llama-server | 10957.35.856.814 I slot print_timing: id 0 | task 2773406 | n_gen = 753, tg = 27.12 t/s, tg_3s = 25.53 t/s
llama-server | 10957.38.864.079 I slot print_timing: id 0 | task 2773406 | n_gen = 825, tg = 26.81 t/s, tg_3s = 23.94 t/s
llama-server | 10957.41.871.806 I slot print_timing: id 0 | task 2773406 | n_gen = 896, tg = 26.52 t/s, tg_3s = 23.61 t/s
llama-server | 10957.44.902.092 I slot print_timing: id 0 | task 2773406 | n_gen = 976, tg = 26.51 t/s, tg_3s = 26.40 t/s
llama-server | 10957.47.923.189 I slot print_timing: id 0 | task 2773406 | n_gen = 1070, tg = 26.86 t/s, tg_3s = 31.11 t/s
llama-server | 10957.50.937.650 I slot print_timing: id 0 | task 2773406 | n_gen = 1155, tg = 26.96 t/s, tg_3s = 28.20 t/s
llama-server | 10957.53.979.184 I slot print_timing: id 0 | task 2773406 | n_gen = 1263, tg = 27.52 t/s, tg_3s = 35.51 t/s
llama-server | 10957.54.716.068 I slot print_timing: id 0 | task 2773406 | prompt eval time = 47828.54 ms / 45416 tokens ( 1.05 ms per token, 949.56 tokens per second)
llama-server | 10957.54.716.071 I slot print_timing: id 0 | task 2773406 | eval time = 46588.59 ms / 1300 tokens ( 35.86 ms per token, 27.88 tokens per second)
llama-server | 10957.54.716.071 I slot print_timing: id 0 | task 2773406 | total time = 94417.13 ms / 46716 tokens
llama-server | 10957.54.716.072 I slot print_timing: id 0 | task 2773406 | graphs reused = 2686304
llama-server | 10957.54.716.075 I slot print_timing: id 0 | task 2773406 | draft acceptance = 0.30980 ( 790 accepted / 2550 generated), mean len = 2.55
llama-server | 10957.54.717.304 I slot release: id 0 | task 2773406 | stop processing: n_tokens = 46716, truncated = 0
llama-server | 10957.55.927.512 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 657393326449
llama-server | 10957.55.928.279 I slot launch_slot_: id 1 | task 2773941 | processing task, is_child = 0
llama-server | 10957.55.930.396 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2059.635 MiB)
llama-server | 10958.01.205.644 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.00 s / 1363.48 tokens per second
llama-server | 10958.03.022.078 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1277.23 tokens per second
llama-server | 10958.04.880.893 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1230.96 tokens per second
llama-server | 10958.06.768.424 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.54 s / 1199.24 tokens per second
llama-server | 10958.08.701.179 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.46 s / 1174.48 tokens per second
llama-server | 10958.10.665.145 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 14336, progress = 0.36, t = 12.42 s / 1154.63 tokens per second
llama-server | 10958.12.669.121 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.41 s / 1137.14 tokens per second
llama-server | 10958.14.712.623 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.44 s / 1121.03 tokens per second
llama-server | 10958.16.794.892 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.52 s / 1106.07 tokens per second
llama-server | 10958.18.924.150 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 22528, progress = 0.57, t = 20.62 s / 1092.27 tokens per second
llama-server | 10958.21.097.924 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 24576, progress = 0.62, t = 22.79 s / 1078.54 tokens per second
llama-server | 10958.23.292.700 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 26624, progress = 0.67, t = 24.98 s / 1065.65 tokens per second
llama-server | 10958.25.527.862 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.21 s / 1053.87 tokens per second
llama-server | 10958.27.793.461 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 30720, progress = 0.78, t = 29.47 s / 1042.52 tokens per second
llama-server | 10958.30.131.155 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 32768, progress = 0.83, t = 31.76 s / 1031.77 tokens per second
llama-server | 10958.32.468.889 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 34816, progress = 0.88, t = 34.12 s / 1020.28 tokens per second
llama-server | 10958.34.843.205 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 36864, progress = 0.93, t = 36.49 s / 1010.31 tokens per second
llama-server | 10958.37.251.248 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 38912, progress = 0.99, t = 38.89 s / 1000.60 tokens per second
llama-server | 10958.37.340.024 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 38940, progress = 0.99, t = 39.60 s / 983.44 tokens per second
llama-server | 10958.38.036.927 I slot print_timing: id 1 | task 2773941 | prompt processing, n_tokens = 39452, progress = 1.00, t = 39.78 s / 991.84 tokens per second
llama-server | 10958.40.412.326 I slot print_timing: id 1 | task 2773941 | prompt eval time = 40611.10 ms / 39456 tokens ( 1.03 ms per token, 971.56 tokens per second)
llama-server | 10958.40.412.329 I slot print_timing: id 1 | task 2773941 | eval time = 2135.61 ms / 93 tokens ( 23.21 ms per token, 43.08 tokens per second)
llama-server | 10958.40.412.330 I slot print_timing: id 1 | task 2773941 | total time = 42746.71 ms / 39549 tokens
llama-server | 10958.40.412.331 I slot print_timing: id 1 | task 2773941 | graphs reused = 2686327
llama-server | 10958.40.412.334 I slot print_timing: id 1 | task 2773941 | draft acceptance = 0.56667 ( 68 accepted / 120 generated), mean len = 3.83
llama-server | 10958.40.413.440 I slot release: id 1 | task 2773941 | stop processing: n_tokens = 39548, truncated = 0
llama-server | 10958.41.482.300 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 657490557356
llama-server | 10958.41.482.900 I slot launch_slot_: id 0 | task 2773988 | processing task, is_child = 0
llama-server | 10958.41.484.868 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2065.885 MiB)
llama-server | 10958.46.553.651 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.00 s / 1364.00 tokens per second
llama-server | 10958.48.366.493 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.81 s / 1278.36 tokens per second
llama-server | 10958.50.216.925 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.64 s / 1232.94 tokens per second
llama-server | 10958.52.101.446 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.52 s / 1201.59 tokens per second
llama-server | 10958.54.023.663 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.43 s / 1177.64 tokens per second
llama-server | 10958.55.998.360 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.40 s / 1156.52 tokens per second
llama-server | 10958.57.999.072 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 16384, progress = 0.35, t = 14.39 s / 1138.66 tokens per second
llama-server | 10959.00.034.639 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.42 s / 1122.64 tokens per second
llama-server | 10959.02.111.120 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 20480, progress = 0.44, t = 18.48 s / 1108.02 tokens per second
llama-server | 10959.04.227.972 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.59 s / 1094.24 tokens per second
llama-server | 10959.06.396.009 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 24576, progress = 0.53, t = 22.74 s / 1080.92 tokens per second
llama-server | 10959.08.589.144 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.93 s / 1067.93 tokens per second
llama-server | 10959.10.819.669 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 28672, progress = 0.62, t = 27.15 s / 1056.07 tokens per second
llama-server | 10959.13.083.463 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 30720, progress = 0.66, t = 29.41 s / 1044.66 tokens per second
llama-server | 10959.15.419.193 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 32768, progress = 0.71, t = 31.70 s / 1033.77 tokens per second
llama-server | 10959.17.753.972 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 34816, progress = 0.75, t = 34.06 s / 1022.19 tokens per second
llama-server | 10959.20.128.323 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 36864, progress = 0.80, t = 36.42 s / 1012.10 tokens per second
llama-server | 10959.22.535.265 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 38912, progress = 0.84, t = 38.82 s / 1002.30 tokens per second
llama-server | 10959.24.993.145 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 40960, progress = 0.89, t = 41.26 s / 992.85 tokens per second
llama-server | 10959.27.479.058 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 43008, progress = 0.93, t = 43.74 s / 983.25 tokens per second
llama-server | 10959.29.993.325 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 45056, progress = 0.97, t = 46.25 s / 974.14 tokens per second
llama-server | 10959.30.873.143 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 45727, progress = 0.99, t = 47.59 s / 960.81 tokens per second
llama-server | 10959.31.603.746 I slot print_timing: id 0 | task 2773988 | prompt processing, n_tokens = 46239, progress = 1.00, t = 47.97 s / 964.01 tokens per second
llama-server | 10959.34.900.198 I slot print_timing: id 0 | task 2773988 | n_gen = 109, tg = 35.37 t/s, tg_3s = 35.70 t/s
llama-server | 10959.37.911.845 I slot print_timing: id 0 | task 2773988 | n_gen = 202, tg = 33.14 t/s, tg_3s = 30.88 t/s
llama-server | 10959.40.925.325 I slot print_timing: id 0 | task 2773988 | n_gen = 291, tg = 31.94 t/s, tg_3s = 29.53 t/s
llama-server | 10959.43.954.460 I slot print_timing: id 0 | task 2773988 | n_gen = 387, tg = 31.88 t/s, tg_3s = 31.69 t/s
llama-server | 10959.46.973.573 I slot print_timing: id 0 | task 2773988 | n_gen = 488, tg = 32.20 t/s, tg_3s = 33.45 t/s
llama-server | 10959.49.989.104 I slot print_timing: id 0 | task 2773988 | n_gen = 583, tg = 32.08 t/s, tg_3s = 31.50 t/s
llama-server | 10959.53.028.248 I slot print_timing: id 0 | task 2773988 | n_gen = 698, tg = 32.91 t/s, tg_3s = 37.84 t/s
llama-server | 10959.56.060.568 I slot print_timing: id 0 | task 2773988 | n_gen = 815, tg = 33.62 t/s, tg_3s = 38.58 t/s
llama-server | 10959.59.103.978 I slot print_timing: id 0 | task 2773988 | n_gen = 890, tg = 32.62 t/s, tg_3s = 24.64 t/s
llama-server | 10960.02.131.076 I slot print_timing: id 0 | task 2773988 | n_gen = 989, tg = 32.62 t/s, tg_3s = 32.70 t/s
llama-server | 10960.05.164.750 I slot print_timing: id 0 | task 2773988 | n_gen = 1108, tg = 33.23 t/s, tg_3s = 39.23 t/s
llama-server | 10960.08.214.919 I slot print_timing: id 0 | task 2773988 | n_gen = 1201, tg = 33.00 t/s, tg_3s = 30.49 t/s
llama-server | 10960.11.252.411 I slot print_timing: id 0 | task 2773988 | n_gen = 1309, tg = 33.19 t/s, tg_3s = 35.56 t/s
llama-server | 10960.14.301.939 I slot print_timing: id 0 | task 2773988 | n_gen = 1395, tg = 32.83 t/s, tg_3s = 28.20 t/s
llama-server | 10960.17.344.241 I slot print_timing: id 0 | task 2773988 | n_gen = 1496, tg = 32.86 t/s, tg_3s = 33.20 t/s
llama-server | 10960.20.390.847 I slot print_timing: id 0 | task 2773988 | n_gen = 1592, tg = 32.77 t/s, tg_3s = 31.51 t/s
llama-server | 10960.23.446.487 I slot print_timing: id 0 | task 2773988 | n_gen = 1688, tg = 32.69 t/s, tg_3s = 31.42 t/s
llama-server | 10960.26.492.369 I slot print_timing: id 0 | task 2773988 | n_gen = 1790, tg = 32.74 t/s, tg_3s = 33.49 t/s
llama-server | 10960.29.557.042 I slot print_timing: id 0 | task 2773988 | n_gen = 1885, tg = 32.65 t/s, tg_3s = 31.00 t/s
llama-server | 10960.32.606.119 I slot print_timing: id 0 | task 2773988 | n_gen = 1940, tg = 31.91 t/s, tg_3s = 18.04 t/s
llama-server | 10960.35.649.609 I slot print_timing: id 0 | task 2773988 | n_gen = 2005, tg = 31.41 t/s, tg_3s = 21.36 t/s
llama-server | 10960.38.692.536 I slot print_timing: id 0 | task 2773988 | n_gen = 2069, tg = 30.94 t/s, tg_3s = 21.03 t/s
llama-server | 10960.41.756.889 I slot print_timing: id 0 | task 2773988 | n_gen = 2147, tg = 30.70 t/s, tg_3s = 25.45 t/s
llama-server | 10960.44.805.404 I slot print_timing: id 0 | task 2773988 | n_gen = 2228, tg = 30.52 t/s, tg_3s = 26.57 t/s
llama-server | 10960.47.857.537 I slot print_timing: id 0 | task 2773988 | n_gen = 2297, tg = 30.21 t/s, tg_3s = 22.61 t/s
llama-server | 10960.50.933.176 I slot print_timing: id 0 | task 2773988 | n_gen = 2398, tg = 30.31 t/s, tg_3s = 32.84 t/s
llama-server | 10960.53.985.750 I slot print_timing: id 0 | task 2773988 | n_gen = 2486, tg = 30.25 t/s, tg_3s = 28.83 t/s
llama-server | 10960.57.035.710 I slot print_timing: id 0 | task 2773988 | n_gen = 2561, tg = 30.05 t/s, tg_3s = 24.59 t/s
llama-server | 10961.00.086.126 I slot print_timing: id 0 | task 2773988 | n_gen = 2645, tg = 29.96 t/s, tg_3s = 27.54 t/s
llama-server | 10961.03.161.291 I slot print_timing: id 0 | task 2773988 | n_gen = 2726, tg = 29.84 t/s, tg_3s = 26.34 t/s
llama-server | 10961.06.225.637 I slot print_timing: id 0 | task 2773988 | n_gen = 2837, tg = 30.05 t/s, tg_3s = 36.22 t/s
llama-server | 10961.09.302.452 I slot print_timing: id 0 | task 2773988 | n_gen = 2918, tg = 29.93 t/s, tg_3s = 26.33 t/s
llama-server | 10961.12.375.026 I slot print_timing: id 0 | task 2773988 | n_gen = 3021, tg = 30.04 t/s, tg_3s = 33.52 t/s
llama-server | 10961.15.437.995 I slot print_timing: id 0 | task 2773988 | n_gen = 3109, tg = 30.00 t/s, tg_3s = 28.73 t/s
llama-server | 10961.18.523.279 I slot print_timing: id 0 | task 2773988 | n_gen = 3217, tg = 30.15 t/s, tg_3s = 35.00 t/s
llama-server | 10961.21.595.518 I slot print_timing: id 0 | task 2773988 | n_gen = 3310, tg = 30.15 t/s, tg_3s = 30.27 t/s
llama-server | 10961.24.664.517 I slot print_timing: id 0 | task 2773988 | n_gen = 3393, tg = 30.07 t/s, tg_3s = 27.04 t/s
llama-server | 10961.27.752.773 I slot print_timing: id 0 | task 2773988 | n_gen = 3477, tg = 29.99 t/s, tg_3s = 27.20 t/s
llama-server | 10961.30.829.290 I slot print_timing: id 0 | task 2773988 | n_gen = 3571, tg = 30.00 t/s, tg_3s = 30.55 t/s
llama-server | 10961.33.904.130 I slot print_timing: id 0 | task 2773988 | n_gen = 3663, tg = 30.00 t/s, tg_3s = 29.92 t/s
llama-server | 10961.36.990.049 I slot print_timing: id 0 | task 2773988 | n_gen = 3740, tg = 29.88 t/s, tg_3s = 24.95 t/s
llama-server | 10961.40.068.783 I slot print_timing: id 0 | task 2773988 | n_gen = 3840, tg = 29.94 t/s, tg_3s = 32.48 t/s
llama-server | 10961.43.147.257 I slot print_timing: id 0 | task 2773988 | n_gen = 3932, tg = 29.94 t/s, tg_3s = 29.88 t/s
llama-server | 10961.46.150.712 I slot print_timing: id 0 | task 2773988 | n_gen = 4022, tg = 29.94 t/s, tg_3s = 29.97 t/s
llama-server | 10961.49.236.557 I slot print_timing: id 0 | task 2773988 | n_gen = 4113, tg = 29.93 t/s, tg_3s = 29.49 t/s
llama-server | 10961.52.247.974 I slot print_timing: id 0 | task 2773988 | n_gen = 4189, tg = 29.83 t/s, tg_3s = 25.24 t/s
llama-server | 10961.55.251.337 I slot print_timing: id 0 | task 2773988 | n_gen = 4308, tg = 30.03 t/s, tg_3s = 39.62 t/s
llama-server | 10961.58.340.531 I slot print_timing: id 0 | task 2773988 | n_gen = 4430, tg = 30.23 t/s, tg_3s = 39.49 t/s
llama-server | 10962.01.346.614 I slot print_timing: id 0 | task 2773988 | n_gen = 4504, tg = 30.12 t/s, tg_3s = 24.62 t/s
llama-server | 10962.04.347.078 I slot print_timing: id 0 | task 2773988 | n_gen = 4604, tg = 30.18 t/s, tg_3s = 33.33 t/s
llama-server | 10962.07.350.053 I slot print_timing: id 0 | task 2773988 | n_gen = 4681, tg = 30.10 t/s, tg_3s = 25.64 t/s
llama-server | 10962.10.369.450 I slot print_timing: id 0 | task 2773988 | n_gen = 4750, tg = 29.96 t/s, tg_3s = 22.85 t/s
llama-server | 10962.13.376.262 I slot print_timing: id 0 | task 2773988 | n_gen = 4838, tg = 29.95 t/s, tg_3s = 29.27 t/s
llama-server | 10962.16.386.054 I slot print_timing: id 0 | task 2773988 | n_gen = 4935, tg = 29.99 t/s, tg_3s = 32.23 t/s
llama-server | 10962.19.413.256 I slot print_timing: id 0 | task 2773988 | n_gen = 5008, tg = 29.88 t/s, tg_3s = 24.11 t/s
llama-server | 10962.22.423.691 I slot print_timing: id 0 | task 2773988 | n_gen = 5085, tg = 29.80 t/s, tg_3s = 25.58 t/s
llama-server | 10962.25.439.214 I slot print_timing: id 0 | task 2773988 | n_gen = 5172, tg = 29.79 t/s, tg_3s = 28.85 t/s
llama-server | 10962.28.476.308 I slot print_timing: id 0 | task 2773988 | n_gen = 5279, tg = 29.88 t/s, tg_3s = 35.23 t/s
llama-server | 10962.31.497.174 I slot print_timing: id 0 | task 2773988 | n_gen = 5372, tg = 29.90 t/s, tg_3s = 30.79 t/s
llama-server | 10962.34.519.530 I slot print_timing: id 0 | task 2773988 | n_gen = 5460, tg = 29.88 t/s, tg_3s = 29.12 t/s
llama-server | 10962.37.558.998 I slot print_timing: id 0 | task 2773988 | n_gen = 5550, tg = 29.88 t/s, tg_3s = 29.61 t/s
llama-server | 10962.40.571.842 I slot print_timing: id 0 | task 2773988 | n_gen = 5624, tg = 29.79 t/s, tg_3s = 24.56 t/s
llama-server | 10962.43.609.486 I slot print_timing: id 0 | task 2773988 | n_gen = 5729, tg = 29.87 t/s, tg_3s = 34.57 t/s
llama-server | 10962.46.636.242 I slot print_timing: id 0 | task 2773988 | n_gen = 5829, tg = 29.92 t/s, tg_3s = 33.04 t/s
llama-server | 10962.49.654.825 I slot print_timing: id 0 | task 2773988 | n_gen = 5920, tg = 29.92 t/s, tg_3s = 30.15 t/s
llama-server | 10962.52.690.278 I slot print_timing: id 0 | task 2773988 | n_gen = 6010, tg = 29.92 t/s, tg_3s = 29.65 t/s
llama-server | 10962.55.709.985 I slot print_timing: id 0 | task 2773988 | n_gen = 6084, tg = 29.84 t/s, tg_3s = 24.51 t/s
llama-server | 10962.58.733.254 I slot print_timing: id 0 | task 2773988 | n_gen = 6164, tg = 29.79 t/s, tg_3s = 26.46 t/s
llama-server | 10963.01.752.611 I slot print_timing: id 0 | task 2773988 | n_gen = 6234, tg = 29.69 t/s, tg_3s = 23.18 t/s
llama-server | 10963.04.793.318 I slot print_timing: id 0 | task 2773988 | n_gen = 6326, tg = 29.70 t/s, tg_3s = 30.26 t/s
llama-server | 10963.07.823.439 I slot print_timing: id 0 | task 2773988 | n_gen = 6408, tg = 29.67 t/s, tg_3s = 27.06 t/s
llama-server | 10963.10.866.117 I slot print_timing: id 0 | task 2773988 | n_gen = 6512, tg = 29.73 t/s, tg_3s = 34.18 t/s
llama-server | 10963.13.237.256 I slot print_timing: id 0 | task 2773988 | prompt eval time = 48831.34 ms / 46243 tokens ( 1.06 ms per token, 946.99 tokens per second)
llama-server | 10963.13.237.259 I slot print_timing: id 0 | task 2773988 | eval time = 221390.20 ms / 6614 tokens ( 33.48 ms per token, 29.87 tokens per second)
llama-server | 10963.13.237.260 I slot print_timing: id 0 | task 2773988 | total time = 270221.54 ms / 52857 tokens
llama-server | 10963.13.237.261 I slot print_timing: id 0 | task 2773988 | graphs reused = 2688674
llama-server | 10963.13.237.264 I slot print_timing: id 0 | task 2773988 | draft acceptance = 0.35712 ( 4239 accepted / 11870 generated), mean len = 2.79
llama-server | 10963.13.238.472 I slot release: id 0 | task 2773988 | stop processing: n_tokens = 52856, truncated = 0
llama-server | 10963.14.450.136 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 657536253492
llama-server | 10963.14.450.738 I slot launch_slot_: id 1 | task 2776388 | processing task, is_child = 0
llama-server | 10963.14.453.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2123.073 MiB)
llama-server | 10963.19.849.392 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.01 s / 1360.05 tokens per second
llama-server | 10963.21.667.897 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.82 s / 1274.43 tokens per second
llama-server | 10963.23.528.329 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.67 s / 1228.83 tokens per second
llama-server | 10963.25.418.042 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.55 s / 1197.18 tokens per second
llama-server | 10963.27.365.229 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.49 s / 1171.48 tokens per second
llama-server | 10963.29.330.875 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 14336, progress = 0.36, t = 12.45 s / 1151.68 tokens per second
llama-server | 10963.31.338.377 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.44 s / 1134.53 tokens per second
llama-server | 10963.33.381.344 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.48 s / 1118.56 tokens per second
llama-server | 10963.35.463.048 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.55 s / 1104.05 tokens per second
llama-server | 10963.37.595.842 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 22528, progress = 0.57, t = 20.66 s / 1090.40 tokens per second
llama-server | 10963.39.772.561 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.83 s / 1076.60 tokens per second
llama-server | 10963.41.972.764 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 26624, progress = 0.68, t = 25.03 s / 1063.76 tokens per second
llama-server | 10963.44.208.702 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.25 s / 1052.01 tokens per second
llama-server | 10963.46.477.859 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 30720, progress = 0.78, t = 29.52 s / 1040.80 tokens per second
llama-server | 10963.48.818.744 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 32768, progress = 0.83, t = 31.81 s / 1030.00 tokens per second
llama-server | 10963.51.157.992 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 34816, progress = 0.89, t = 34.18 s / 1018.64 tokens per second
llama-server | 10963.53.534.885 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 36864, progress = 0.94, t = 36.54 s / 1008.74 tokens per second
llama-server | 10963.55.835.007 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 38775, progress = 0.99, t = 38.95 s / 995.59 tokens per second
llama-server | 10963.56.540.464 I slot print_timing: id 1 | task 2776388 | prompt processing, n_tokens = 39287, progress = 1.00, t = 39.64 s / 991.11 tokens per second
llama-server | 10963.59.748.801 I slot print_timing: id 1 | task 2776388 | prompt eval time = 40433.77 ms / 39291 tokens ( 1.03 ms per token, 971.74 tokens per second)
llama-server | 10963.59.748.804 I slot print_timing: id 1 | task 2776388 | eval time = 3015.64 ms / 117 tokens ( 26.00 ms per token, 38.47 tokens per second)
llama-server | 10963.59.748.804 I slot print_timing: id 1 | task 2776388 | total time = 43449.41 ms / 39408 tokens
llama-server | 10963.59.748.805 I slot print_timing: id 1 | task 2776388 | graphs reused = 2688707
llama-server | 10963.59.748.808 I slot print_timing: id 1 | task 2776388 | draft acceptance = 0.48235 ( 82 accepted / 170 generated), mean len = 3.41
llama-server | 10963.59.749.910 I slot release: id 1 | task 2776388 | stop processing: n_tokens = 39407, truncated = 0
llama-server | 10964.00.883.419 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 657809078524
llama-server | 10964.00.884.096 I slot launch_slot_: id 0 | task 2776444 | processing task, is_child = 0
llama-server | 10964.00.885.988 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2122.276 MiB)
llama-server | 10964.07.702.418 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1278.10 tokens per second
llama-server | 10964.09.554.651 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1231.56 tokens per second
llama-server | 10964.11.437.500 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.53 s / 1200.73 tokens per second
llama-server | 10964.13.373.534 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 657855589963
llama-server | 10964.13.373.710 I slot launch_slot_: id 1 | task 2776451 | processing task, is_child = 0
llama-server | 10964.13.373.733 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.45 s / 1175.39 tokens per second
llama-server | 10964.15.338.836 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.41 s / 1155.64 tokens per second
llama-server | 10964.17.339.731 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.40 s / 1137.88 tokens per second
llama-server | 10964.19.383.558 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.43 s / 1121.85 tokens per second
llama-server | 10964.21.460.319 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.50 s / 1106.92 tokens per second
llama-server | 10964.23.576.168 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.61 s / 1093.22 tokens per second
llama-server | 10964.25.748.928 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.76 s / 1079.92 tokens per second
llama-server | 10964.27.945.488 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 26624, progress = 0.69, t = 24.96 s / 1066.83 tokens per second
llama-server | 10964.30.174.357 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 28672, progress = 0.74, t = 27.18 s / 1055.04 tokens per second
llama-server | 10964.32.438.322 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.43 s / 1043.75 tokens per second
llama-server | 10964.34.774.397 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 32768, progress = 0.85, t = 31.72 s / 1032.95 tokens per second
llama-server | 10964.37.108.361 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 34816, progress = 0.90, t = 34.08 s / 1021.46 tokens per second
llama-server | 10964.39.480.757 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 36864, progress = 0.95, t = 36.45 s / 1011.48 tokens per second
llama-server | 10964.42.036.086 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 38098, progress = 0.99, t = 39.02 s / 976.37 tokens per second
llama-server | 10964.43.646.614 I slot print_timing: id 0 | task 2776444 | prompt processing, n_tokens = 38610, progress = 1.00, t = 40.95 s / 942.93 tokens per second
llama-server | 10964.43.821.242 I slot print_timing: id 1 | task 2776451 | prompt processing, n_tokens = 1492, progress = 0.19, t = 3.81 s / 391.41 tokens per second
llama-server | 10964.46.475.548 I slot print_timing: id 1 | task 2776451 | prompt processing, n_tokens = 3536, progress = 0.46, t = 6.85 s / 516.34 tokens per second
llama-server | 10964.49.023.519 I slot print_timing: id 1 | task 2776451 | prompt processing, n_tokens = 5578, progress = 0.73, t = 9.39 s / 594.03 tokens per second
llama-server | 10964.51.120.887 I slot print_timing: id 1 | task 2776451 | prompt processing, n_tokens = 7173, progress = 0.93, t = 11.52 s / 622.53 tokens per second
llama-server | 10964.51.983.178 I slot print_timing: id 1 | task 2776451 | prompt processing, n_tokens = 7685, progress = 1.00, t = 12.45 s / 617.16 tokens per second
llama-server | 10964.54.747.581 I slot print_timing: id 0 | task 2776444 | n_gen = 105, tg = 12.56 t/s, tg_3s = 12.68 t/s
llama-server | 10964.55.286.579 I slot print_timing: id 1 | task 2776451 | n_gen = 113, tg = 37.24 t/s, tg_3s = 37.56 t/s
llama-server | 10964.57.816.914 I slot print_timing: id 0 | task 2776444 | n_gen = 211, tg = 18.50 t/s, tg_3s = 34.54 t/s
llama-server | 10964.58.353.477 I slot print_timing: id 1 | task 2776451 | n_gen = 213, tg = 34.90 t/s, tg_3s = 32.61 t/s
llama-server | 10965.00.893.830 I slot print_timing: id 0 | task 2776444 | n_gen = 313, tg = 21.62 t/s, tg_3s = 33.15 t/s
llama-server | 10965.01.437.440 I slot print_timing: id 1 | task 2776451 | n_gen = 348, tg = 37.89 t/s, tg_3s = 43.77 t/s
llama-server | 10965.03.972.460 I slot print_timing: id 0 | task 2776444 | n_gen = 409, tg = 23.30 t/s, tg_3s = 31.18 t/s
llama-server | 10965.04.512.170 I slot print_timing: id 1 | task 2776451 | n_gen = 452, tg = 36.87 t/s, tg_3s = 33.82 t/s
llama-server | 10965.07.057.173 I slot print_timing: id 0 | task 2776444 | n_gen = 516, tg = 25.01 t/s, tg_3s = 34.69 t/s
llama-server | 10965.07.599.909 I slot print_timing: id 1 | task 2776451 | n_gen = 574, tg = 37.40 t/s, tg_3s = 39.51 t/s
llama-server | 10965.10.126.675 I slot print_timing: id 0 | task 2776444 | n_gen = 629, tg = 26.54 t/s, tg_3s = 36.81 t/s
llama-server | 10965.10.670.541 I slot print_timing: id 1 | task 2776451 | n_gen = 675, tg = 36.65 t/s, tg_3s = 32.89 t/s
llama-server | 10965.13.215.238 I slot print_timing: id 0 | task 2776444 | n_gen = 724, tg = 27.03 t/s, tg_3s = 30.76 t/s
llama-server | 10965.13.757.152 I slot print_timing: id 1 | task 2776451 | n_gen = 790, tg = 36.73 t/s, tg_3s = 37.26 t/s
llama-server | 10965.16.216.288 I slot print_timing: id 0 | task 2776444 | n_gen = 827, tg = 27.76 t/s, tg_3s = 34.32 t/s
llama-server | 10965.16.761.800 I slot print_timing: id 1 | task 2776451 | n_gen = 921, tg = 37.58 t/s, tg_3s = 43.60 t/s
llama-server | 10965.19.228.602 I slot print_timing: id 0 | task 2776444 | n_gen = 939, tg = 28.63 t/s, tg_3s = 37.18 t/s
llama-server | 10965.19.776.155 I slot print_timing: id 1 | task 2776451 | n_gen = 1044, tg = 37.93 t/s, tg_3s = 40.80 t/s
llama-server | 10965.22.254.262 I slot print_timing: id 0 | task 2776444 | n_gen = 1080, tg = 30.15 t/s, tg_3s = 46.60 t/s
llama-server | 10965.22.799.460 I slot print_timing: id 1 | task 2776451 | n_gen = 1154, tg = 37.78 t/s, tg_3s = 36.38 t/s
llama-server | 10965.25.272.837 I slot print_timing: id 0 | task 2776444 | n_gen = 1192, tg = 30.69 t/s, tg_3s = 37.10 t/s
llama-server | 10965.25.818.295 I slot print_timing: id 1 | task 2776451 | n_gen = 1253, tg = 37.33 t/s, tg_3s = 32.79 t/s
llama-server | 10965.28.301.962 I slot print_timing: id 0 | task 2776444 | n_gen = 1314, tg = 31.38 t/s, tg_3s = 40.28 t/s
llama-server | 10965.28.850.871 I slot print_timing: id 1 | task 2776451 | n_gen = 1386, tg = 37.87 t/s, tg_3s = 43.86 t/s
llama-server | 10965.31.331.690 I slot print_timing: id 0 | task 2776444 | n_gen = 1425, tg = 31.74 t/s, tg_3s = 36.64 t/s
llama-server | 10965.31.880.824 I slot print_timing: id 1 | task 2776451 | n_gen = 1474, tg = 37.20 t/s, tg_3s = 29.04 t/s
llama-server | 10965.34.345.186 I slot print_timing: id 0 | task 2776444 | n_gen = 1557, tg = 32.50 t/s, tg_3s = 43.80 t/s
llama-server | 10965.34.918.244 I slot print_timing: id 1 | task 2776451 | n_gen = 1545, tg = 36.21 t/s, tg_3s = 23.38 t/s
llama-server | 10965.37.378.756 I slot print_timing: id 0 | task 2776444 | n_gen = 1651, tg = 32.41 t/s, tg_3s = 30.99 t/s
llama-server | 10965.37.926.599 I slot print_timing: id 1 | task 2776451 | n_gen = 1631, tg = 35.71 t/s, tg_3s = 28.59 t/s
llama-server | 10965.40.416.208 I slot print_timing: id 0 | task 2776444 | n_gen = 1778, tg = 32.94 t/s, tg_3s = 41.81 t/s
llama-server | 10965.40.969.492 I slot print_timing: id 1 | task 2776451 | n_gen = 1720, tg = 35.30 t/s, tg_3s = 29.25 t/s
llama-server | 10965.43.456.746 I slot print_timing: id 0 | task 2776444 | n_gen = 1871, tg = 32.81 t/s, tg_3s = 30.59 t/s
llama-server | 10965.44.007.210 I slot print_timing: id 1 | task 2776451 | n_gen = 1815, tg = 35.07 t/s, tg_3s = 31.27 t/s
llama-server | 10965.46.478.347 I slot print_timing: id 0 | task 2776444 | n_gen = 1981, tg = 32.99 t/s, tg_3s = 36.40 t/s
llama-server | 10965.47.052.399 I slot print_timing: id 1 | task 2776451 | n_gen = 1892, tg = 34.52 t/s, tg_3s = 25.29 t/s
llama-server | 10965.49.526.876 I slot print_timing: id 0 | task 2776444 | n_gen = 2070, tg = 32.81 t/s, tg_3s = 29.19 t/s
llama-server | 10965.50.077.448 I slot print_timing: id 1 | task 2776451 | n_gen = 1996, tg = 34.52 t/s, tg_3s = 34.38 t/s
llama-server | 10965.52.580.466 I slot print_timing: id 0 | task 2776444 | n_gen = 2173, tg = 32.85 t/s, tg_3s = 33.73 t/s
llama-server | 10965.53.140.032 I slot print_timing: id 1 | task 2776451 | n_gen = 2100, tg = 34.49 t/s, tg_3s = 33.96 t/s
llama-server | 10965.55.643.337 I slot print_timing: id 0 | task 2776444 | n_gen = 2293, tg = 33.13 t/s, tg_3s = 39.18 t/s
llama-server | 10965.56.196.835 I slot print_timing: id 1 | task 2776451 | n_gen = 2209, tg = 34.54 t/s, tg_3s = 35.66 t/s
llama-server | 10965.58.700.833 I slot print_timing: id 0 | task 2776444 | n_gen = 2387, tg = 33.03 t/s, tg_3s = 30.74 t/s
llama-server | 10965.59.252.763 I slot print_timing: id 1 | task 2776451 | n_gen = 2302, tg = 34.36 t/s, tg_3s = 30.43 t/s
llama-server | 10966.01.737.991 I slot print_timing: id 0 | task 2776444 | n_gen = 2487, tg = 33.03 t/s, tg_3s = 32.93 t/s
llama-server | 10966.02.313.776 I slot print_timing: id 1 | task 2776451 | n_gen = 2401, tg = 34.27 t/s, tg_3s = 32.34 t/s
llama-server | 10966.04.816.495 I slot print_timing: id 0 | task 2776444 | n_gen = 2614, tg = 33.35 t/s, tg_3s = 41.25 t/s
llama-server | 10966.05.391.756 I slot print_timing: id 1 | task 2776451 | n_gen = 2530, tg = 34.59 t/s, tg_3s = 41.91 t/s
llama-server | 10966.07.891.347 I slot print_timing: id 0 | task 2776444 | n_gen = 2729, tg = 33.50 t/s, tg_3s = 37.40 t/s
llama-server | 10966.08.449.298 I slot print_timing: id 1 | task 2776451 | n_gen = 2660, tg = 34.91 t/s, tg_3s = 42.52 t/s
llama-server | 10966.10.973.110 I slot print_timing: id 0 | task 2776444 | n_gen = 2838, tg = 33.57 t/s, tg_3s = 35.37 t/s
llama-server | 10966.11.531.131 I slot print_timing: id 1 | task 2776451 | n_gen = 2804, tg = 35.37 t/s, tg_3s = 46.73 t/s
llama-server | 10966.14.064.863 I slot print_timing: id 0 | task 2776444 | n_gen = 2948, tg = 33.64 t/s, tg_3s = 35.58 t/s
llama-server | 10966.14.619.789 I slot print_timing: id 1 | task 2776451 | n_gen = 2920, tg = 35.45 t/s, tg_3s = 37.56 t/s
llama-server | 10966.17.148.611 I slot print_timing: id 0 | task 2776444 | n_gen = 3051, tg = 33.63 t/s, tg_3s = 33.40 t/s
llama-server | 10966.17.709.810 I slot print_timing: id 1 | task 2776451 | n_gen = 3027, tg = 35.42 t/s, tg_3s = 34.63 t/s
llama-server | 10966.20.238.137 I slot print_timing: id 0 | task 2776444 | n_gen = 3186, tg = 33.96 t/s, tg_3s = 43.70 t/s
llama-server | 10966.20.794.492 I slot print_timing: id 1 | task 2776451 | n_gen = 3113, tg = 35.16 t/s, tg_3s = 27.88 t/s
llama-server | 10966.23.320.217 I slot print_timing: id 0 | task 2776444 | n_gen = 3283, tg = 33.89 t/s, tg_3s = 31.47 t/s
llama-server | 10966.23.878.955 I slot print_timing: id 1 | task 2776451 | n_gen = 3204, tg = 34.97 t/s, tg_3s = 29.50 t/s
llama-server | 10966.26.396.109 I slot print_timing: id 0 | task 2776444 | n_gen = 3383, tg = 33.84 t/s, tg_3s = 32.51 t/s
llama-server | 10966.26.883.435 I slot print_timing: id 1 | task 2776451 | n_gen = 3295, tg = 34.82 t/s, tg_3s = 30.29 t/s
llama-server | 10966.29.406.326 I slot print_timing: id 0 | task 2776444 | n_gen = 3500, tg = 33.99 t/s, tg_3s = 38.87 t/s
llama-server | 10966.29.966.819 I slot print_timing: id 1 | task 2776451 | n_gen = 3407, tg = 34.87 t/s, tg_3s = 36.32 t/s
llama-server | 10966.32.414.908 I slot print_timing: id 0 | task 2776444 | n_gen = 3601, tg = 33.98 t/s, tg_3s = 33.57 t/s
llama-server | 10966.32.975.285 I slot print_timing: id 1 | task 2776451 | n_gen = 3507, tg = 34.82 t/s, tg_3s = 33.24 t/s
llama-server | 10966.35.428.973 I slot print_timing: id 0 | task 2776444 | n_gen = 3698, tg = 33.93 t/s, tg_3s = 32.18 t/s
llama-server | 10966.35.989.493 I slot print_timing: id 1 | task 2776451 | n_gen = 3595, tg = 34.65 t/s, tg_3s = 29.20 t/s
llama-server | 10966.38.446.618 I slot print_timing: id 0 | task 2776444 | n_gen = 3808, tg = 34.00 t/s, tg_3s = 36.45 t/s
llama-server | 10966.39.011.671 I slot print_timing: id 1 | task 2776451 | n_gen = 3699, tg = 34.65 t/s, tg_3s = 34.41 t/s
llama-server | 10966.41.447.843 I slot print_timing: id 0 | task 2776444 | n_gen = 3942, tg = 34.27 t/s, tg_3s = 44.65 t/s
llama-server | 10966.42.029.664 I slot print_timing: id 1 | task 2776451 | n_gen = 3770, tg = 34.34 t/s, tg_3s = 23.53 t/s
llama-server | 10966.44.473.312 I slot print_timing: id 0 | task 2776444 | n_gen = 4076, tg = 34.53 t/s, tg_3s = 44.29 t/s
llama-server | 10966.45.042.799 I slot print_timing: id 1 | task 2776451 | n_gen = 3871, tg = 34.32 t/s, tg_3s = 33.52 t/s
llama-server | 10966.47.506.941 I slot print_timing: id 0 | task 2776444 | n_gen = 4185, tg = 34.57 t/s, tg_3s = 35.93 t/s
llama-server | 10966.48.069.732 I slot print_timing: id 1 | task 2776451 | n_gen = 3977, tg = 34.34 t/s, tg_3s = 35.02 t/s
llama-server | 10966.50.539.411 I slot print_timing: id 0 | task 2776444 | n_gen = 4285, tg = 34.53 t/s, tg_3s = 32.98 t/s
llama-server | 10966.51.103.983 I slot print_timing: id 1 | task 2776451 | n_gen = 4098, tg = 34.48 t/s, tg_3s = 39.88 t/s
llama-server | 10966.53.577.450 I slot print_timing: id 0 | task 2776444 | n_gen = 4386, tg = 34.50 t/s, tg_3s = 33.25 t/s
llama-server | 10966.54.146.469 I slot print_timing: id 1 | task 2776451 | n_gen = 4220, tg = 34.62 t/s, tg_3s = 40.10 t/s
llama-server | 10966.56.623.461 I slot print_timing: id 0 | task 2776444 | n_gen = 4487, tg = 34.47 t/s, tg_3s = 33.16 t/s
llama-server | 10966.57.190.612 I slot print_timing: id 1 | task 2776451 | n_gen = 4328, tg = 34.64 t/s, tg_3s = 35.48 t/s
llama-server | 10966.59.641.225 I slot print_timing: id 0 | task 2776444 | n_gen = 4576, tg = 34.35 t/s, tg_3s = 29.49 t/s
llama-server | 10967.00.227.659 I slot print_timing: id 1 | task 2776451 | n_gen = 4420, tg = 34.54 t/s, tg_3s = 30.29 t/s
llama-server | 10967.02.689.386 I slot print_timing: id 0 | task 2776444 | n_gen = 4682, tg = 34.36 t/s, tg_3s = 34.78 t/s
llama-server | 10967.03.258.419 I slot print_timing: id 1 | task 2776451 | n_gen = 4529, tg = 34.57 t/s, tg_3s = 35.96 t/s
llama-server | 10967.05.734.479 I slot print_timing: id 0 | task 2776444 | n_gen = 4745, tg = 34.06 t/s, tg_3s = 20.69 t/s
llama-server | 10967.06.306.214 I slot print_timing: id 1 | task 2776451 | n_gen = 4642, tg = 34.63 t/s, tg_3s = 37.08 t/s
llama-server | 10967.08.783.210 I slot print_timing: id 0 | task 2776444 | n_gen = 4844, tg = 34.03 t/s, tg_3s = 32.47 t/s
llama-server | 10967.09.353.096 I slot print_timing: id 1 | task 2776451 | n_gen = 4758, tg = 34.70 t/s, tg_3s = 38.07 t/s
llama-server | 10967.11.836.403 I slot print_timing: id 0 | task 2776444 | n_gen = 4942, tg = 33.99 t/s, tg_3s = 32.10 t/s
llama-server | 10967.12.405.478 I slot print_timing: id 1 | task 2776451 | n_gen = 4870, tg = 34.75 t/s, tg_3s = 36.69 t/s
llama-server | 10967.14.867.293 I slot print_timing: id 0 | task 2776444 | n_gen = 5043, tg = 33.98 t/s, tg_3s = 33.32 t/s
llama-server | 10967.15.460.599 I slot print_timing: id 1 | task 2776451 | n_gen = 4974, tg = 34.73 t/s, tg_3s = 34.04 t/s
llama-server | 10967.17.945.568 I slot print_timing: id 0 | task 2776444 | n_gen = 5176, tg = 34.16 t/s, tg_3s = 43.21 t/s
llama-server | 10967.18.515.740 I slot print_timing: id 1 | task 2776451 | n_gen = 5076, tg = 34.70 t/s, tg_3s = 33.39 t/s
llama-server | 10967.19.296.081 I slot print_timing: id 0 | task 2776444 | prompt eval time = 44118.71 ms / 38614 tokens ( 1.14 ms per token, 875.23 tokens per second)
llama-server | 10967.19.296.086 I slot print_timing: id 0 | task 2776444 | eval time = 152831.20 ms / 5205 tokens ( 29.37 ms per token, 34.05 tokens per second)
llama-server | 10967.19.296.087 I slot print_timing: id 0 | task 2776444 | total time = 196949.91 ms / 43819 tokens
llama-server | 10967.19.296.088 I slot print_timing: id 0 | task 2776444 | graphs reused = 2690246
llama-server | 10967.19.296.091 I slot print_timing: id 0 | task 2776444 | draft acceptance = 0.45666 ( 3619 accepted / 7925 generated), mean len = 3.28
llama-server | 10967.19.297.292 I slot release: id 0 | task 2776444 | stop processing: n_tokens = 43818, truncated = 0
llama-server | 10967.20.770.650 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658055137344
llama-server | 10967.24.052.014 I slot launch_slot_: id 0 | task 2778067 | processing task, is_child = 0
llama-server | 10967.26.920.806 I slot print_timing: id 1 | task 2776451 | n_gen = 5148, tg = 33.28 t/s, tg_3s = 8.57 t/s
llama-server | 10967.29.739.649 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 4084, progress = 0.11, t = 5.53 s / 738.99 tokens per second
llama-server | 10967.32.576.633 I slot print_timing: id 1 | task 2776451 | n_gen = 5153, tg = 32.14 t/s, tg_3s = 0.88 t/s
llama-server | 10967.32.585.438 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 6126, progress = 0.16, t = 8.37 s / 731.61 tokens per second
llama-server | 10967.35.399.436 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 8168, progress = 0.21, t = 11.19 s / 730.05 tokens per second
llama-server | 10967.38.206.550 I slot print_timing: id 1 | task 2776451 | n_gen = 5161, tg = 31.10 t/s, tg_3s = 1.42 t/s
llama-server | 10967.38.215.801 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 10210, progress = 0.26, t = 14.00 s / 729.16 tokens per second
llama-server | 10967.41.031.503 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 12252, progress = 0.32, t = 16.82 s / 728.44 tokens per second
llama-server | 10967.43.839.617 I slot print_timing: id 1 | task 2776451 | n_gen = 5169, tg = 30.12 t/s, tg_3s = 1.42 t/s
llama-server | 10967.43.848.496 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 14294, progress = 0.37, t = 19.64 s / 727.94 tokens per second
llama-server | 10967.46.664.670 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 16336, progress = 0.42, t = 22.45 s / 727.60 tokens per second
llama-server | 10967.49.472.095 I slot print_timing: id 1 | task 2776451 | n_gen = 5178, tg = 29.22 t/s, tg_3s = 1.60 t/s
llama-server | 10967.49.480.913 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 18378, progress = 0.47, t = 25.27 s / 727.34 tokens per second
llama-server | 10967.52.297.517 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 20420, progress = 0.53, t = 28.09 s / 727.06 tokens per second
llama-server | 10967.55.108.043 I slot print_timing: id 1 | task 2776451 | n_gen = 5183, tg = 28.34 t/s, tg_3s = 0.89 t/s
llama-server | 10967.55.116.570 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 22462, progress = 0.58, t = 30.90 s / 726.81 tokens per second
llama-server | 10967.57.944.165 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 24504, progress = 0.63, t = 33.72 s / 726.60 tokens per second
llama-server | 10968.00.752.350 I slot print_timing: id 1 | task 2776451 | n_gen = 5186, tg = 27.51 t/s, tg_3s = 0.53 t/s
llama-server | 10968.00.761.190 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 26546, progress = 0.68, t = 36.55 s / 726.28 tokens per second
llama-server | 10968.03.579.550 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 28588, progress = 0.74, t = 39.37 s / 726.21 tokens per second
llama-server | 10968.06.390.473 I slot print_timing: id 1 | task 2776451 | n_gen = 5191, tg = 26.74 t/s, tg_3s = 0.89 t/s
llama-server | 10968.06.399.349 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 30630, progress = 0.79, t = 42.19 s / 726.04 tokens per second
llama-server | 10968.09.217.699 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 32672, progress = 0.84, t = 45.01 s / 725.96 tokens per second
llama-server | 10968.12.027.900 I slot print_timing: id 1 | task 2776451 | n_gen = 5197, tg = 26.01 t/s, tg_3s = 1.06 t/s
llama-server | 10968.12.036.607 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 34714, progress = 0.89, t = 47.83 s / 725.85 tokens per second
llama-server | 10968.14.853.890 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 36756, progress = 0.95, t = 50.64 s / 725.80 tokens per second
llama-server | 10968.17.149.972 I slot print_timing: id 1 | task 2776451 | n_gen = 5203, tg = 25.39 t/s, tg_3s = 1.17 t/s
llama-server | 10968.17.158.639 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 38357, progress = 0.99, t = 52.97 s / 724.07 tokens per second
llama-server | 10968.18.264.092 I slot print_timing: id 0 | task 2778067 | prompt processing, n_tokens = 38869, progress = 1.00, t = 54.15 s / 717.80 tokens per second
llama-server | 10968.20.201.778 I slot print_timing: id 1 | task 2776451 | n_gen = 5264, tg = 25.31 t/s, tg_3s = 19.99 t/s
llama-server | 10968.22.282.812 I slot print_timing: id 0 | task 2778067 | n_gen = 100, tg = 27.91 t/s, tg_3s = 28.19 t/s
llama-server | 10968.23.235.096 I slot print_timing: id 1 | task 2776451 | n_gen = 5349, tg = 25.35 t/s, tg_3s = 28.02 t/s
llama-server | 10968.23.899.457 I slot print_timing: id 0 | task 2778067 | prompt eval time = 54672.17 ms / 38873 tokens ( 1.41 ms per token, 711.02 tokens per second)
llama-server | 10968.23.899.460 I slot print_timing: id 0 | task 2778067 | eval time = 5163.83 ms / 173 tokens ( 30.02 ms per token, 33.31 tokens per second)
llama-server | 10968.23.899.461 I slot print_timing: id 0 | task 2778067 | total time = 59836.00 ms / 39046 tokens
llama-server | 10968.23.899.462 I slot print_timing: id 0 | task 2778067 | graphs reused = 2690351
llama-server | 10968.23.899.467 I slot print_timing: id 0 | task 2778067 | draft acceptance = 0.44074 ( 119 accepted / 270 generated), mean len = 3.20
llama-server | 10968.23.900.693 I slot release: id 0 | task 2778067 | stop processing: n_tokens = 39046, truncated = 0
llama-server | 10968.25.082.883 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658119740745
llama-server | 10968.25.084.838 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1883.947 MiB)
llama-server | 10968.27.136.720 I slot launch_slot_: id 0 | task 2778155 | processing task, is_child = 0
llama-server | 10968.29.992.018 I slot print_timing: id 1 | task 2776451 | n_gen = 5410, tg = 24.84 t/s, tg_3s = 9.03 t/s
llama-server | 10968.32.808.793 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.51 s / 740.99 tokens per second
llama-server | 10968.35.629.107 I slot print_timing: id 1 | task 2776451 | n_gen = 5413, tg = 24.23 t/s, tg_3s = 0.53 t/s
llama-server | 10968.35.637.920 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 6126, progress = 0.16, t = 8.34 s / 734.33 tokens per second
llama-server | 10968.38.445.192 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 8168, progress = 0.21, t = 11.15 s / 732.60 tokens per second
llama-server | 10968.41.246.765 I slot print_timing: id 1 | task 2776451 | n_gen = 5416, tg = 23.65 t/s, tg_3s = 0.53 t/s
llama-server | 10968.41.255.344 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 10210, progress = 0.26, t = 13.96 s / 731.42 tokens per second
llama-server | 10968.44.065.479 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 12252, progress = 0.31, t = 16.77 s / 730.61 tokens per second
llama-server | 10968.46.871.102 I slot print_timing: id 1 | task 2776451 | n_gen = 5422, tg = 23.11 t/s, tg_3s = 1.07 t/s
llama-server | 10968.46.879.924 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 14294, progress = 0.37, t = 19.58 s / 729.93 tokens per second
llama-server | 10968.49.694.416 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 16336, progress = 0.42, t = 22.40 s / 729.36 tokens per second
llama-server | 10968.52.499.649 I slot print_timing: id 1 | task 2776451 | n_gen = 5427, tg = 22.59 t/s, tg_3s = 0.89 t/s
llama-server | 10968.52.508.479 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 18378, progress = 0.47, t = 25.21 s / 729.03 tokens per second
llama-server | 10968.55.326.028 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 20420, progress = 0.52, t = 28.03 s / 728.54 tokens per second
llama-server | 10968.58.134.419 I slot print_timing: id 1 | task 2776451 | n_gen = 5434, tg = 22.10 t/s, tg_3s = 1.24 t/s
llama-server | 10968.58.143.306 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 22462, progress = 0.57, t = 30.85 s / 728.19 tokens per second
llama-server | 10969.00.960.299 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 24504, progress = 0.63, t = 33.66 s / 727.91 tokens per second
llama-server | 10969.03.766.689 I slot print_timing: id 1 | task 2776451 | n_gen = 5438, tg = 21.62 t/s, tg_3s = 0.71 t/s
llama-server | 10969.03.775.995 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 26546, progress = 0.68, t = 36.48 s / 727.70 tokens per second
llama-server | 10969.06.592.280 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 28588, progress = 0.73, t = 39.30 s / 727.50 tokens per second
llama-server | 10969.09.399.822 I slot print_timing: id 1 | task 2776451 | n_gen = 5443, tg = 21.17 t/s, tg_3s = 0.89 t/s
llama-server | 10969.09.408.510 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 30630, progress = 0.78, t = 42.11 s / 727.33 tokens per second
llama-server | 10969.12.226.862 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 32672, progress = 0.84, t = 44.93 s / 727.19 tokens per second
llama-server | 10969.15.036.778 I slot print_timing: id 1 | task 2776451 | n_gen = 5448, tg = 20.73 t/s, tg_3s = 0.89 t/s
llama-server | 10969.15.045.922 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 34714, progress = 0.89, t = 47.75 s / 727.01 tokens per second
llama-server | 10969.17.862.123 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 36756, progress = 0.94, t = 50.57 s / 726.87 tokens per second
llama-server | 10969.20.427.912 I slot print_timing: id 1 | task 2776451 | n_gen = 5452, tg = 20.33 t/s, tg_3s = 0.74 t/s
llama-server | 10969.20.436.342 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 38574, progress = 0.99, t = 53.15 s / 725.71 tokens per second
llama-server | 10969.21.548.968 I slot print_timing: id 0 | task 2778155 | prompt processing, n_tokens = 39086, progress = 1.00, t = 54.35 s / 719.16 tokens per second
llama-server | 10969.23.464.587 I slot print_timing: id 1 | task 2776451 | n_gen = 5492, tg = 20.25 t/s, tg_3s = 13.17 t/s
llama-server | 10969.25.077.876 I slot print_timing: id 0 | task 2778155 | n_gen = 119, tg = 38.33 t/s, tg_3s = 38.65 t/s
llama-server | 10969.26.506.463 I slot print_timing: id 1 | task 2776451 | n_gen = 5594, tg = 20.40 t/s, tg_3s = 33.53 t/s
llama-server | 10969.28.117.554 I slot print_timing: id 0 | task 2778155 | n_gen = 248, tg = 40.37 t/s, tg_3s = 42.44 t/s
llama-server | 10969.29.536.389 I slot print_timing: id 1 | task 2776451 | n_gen = 5673, tg = 20.46 t/s, tg_3s = 26.07 t/s
llama-server | 10969.31.168.996 I slot print_timing: id 0 | task 2778155 | n_gen = 326, tg = 35.44 t/s, tg_3s = 25.56 t/s
llama-server | 10969.32.599.273 I slot print_timing: id 1 | task 2776451 | n_gen = 5785, tg = 20.63 t/s, tg_3s = 36.57 t/s
llama-server | 10969.34.211.856 I slot print_timing: id 0 | task 2778155 | n_gen = 421, tg = 34.39 t/s, tg_3s = 31.22 t/s
llama-server | 10969.35.634.218 I slot print_timing: id 1 | task 2776451 | n_gen = 5867, tg = 20.70 t/s, tg_3s = 27.02 t/s
llama-server | 10969.37.246.845 I slot print_timing: id 0 | task 2778155 | n_gen = 530, tg = 34.69 t/s, tg_3s = 35.91 t/s
llama-server | 10969.38.672.716 I slot print_timing: id 1 | task 2776451 | n_gen = 5943, tg = 20.75 t/s, tg_3s = 25.01 t/s
llama-server | 10969.40.290.109 I slot print_timing: id 0 | task 2778155 | n_gen = 658, tg = 35.92 t/s, tg_3s = 42.06 t/s
llama-server | 10969.41.713.973 I slot print_timing: id 1 | task 2776451 | n_gen = 6028, tg = 20.82 t/s, tg_3s = 27.95 t/s
llama-server | 10969.43.335.172 I slot print_timing: id 0 | task 2778155 | n_gen = 758, tg = 35.48 t/s, tg_3s = 32.84 t/s
llama-server | 10969.44.764.220 I slot print_timing: id 1 | task 2776451 | n_gen = 6110, tg = 20.89 t/s, tg_3s = 26.88 t/s
llama-server | 10969.46.377.558 I slot print_timing: id 0 | task 2778155 | n_gen = 871, tg = 35.69 t/s, tg_3s = 37.14 t/s
llama-server | 10969.46.758.164 I slot print_timing: id 0 | task 2778155 | prompt eval time = 54850.76 ms / 39090 tokens ( 1.40 ms per token, 712.66 tokens per second)
llama-server | 10969.46.758.167 I slot print_timing: id 0 | task 2778155 | eval time = 24759.15 ms / 890 tokens ( 27.85 ms per token, 35.91 tokens per second)
llama-server | 10969.46.758.168 I slot print_timing: id 0 | task 2778155 | total time = 79609.91 ms / 39980 tokens
llama-server | 10969.46.758.168 I slot print_timing: id 0 | task 2778155 | graphs reused = 2690659
llama-server | 10969.46.758.171 I slot print_timing: id 0 | task 2778155 | draft acceptance = 0.48385 ( 629 accepted / 1300 generated), mean len = 3.42
llama-server | 10969.46.759.397 I slot release: id 0 | task 2778155 | stop processing: n_tokens = 39979, truncated = 0
llama-server | 10969.47.844.411 I slot print_timing: id 1 | task 2776451 | n_gen = 6200, tg = 20.97 t/s, tg_3s = 29.22 t/s
llama-server | 10969.48.229.996 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658202599449
llama-server | 10969.48.231.978 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2326.424 MiB)
llama-server | 10969.50.613.560 I slot launch_slot_: id 0 | task 2778452 | processing task, is_child = 0
llama-server | 10969.53.481.584 I slot print_timing: id 1 | task 2776451 | n_gen = 6206, tg = 20.60 t/s, tg_3s = 1.06 t/s
llama-server | 10969.56.303.730 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.53 s / 738.66 tokens per second
llama-server | 10969.59.135.235 I slot print_timing: id 1 | task 2776451 | n_gen = 6214, tg = 20.25 t/s, tg_3s = 1.42 t/s
llama-server | 10969.59.143.991 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 6126, progress = 0.16, t = 8.37 s / 732.15 tokens per second
llama-server | 10970.01.957.246 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 8168, progress = 0.21, t = 11.18 s / 730.42 tokens per second
llama-server | 10970.04.765.152 I slot print_timing: id 1 | task 2776451 | n_gen = 6224, tg = 19.91 t/s, tg_3s = 1.78 t/s
llama-server | 10970.04.773.990 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 10210, progress = 0.26, t = 14.00 s / 729.28 tokens per second
llama-server | 10970.07.590.211 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 12252, progress = 0.31, t = 16.82 s / 728.62 tokens per second
llama-server | 10970.10.395.047 I slot print_timing: id 1 | task 2776451 | n_gen = 6231, tg = 19.58 t/s, tg_3s = 1.24 t/s
llama-server | 10970.10.403.961 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 14294, progress = 0.37, t = 19.63 s / 728.15 tokens per second
llama-server | 10970.13.223.061 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 16336, progress = 0.42, t = 22.44 s / 727.84 tokens per second
llama-server | 10970.16.027.844 I slot print_timing: id 1 | task 2776451 | n_gen = 6234, tg = 19.25 t/s, tg_3s = 0.53 t/s
llama-server | 10970.16.036.523 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 18378, progress = 0.47, t = 25.26 s / 727.47 tokens per second
llama-server | 10970.18.864.275 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 20420, progress = 0.52, t = 28.08 s / 727.22 tokens per second
llama-server | 10970.21.669.412 I slot print_timing: id 1 | task 2776451 | n_gen = 6241, tg = 18.94 t/s, tg_3s = 1.24 t/s
llama-server | 10970.21.677.922 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 22462, progress = 0.57, t = 30.91 s / 726.80 tokens per second
llama-server | 10970.24.492.754 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 24504, progress = 0.63, t = 33.72 s / 726.71 tokens per second
llama-server | 10970.27.299.494 I slot print_timing: id 1 | task 2776451 | n_gen = 6252, tg = 18.66 t/s, tg_3s = 1.95 t/s
llama-server | 10970.27.308.280 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 26546, progress = 0.68, t = 36.53 s / 726.59 tokens per second
llama-server | 10970.30.124.576 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 28588, progress = 0.73, t = 39.35 s / 726.49 tokens per second
llama-server | 10970.32.932.622 I slot print_timing: id 1 | task 2776451 | n_gen = 6261, tg = 18.38 t/s, tg_3s = 1.60 t/s
llama-server | 10970.32.941.397 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 30630, progress = 0.78, t = 42.17 s / 726.38 tokens per second
llama-server | 10970.35.758.860 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 32672, progress = 0.84, t = 44.99 s / 726.29 tokens per second
llama-server | 10970.38.566.710 I slot print_timing: id 1 | task 2776451 | n_gen = 6267, tg = 18.09 t/s, tg_3s = 1.06 t/s
llama-server | 10970.38.575.548 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 34714, progress = 0.89, t = 47.80 s / 726.19 tokens per second
llama-server | 10970.41.390.237 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 36756, progress = 0.94, t = 50.62 s / 726.15 tokens per second
llama-server | 10970.43.984.106 I slot print_timing: id 1 | task 2776451 | n_gen = 6272, tg = 17.83 t/s, tg_3s = 0.92 t/s
llama-server | 10970.43.992.579 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 38591, progress = 0.99, t = 53.23 s / 724.96 tokens per second
llama-server | 10970.45.076.899 I slot print_timing: id 0 | task 2778452 | prompt processing, n_tokens = 39103, progress = 1.00, t = 54.40 s / 718.79 tokens per second
llama-server | 10970.47.013.705 I slot print_timing: id 1 | task 2776451 | n_gen = 6327, tg = 17.83 t/s, tg_3s = 18.15 t/s
llama-server | 10970.49.005.707 I slot print_timing: id 0 | task 2778452 | n_gen = 100, tg = 28.65 t/s, tg_3s = 28.94 t/s
llama-server | 10970.49.767.043 I slot print_timing: id 0 | task 2778452 | prompt eval time = 54925.10 ms / 39107 tokens ( 1.40 ms per token, 712.01 tokens per second)
llama-server | 10970.49.767.047 I slot print_timing: id 0 | task 2778452 | eval time = 4216.73 ms / 136 tokens ( 31.24 ms per token, 32.02 tokens per second)
llama-server | 10970.49.767.047 I slot print_timing: id 0 | task 2778452 | total time = 59141.83 ms / 39243 tokens
llama-server | 10970.49.767.048 I slot print_timing: id 0 | task 2778452 | graphs reused = 2690754
llama-server | 10970.49.767.051 I slot print_timing: id 0 | task 2778452 | draft acceptance = 0.41364 ( 91 accepted / 220 generated), mean len = 3.07
llama-server | 10970.49.768.293 I slot release: id 0 | task 2778452 | stop processing: n_tokens = 39242, truncated = 0
llama-server | 10970.50.079.956 I slot print_timing: id 1 | task 2776451 | n_gen = 6432, tg = 17.97 t/s, tg_3s = 34.24 t/s
llama-server | 10970.50.845.380 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658265608346
llama-server | 10970.50.847.301 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1879.259 MiB)
llama-server | 10970.53.451.262 I slot launch_slot_: id 0 | task 2778529 | processing task, is_child = 0
llama-server | 10970.56.299.538 I slot print_timing: id 1 | task 2776451 | n_gen = 6447, tg = 17.71 t/s, tg_3s = 2.41 t/s
llama-server | 10970.59.114.733 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 4084, progress = 0.11, t = 5.50 s / 742.33 tokens per second
llama-server | 10971.01.935.229 I slot print_timing: id 1 | task 2776451 | n_gen = 6458, tg = 17.47 t/s, tg_3s = 1.95 t/s
llama-server | 10971.01.943.999 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 6126, progress = 0.16, t = 8.33 s / 735.22 tokens per second
llama-server | 10971.04.748.696 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 8168, progress = 0.21, t = 11.14 s / 733.34 tokens per second
llama-server | 10971.07.549.442 I slot print_timing: id 1 | task 2776451 | n_gen = 6465, tg = 17.22 t/s, tg_3s = 1.25 t/s
llama-server | 10971.07.558.148 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 10210, progress = 0.26, t = 13.95 s / 732.12 tokens per second
llama-server | 10971.10.366.619 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 12252, progress = 0.32, t = 16.76 s / 731.24 tokens per second
llama-server | 10971.13.167.361 I slot print_timing: id 1 | task 2776451 | n_gen = 6471, tg = 16.99 t/s, tg_3s = 1.07 t/s
llama-server | 10971.13.176.582 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 14294, progress = 0.37, t = 19.56 s / 730.61 tokens per second
llama-server | 10971.15.991.485 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 16336, progress = 0.42, t = 22.38 s / 730.06 tokens per second
llama-server | 10971.18.794.023 I slot print_timing: id 1 | task 2776451 | n_gen = 6476, tg = 16.75 t/s, tg_3s = 0.89 t/s
llama-server | 10971.18.802.848 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 18378, progress = 0.47, t = 25.19 s / 729.53 tokens per second
llama-server | 10971.21.614.572 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 20420, progress = 0.53, t = 28.00 s / 729.17 tokens per second
llama-server | 10971.24.419.199 I slot print_timing: id 1 | task 2776451 | n_gen = 6482, tg = 16.53 t/s, tg_3s = 1.07 t/s
llama-server | 10971.24.428.067 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 22462, progress = 0.58, t = 30.82 s / 728.88 tokens per second
llama-server | 10971.27.241.199 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 24504, progress = 0.63, t = 33.63 s / 728.62 tokens per second
llama-server | 10971.30.046.883 I slot print_timing: id 1 | task 2776451 | n_gen = 6485, tg = 16.30 t/s, tg_3s = 0.53 t/s
llama-server | 10971.30.055.702 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 26546, progress = 0.68, t = 36.45 s / 728.38 tokens per second
llama-server | 10971.32.871.795 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 28588, progress = 0.74, t = 39.26 s / 728.15 tokens per second
llama-server | 10971.35.676.993 I slot print_timing: id 1 | task 2776451 | n_gen = 6496, tg = 16.10 t/s, tg_3s = 1.95 t/s
llama-server | 10971.35.685.821 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 30630, progress = 0.79, t = 42.08 s / 727.98 tokens per second
llama-server | 10971.38.502.259 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 32672, progress = 0.84, t = 44.89 s / 727.80 tokens per second
llama-server | 10971.41.308.656 I slot print_timing: id 1 | task 2776451 | n_gen = 6504, tg = 15.90 t/s, tg_3s = 1.42 t/s
llama-server | 10971.41.317.507 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 34714, progress = 0.89, t = 47.71 s / 727.66 tokens per second
llama-server | 10971.44.135.384 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 36756, progress = 0.95, t = 50.52 s / 727.50 tokens per second
llama-server | 10971.46.463.201 I slot print_timing: id 1 | task 2776451 | n_gen = 6511, tg = 15.72 t/s, tg_3s = 1.36 t/s
llama-server | 10971.46.472.119 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 38365, progress = 0.99, t = 52.89 s / 725.37 tokens per second
llama-server | 10971.47.543.836 I slot print_timing: id 0 | task 2778529 | prompt processing, n_tokens = 38877, progress = 1.00, t = 54.03 s / 719.57 tokens per second
llama-server | 10971.49.489.929 I slot print_timing: id 1 | task 2776451 | n_gen = 6564, tg = 15.73 t/s, tg_3s = 17.51 t/s
llama-server | 10971.51.664.248 I slot print_timing: id 0 | task 2778529 | n_gen = 100, tg = 26.54 t/s, tg_3s = 26.80 t/s
llama-server | 10971.52.514.286 I slot print_timing: id 1 | task 2776451 | n_gen = 6650, tg = 15.82 t/s, tg_3s = 28.44 t/s
llama-server | 10971.54.692.085 I slot print_timing: id 0 | task 2778529 | n_gen = 186, tg = 27.37 t/s, tg_3s = 28.40 t/s
llama-server | 10971.55.544.288 I slot print_timing: id 1 | task 2776451 | n_gen = 6752, tg = 15.95 t/s, tg_3s = 33.66 t/s
llama-server | 10971.57.727.398 I slot print_timing: id 0 | task 2778529 | n_gen = 281, tg = 28.59 t/s, tg_3s = 31.30 t/s
llama-server | 10971.58.580.561 I slot print_timing: id 1 | task 2776451 | n_gen = 6859, tg = 16.09 t/s, tg_3s = 35.24 t/s
llama-server | 10972.00.781.981 I slot print_timing: id 0 | task 2778529 | n_gen = 409, tg = 31.76 t/s, tg_3s = 41.90 t/s
llama-server | 10972.01.635.649 I slot print_timing: id 1 | task 2776451 | n_gen = 6978, tg = 16.25 t/s, tg_3s = 38.95 t/s
llama-server | 10972.03.812.465 I slot print_timing: id 0 | task 2778529 | n_gen = 511, tg = 32.12 t/s, tg_3s = 33.66 t/s
llama-server | 10972.04.666.562 I slot print_timing: id 1 | task 2776451 | n_gen = 7096, tg = 16.41 t/s, tg_3s = 38.93 t/s
llama-server | 10972.06.845.180 I slot print_timing: id 0 | task 2778529 | n_gen = 626, tg = 33.05 t/s, tg_3s = 37.92 t/s
llama-server | 10972.07.699.157 I slot print_timing: id 1 | task 2776451 | n_gen = 7200, tg = 16.53 t/s, tg_3s = 34.29 t/s
llama-server | 10972.09.888.515 I slot print_timing: id 0 | task 2778529 | n_gen = 720, tg = 32.75 t/s, tg_3s = 30.89 t/s
llama-server | 10972.10.743.189 I slot print_timing: id 1 | task 2776451 | n_gen = 7342, tg = 16.74 t/s, tg_3s = 46.65 t/s
llama-server | 10972.12.925.381 I slot print_timing: id 0 | task 2778529 | n_gen = 820, tg = 32.77 t/s, tg_3s = 32.93 t/s
llama-server | 10972.13.782.599 I slot print_timing: id 1 | task 2776451 | n_gen = 7461, tg = 16.90 t/s, tg_3s = 39.15 t/s
llama-server | 10972.15.961.736 I slot print_timing: id 0 | task 2778529 | n_gen = 914, tg = 32.57 t/s, tg_3s = 30.96 t/s
llama-server | 10972.16.818.267 I slot print_timing: id 1 | task 2776451 | n_gen = 7582, tg = 17.05 t/s, tg_3s = 39.86 t/s
llama-server | 10972.19.008.391 I slot print_timing: id 0 | task 2778529 | n_gen = 1032, tg = 33.18 t/s, tg_3s = 38.73 t/s
llama-server | 10972.19.862.481 I slot print_timing: id 1 | task 2776451 | n_gen = 7690, tg = 17.18 t/s, tg_3s = 35.48 t/s
llama-server | 10972.22.042.797 I slot print_timing: id 0 | task 2778529 | n_gen = 1132, tg = 33.16 t/s, tg_3s = 32.96 t/s
llama-server | 10972.22.899.660 I slot print_timing: id 1 | task 2776451 | n_gen = 7851, tg = 17.42 t/s, tg_3s = 53.01 t/s
llama-server | 10972.25.082.029 I slot print_timing: id 0 | task 2778529 | n_gen = 1211, tg = 32.57 t/s, tg_3s = 25.99 t/s
llama-server | 10972.25.933.476 I slot print_timing: id 1 | task 2776451 | n_gen = 8000, tg = 17.63 t/s, tg_3s = 49.11 t/s
llama-server | 10972.28.107.108 I slot print_timing: id 0 | task 2778529 | n_gen = 1293, tg = 32.16 t/s, tg_3s = 27.11 t/s
llama-server | 10972.28.967.339 I slot print_timing: id 1 | task 2776451 | n_gen = 8102, tg = 17.74 t/s, tg_3s = 33.62 t/s
llama-server | 10972.31.150.355 I slot print_timing: id 0 | task 2778529 | n_gen = 1404, tg = 32.46 t/s, tg_3s = 36.47 t/s
llama-server | 10972.32.010.652 I slot print_timing: id 1 | task 2776451 | n_gen = 8196, tg = 17.83 t/s, tg_3s = 30.89 t/s
llama-server | 10972.34.196.557 I slot print_timing: id 0 | task 2778529 | n_gen = 1528, tg = 33.01 t/s, tg_3s = 40.71 t/s
llama-server | 10972.35.050.564 I slot print_timing: id 1 | task 2776451 | n_gen = 8320, tg = 17.98 t/s, tg_3s = 40.79 t/s
llama-server | 10972.37.244.236 I slot print_timing: id 0 | task 2778529 | n_gen = 1642, tg = 33.28 t/s, tg_3s = 37.41 t/s
llama-server | 10972.38.108.098 I slot print_timing: id 1 | task 2776451 | n_gen = 8504, tg = 18.25 t/s, tg_3s = 60.18 t/s
llama-server | 10972.40.329.053 I slot print_timing: id 0 | task 2778529 | n_gen = 1771, tg = 33.78 t/s, tg_3s = 41.82 t/s
llama-server | 10972.41.193.061 I slot print_timing: id 1 | task 2776451 | n_gen = 8626, tg = 18.39 t/s, tg_3s = 39.55 t/s
llama-server | 10972.43.415.955 I slot print_timing: id 0 | task 2778529 | n_gen = 1873, tg = 33.74 t/s, tg_3s = 33.04 t/s
llama-server | 10972.44.278.105 I slot print_timing: id 1 | task 2776451 | n_gen = 8800, tg = 18.64 t/s, tg_3s = 56.40 t/s
llama-server | 10972.46.492.339 I slot print_timing: id 0 | task 2778529 | n_gen = 1978, tg = 33.76 t/s, tg_3s = 34.13 t/s
llama-server | 10972.47.356.130 I slot print_timing: id 1 | task 2776451 | n_gen = 8908, tg = 18.75 t/s, tg_3s = 35.09 t/s
llama-server | 10972.47.450.525 I slot print_timing: id 0 | task 2778529 | prompt eval time = 54470.80 ms / 38881 tokens ( 1.40 ms per token, 713.80 tokens per second)
llama-server | 10972.47.450.527 I slot print_timing: id 0 | task 2778529 | eval time = 59516.70 ms / 2034 tokens ( 29.28 ms per token, 34.16 tokens per second)
llama-server | 10972.47.450.528 I slot print_timing: id 0 | task 2778529 | total time = 113987.50 ms / 40915 tokens
llama-server | 10972.47.450.529 I slot print_timing: id 0 | task 2778529 | graphs reused = 2691423
llama-server | 10972.47.450.531 I slot print_timing: id 0 | task 2778529 | draft acceptance = 0.45056 ( 1408 accepted / 3125 generated), mean len = 3.25
llama-server | 10972.47.451.772 I slot release: id 0 | task 2778529 | stop processing: n_tokens = 40914, truncated = 0
llama-server | 10972.50.398.701 I slot print_timing: id 1 | task 2776451 | n_gen = 9001, tg = 18.82 t/s, tg_3s = 30.57 t/s
llama-server | 10972.53.400.662 I slot print_timing: id 1 | task 2776451 | n_gen = 9103, tg = 18.92 t/s, tg_3s = 33.98 t/s
llama-server | 10972.56.497.928 I slot print_timing: id 1 | task 2776451 | n_gen = 9204, tg = 19.01 t/s, tg_3s = 32.61 t/s
llama-server | 10972.59.526.351 I slot print_timing: id 1 | task 2776451 | n_gen = 9337, tg = 19.16 t/s, tg_3s = 43.92 t/s
llama-server | 10973.02.549.327 I slot print_timing: id 1 | task 2776451 | n_gen = 9499, tg = 19.37 t/s, tg_3s = 53.59 t/s
llama-server | 10973.05.501.160 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658383291824
llama-server | 10973.05.503.245 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2025.920 MiB)
llama-server | 10973.08.709.409 I slot launch_slot_: id 0 | task 2779361 | processing task, is_child = 0
llama-server | 10973.11.603.478 I slot print_timing: id 1 | task 2776451 | n_gen = 9681, tg = 19.39 t/s, tg_3s = 20.10 t/s
llama-server | 10973.14.453.106 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.58 s / 731.57 tokens per second
llama-server | 10973.17.310.856 I slot print_timing: id 1 | task 2776451 | n_gen = 9693, tg = 19.19 t/s, tg_3s = 2.10 t/s
llama-server | 10973.17.319.661 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.45 s / 724.94 tokens per second
llama-server | 10973.20.159.639 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 8168, progress = 0.21, t = 11.29 s / 723.47 tokens per second
llama-server | 10973.22.995.367 I slot print_timing: id 1 | task 2776451 | n_gen = 9705, tg = 19.00 t/s, tg_3s = 2.11 t/s
llama-server | 10973.23.004.211 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 10210, progress = 0.26, t = 14.13 s / 722.46 tokens per second
llama-server | 10973.25.848.149 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 12252, progress = 0.31, t = 16.98 s / 721.61 tokens per second
llama-server | 10973.28.684.490 I slot print_timing: id 1 | task 2776451 | n_gen = 9717, tg = 18.81 t/s, tg_3s = 2.11 t/s
llama-server | 10973.28.693.278 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 14294, progress = 0.36, t = 19.82 s / 721.06 tokens per second
llama-server | 10973.31.539.492 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 16336, progress = 0.41, t = 22.67 s / 720.64 tokens per second
llama-server | 10973.34.372.738 I slot print_timing: id 1 | task 2776451 | n_gen = 9729, tg = 18.63 t/s, tg_3s = 2.11 t/s
llama-server | 10973.34.381.602 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 18378, progress = 0.46, t = 25.51 s / 720.36 tokens per second
llama-server | 10973.37.226.525 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 20420, progress = 0.51, t = 28.36 s / 720.11 tokens per second
llama-server | 10973.40.063.364 I slot print_timing: id 1 | task 2776451 | n_gen = 9741, tg = 18.45 t/s, tg_3s = 2.11 t/s
llama-server | 10973.40.072.173 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 22462, progress = 0.57, t = 31.20 s / 719.86 tokens per second
llama-server | 10973.42.916.473 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 24504, progress = 0.62, t = 34.05 s / 719.70 tokens per second
llama-server | 10973.45.753.500 I slot print_timing: id 1 | task 2776451 | n_gen = 9753, tg = 18.28 t/s, tg_3s = 2.11 t/s
llama-server | 10973.45.762.283 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 26546, progress = 0.67, t = 36.89 s / 719.54 tokens per second
llama-server | 10973.48.610.329 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 28588, progress = 0.72, t = 39.74 s / 719.35 tokens per second
llama-server | 10973.51.446.338 I slot print_timing: id 1 | task 2776451 | n_gen = 9765, tg = 18.11 t/s, tg_3s = 2.11 t/s
llama-server | 10973.51.455.129 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 30630, progress = 0.77, t = 42.59 s / 719.24 tokens per second
llama-server | 10973.54.299.243 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 32672, progress = 0.82, t = 45.43 s / 719.17 tokens per second
llama-server | 10973.57.135.958 I slot print_timing: id 1 | task 2776451 | n_gen = 9775, tg = 17.94 t/s, tg_3s = 1.76 t/s
llama-server | 10973.57.144.803 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 34714, progress = 0.87, t = 48.28 s / 719.07 tokens per second
llama-server | 10973.59.988.631 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 36756, progress = 0.93, t = 51.12 s / 719.01 tokens per second
llama-server | 10974.02.827.803 I slot print_timing: id 1 | task 2776451 | n_gen = 9780, tg = 17.76 t/s, tg_3s = 0.88 t/s
llama-server | 10974.02.836.686 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 38798, progress = 0.98, t = 53.97 s / 718.91 tokens per second
llama-server | 10974.03.512.649 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 39162, progress = 0.99, t = 54.75 s / 715.27 tokens per second
llama-server | 10974.04.614.130 I slot print_timing: id 0 | task 2779361 | prompt processing, n_tokens = 39674, progress = 1.00, t = 55.84 s / 710.46 tokens per second
llama-server | 10974.05.838.268 I slot print_timing: id 1 | task 2776451 | n_gen = 9797, tg = 17.70 t/s, tg_3s = 5.65 t/s
llama-server | 10974.08.134.784 I slot print_timing: id 0 | task 2779361 | n_gen = 123, tg = 40.56 t/s, tg_3s = 40.89 t/s
llama-server | 10974.08.901.249 I slot print_timing: id 1 | task 2776451 | n_gen = 9886, tg = 17.76 t/s, tg_3s = 29.06 t/s
llama-server | 10974.11.198.844 I slot print_timing: id 0 | task 2779361 | n_gen = 252, tg = 41.34 t/s, tg_3s = 42.10 t/s
llama-server | 10974.11.390.833 I slot print_timing: id 0 | task 2779361 | prompt eval time = 56406.19 ms / 39678 tokens ( 1.42 ms per token, 703.43 tokens per second)
llama-server | 10974.11.390.836 I slot print_timing: id 0 | task 2779361 | eval time = 6263.85 ms / 261 tokens ( 24.09 ms per token, 41.51 tokens per second)
llama-server | 10974.11.390.836 I slot print_timing: id 0 | task 2779361 | total time = 62670.05 ms / 39939 tokens
llama-server | 10974.11.390.837 I slot print_timing: id 0 | task 2779361 | graphs reused = 2691706
llama-server | 10974.11.390.840 I slot print_timing: id 0 | task 2779361 | draft acceptance = 0.60308 ( 196 accepted / 325 generated), mean len = 4.02
llama-server | 10974.11.391.959 I slot release: id 0 | task 2779361 | stop processing: n_tokens = 39939, truncated = 0
llama-server | 10974.11.996.538 I slot print_timing: id 1 | task 2776451 | n_gen = 9981, tg = 17.83 t/s, tg_3s = 30.69 t/s
llama-server | 10974.12.577.184 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658467232011
llama-server | 10974.12.579.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1867.256 MiB)
llama-server | 10974.15.674.366 I slot launch_slot_: id 0 | task 2779461 | processing task, is_child = 0
llama-server | 10974.18.593.841 I slot print_timing: id 1 | task 2776451 | n_gen = 9997, tg = 17.65 t/s, tg_3s = 2.43 t/s
llama-server | 10974.21.455.638 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.60 s / 729.37 tokens per second
llama-server | 10974.24.324.273 I slot print_timing: id 1 | task 2776451 | n_gen = 10005, tg = 17.49 t/s, tg_3s = 1.40 t/s
llama-server | 10974.24.333.406 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.48 s / 722.70 tokens per second
llama-server | 10974.27.187.664 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 8168, progress = 0.21, t = 11.33 s / 720.82 tokens per second
llama-server | 10974.30.035.211 I slot print_timing: id 1 | task 2776451 | n_gen = 10008, tg = 17.32 t/s, tg_3s = 0.53 t/s
llama-server | 10974.30.044.107 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 10210, progress = 0.26, t = 14.19 s / 719.62 tokens per second
llama-server | 10974.32.900.856 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 12252, progress = 0.31, t = 17.05 s / 718.80 tokens per second
llama-server | 10974.35.751.602 I slot print_timing: id 1 | task 2776451 | n_gen = 10013, tg = 17.16 t/s, tg_3s = 0.87 t/s
llama-server | 10974.35.760.770 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 14294, progress = 0.36, t = 19.91 s / 718.10 tokens per second
llama-server | 10974.38.619.532 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 16336, progress = 0.41, t = 22.76 s / 717.63 tokens per second
llama-server | 10974.41.469.146 I slot print_timing: id 1 | task 2776451 | n_gen = 10016, tg = 17.00 t/s, tg_3s = 0.52 t/s
llama-server | 10974.41.477.759 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 18378, progress = 0.46, t = 25.62 s / 717.24 tokens per second
llama-server | 10974.44.338.703 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 20420, progress = 0.52, t = 28.48 s / 716.91 tokens per second
llama-server | 10974.47.190.462 I slot print_timing: id 1 | task 2776451 | n_gen = 10021, tg = 16.84 t/s, tg_3s = 0.87 t/s
llama-server | 10974.47.199.548 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 22462, progress = 0.57, t = 31.34 s / 716.62 tokens per second
llama-server | 10974.50.061.749 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 24504, progress = 0.62, t = 34.21 s / 716.36 tokens per second
llama-server | 10974.52.915.859 I slot print_timing: id 1 | task 2776451 | n_gen = 10027, tg = 16.69 t/s, tg_3s = 1.05 t/s
llama-server | 10974.52.924.652 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 26546, progress = 0.67, t = 37.07 s / 716.12 tokens per second
llama-server | 10974.55.785.991 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 28588, progress = 0.72, t = 39.93 s / 715.95 tokens per second
llama-server | 10974.58.639.976 I slot print_timing: id 1 | task 2776451 | n_gen = 10032, tg = 16.54 t/s, tg_3s = 0.87 t/s
llama-server | 10974.58.649.089 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 30630, progress = 0.77, t = 42.79 s / 715.76 tokens per second
llama-server | 10975.01.512.976 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 32672, progress = 0.82, t = 45.66 s / 715.59 tokens per second
llama-server | 10975.04.366.417 I slot print_timing: id 1 | task 2776451 | n_gen = 10037, tg = 16.40 t/s, tg_3s = 0.87 t/s
llama-server | 10975.04.375.275 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 34714, progress = 0.88, t = 48.52 s / 715.45 tokens per second
llama-server | 10975.07.239.345 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 36756, progress = 0.93, t = 51.38 s / 715.33 tokens per second
llama-server | 10975.10.097.768 I slot print_timing: id 1 | task 2776451 | n_gen = 10047, tg = 16.26 t/s, tg_3s = 1.74 t/s
llama-server | 10975.10.106.633 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 38798, progress = 0.98, t = 54.25 s / 715.17 tokens per second
llama-server | 10975.10.647.400 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 39090, progress = 0.99, t = 54.93 s / 711.68 tokens per second
llama-server | 10975.11.774.352 I slot print_timing: id 0 | task 2779461 | prompt processing, n_tokens = 39602, progress = 1.00, t = 56.04 s / 706.72 tokens per second
llama-server | 10975.13.118.388 I slot print_timing: id 1 | task 2776451 | n_gen = 10093, tg = 16.26 t/s, tg_3s = 15.23 t/s
llama-server | 10975.15.314.712 I slot print_timing: id 0 | task 2779461 | n_gen = 109, tg = 35.93 t/s, tg_3s = 36.26 t/s
llama-server | 10975.16.172.961 I slot print_timing: id 1 | task 2776451 | n_gen = 10172, tg = 16.30 t/s, tg_3s = 25.86 t/s
llama-server | 10975.18.366.779 I slot print_timing: id 0 | task 2779461 | n_gen = 191, tg = 31.36 t/s, tg_3s = 26.87 t/s
llama-server | 10975.19.228.761 I slot print_timing: id 1 | task 2776451 | n_gen = 10270, tg = 16.38 t/s, tg_3s = 32.07 t/s
llama-server | 10975.21.424.922 I slot print_timing: id 0 | task 2779461 | n_gen = 291, tg = 31.81 t/s, tg_3s = 32.70 t/s
llama-server | 10975.22.286.062 I slot print_timing: id 1 | task 2776451 | n_gen = 10362, tg = 16.45 t/s, tg_3s = 30.09 t/s
llama-server | 10975.24.503.888 I slot print_timing: id 0 | task 2779461 | n_gen = 414, tg = 33.87 t/s, tg_3s = 39.95 t/s
llama-server | 10975.25.365.766 I slot print_timing: id 1 | task 2776451 | n_gen = 10483, tg = 16.56 t/s, tg_3s = 39.29 t/s
llama-server | 10975.27.563.771 I slot print_timing: id 0 | task 2779461 | n_gen = 489, tg = 31.99 t/s, tg_3s = 24.51 t/s
llama-server | 10975.28.453.772 I slot print_timing: id 1 | task 2776451 | n_gen = 10618, tg = 16.69 t/s, tg_3s = 43.72 t/s
llama-server | 10975.30.566.905 I slot print_timing: id 0 | task 2779461 | n_gen = 554, tg = 30.29 t/s, tg_3s = 21.64 t/s
llama-server | 10975.31.547.019 I slot print_timing: id 1 | task 2776451 | n_gen = 10765, tg = 16.84 t/s, tg_3s = 47.52 t/s
llama-server | 10975.33.651.496 I slot print_timing: id 0 | task 2779461 | n_gen = 633, tg = 29.61 t/s, tg_3s = 25.61 t/s
llama-server | 10975.34.610.862 I slot print_timing: id 1 | task 2776451 | n_gen = 10863, tg = 16.91 t/s, tg_3s = 31.99 t/s
llama-server | 10975.36.659.173 I slot print_timing: id 0 | task 2779461 | n_gen = 704, tg = 28.87 t/s, tg_3s = 23.61 t/s
llama-server | 10975.37.625.473 I slot print_timing: id 1 | task 2776451 | n_gen = 11042, tg = 17.11 t/s, tg_3s = 59.38 t/s
llama-server | 10975.39.677.467 I slot print_timing: id 0 | task 2779461 | n_gen = 793, tg = 28.94 t/s, tg_3s = 29.49 t/s
llama-server | 10975.40.638.697 I slot print_timing: id 1 | task 2776451 | n_gen = 11181, tg = 17.24 t/s, tg_3s = 46.13 t/s
llama-server | 10975.42.681.771 I slot print_timing: id 0 | task 2779461 | n_gen = 879, tg = 28.91 t/s, tg_3s = 28.63 t/s
llama-server | 10975.43.642.192 I slot print_timing: id 1 | task 2776451 | n_gen = 11274, tg = 17.31 t/s, tg_3s = 30.96 t/s
llama-server | 10975.45.761.704 I slot print_timing: id 0 | task 2779461 | n_gen = 950, tg = 28.37 t/s, tg_3s = 23.05 t/s
llama-server | 10975.46.662.927 I slot print_timing: id 1 | task 2776451 | n_gen = 11394, tg = 17.41 t/s, tg_3s = 39.73 t/s
llama-server | 10975.48.792.894 I slot print_timing: id 0 | task 2779461 | n_gen = 1040, tg = 28.48 t/s, tg_3s = 29.69 t/s
llama-server | 10975.49.757.911 I slot print_timing: id 1 | task 2776451 | n_gen = 11523, tg = 17.52 t/s, tg_3s = 41.68 t/s
llama-server | 10975.51.810.148 I slot print_timing: id 0 | task 2779461 | n_gen = 1112, tg = 28.13 t/s, tg_3s = 23.86 t/s
llama-server | 10975.52.776.231 I slot print_timing: id 1 | task 2776451 | n_gen = 11623, tg = 17.60 t/s, tg_3s = 33.13 t/s
llama-server | 10975.54.901.823 I slot print_timing: id 0 | task 2779461 | n_gen = 1173, tg = 27.52 t/s, tg_3s = 19.73 t/s
llama-server | 10975.55.800.485 I slot print_timing: id 1 | task 2776451 | n_gen = 11726, tg = 17.67 t/s, tg_3s = 34.06 t/s
llama-server | 10975.57.937.264 I slot print_timing: id 0 | task 2779461 | n_gen = 1251, tg = 27.40 t/s, tg_3s = 25.70 t/s
llama-server | 10975.58.843.147 I slot print_timing: id 1 | task 2776451 | n_gen = 11867, tg = 17.80 t/s, tg_3s = 46.34 t/s
llama-server | 10976.00.986.271 I slot print_timing: id 0 | task 2779461 | n_gen = 1341, tg = 27.53 t/s, tg_3s = 29.52 t/s
llama-server | 10976.01.889.420 I slot print_timing: id 1 | task 2776451 | n_gen = 12041, tg = 17.98 t/s, tg_3s = 57.12 t/s
llama-server | 10976.03.838.999 I slot print_timing: id 0 | task 2779461 | prompt eval time = 56622.11 ms / 39606 tokens ( 1.43 ms per token, 699.48 tokens per second)
llama-server | 10976.03.839.003 I slot print_timing: id 0 | task 2779461 | eval time = 51530.46 ms / 1428 tokens ( 36.11 ms per token, 27.69 tokens per second)
llama-server | 10976.03.839.004 I slot print_timing: id 0 | task 2779461 | total time = 108152.56 ms / 41034 tokens
llama-server | 10976.03.839.005 I slot print_timing: id 0 | task 2779461 | graphs reused = 2692276
llama-server | 10976.03.839.009 I slot print_timing: id 0 | task 2779461 | draft acceptance = 0.33647 ( 895 accepted / 2660 generated), mean len = 2.68
llama-server | 10976.03.840.219 I slot release: id 0 | task 2779461 | stop processing: n_tokens = 41033, truncated = 0
llama-server | 10976.04.956.838 I slot print_timing: id 1 | task 2776451 | n_gen = 12194, tg = 18.13 t/s, tg_3s = 49.88 t/s
llama-server | 10976.05.155.930 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658579680272
llama-server | 10976.05.158.129 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1898.278 MiB)
llama-server | 10976.08.810.509 I slot launch_slot_: id 0 | task 2780029 | processing task, is_child = 0
llama-server | 10976.11.752.815 I slot print_timing: id 1 | task 2776451 | n_gen = 12212, tg = 17.97 t/s, tg_3s = 2.65 t/s
llama-server | 10976.14.648.773 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 4084, progress = 0.09, t = 5.68 s / 719.41 tokens per second
llama-server | 10976.17.563.052 I slot print_timing: id 1 | task 2776451 | n_gen = 12224, tg = 17.84 t/s, tg_3s = 2.07 t/s
llama-server | 10976.17.571.941 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 6126, progress = 0.13, t = 8.59 s / 713.03 tokens per second
llama-server | 10976.20.459.777 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 8168, progress = 0.17, t = 11.49 s / 710.94 tokens per second
llama-server | 10976.23.341.739 I slot print_timing: id 1 | task 2776451 | n_gen = 12236, tg = 17.70 t/s, tg_3s = 2.08 t/s
llama-server | 10976.23.350.653 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 10210, progress = 0.22, t = 14.38 s / 710.03 tokens per second
llama-server | 10976.26.243.526 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 12252, progress = 0.26, t = 17.27 s / 709.37 tokens per second
llama-server | 10976.29.124.984 I slot print_timing: id 1 | task 2776451 | n_gen = 12248, tg = 17.57 t/s, tg_3s = 2.07 t/s
llama-server | 10976.29.134.208 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 14294, progress = 0.30, t = 20.16 s / 708.95 tokens per second
llama-server | 10976.32.026.388 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 16336, progress = 0.35, t = 23.05 s / 708.57 tokens per second
llama-server | 10976.34.905.808 I slot print_timing: id 1 | task 2776451 | n_gen = 12260, tg = 17.45 t/s, tg_3s = 2.08 t/s
llama-server | 10976.34.914.479 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 18378, progress = 0.39, t = 25.94 s / 708.36 tokens per second
llama-server | 10976.37.805.543 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 20420, progress = 0.44, t = 28.84 s / 708.16 tokens per second
llama-server | 10976.40.697.078 I slot print_timing: id 1 | task 2776451 | n_gen = 12269, tg = 17.32 t/s, tg_3s = 1.55 t/s
llama-server | 10976.40.705.967 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 22462, progress = 0.48, t = 31.73 s / 707.84 tokens per second
llama-server | 10976.43.596.694 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 24504, progress = 0.52, t = 34.63 s / 707.67 tokens per second
llama-server | 10976.46.478.426 I slot print_timing: id 1 | task 2776451 | n_gen = 12281, tg = 17.19 t/s, tg_3s = 2.08 t/s
llama-server | 10976.46.487.316 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 26546, progress = 0.57, t = 37.52 s / 707.58 tokens per second
llama-server | 10976.49.380.899 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 28588, progress = 0.61, t = 40.41 s / 707.46 tokens per second
llama-server | 10976.52.263.344 I slot print_timing: id 1 | task 2776451 | n_gen = 12293, tg = 17.07 t/s, tg_3s = 2.07 t/s
llama-server | 10976.52.272.244 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 30630, progress = 0.65, t = 43.30 s / 707.35 tokens per second
llama-server | 10976.55.166.562 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 32672, progress = 0.70, t = 46.20 s / 707.25 tokens per second
llama-server | 10976.58.054.647 I slot print_timing: id 1 | task 2776451 | n_gen = 12305, tg = 16.95 t/s, tg_3s = 2.07 t/s
llama-server | 10976.58.063.638 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 34714, progress = 0.74, t = 49.09 s / 707.11 tokens per second
llama-server | 10977.00.956.557 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 36756, progress = 0.78, t = 51.99 s / 707.04 tokens per second
llama-server | 10977.03.843.103 I slot print_timing: id 1 | task 2776451 | n_gen = 12317, tg = 16.84 t/s, tg_3s = 2.07 t/s
llama-server | 10977.03.852.246 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 38798, progress = 0.83, t = 54.88 s / 706.94 tokens per second
llama-server | 10977.06.747.708 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 40840, progress = 0.87, t = 57.78 s / 706.86 tokens per second
llama-server | 10977.09.666.488 I slot print_timing: id 1 | task 2776451 | n_gen = 12329, tg = 16.72 t/s, tg_3s = 2.06 t/s
llama-server | 10977.09.675.368 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 42882, progress = 0.91, t = 60.70 s / 706.51 tokens per second
llama-server | 10977.12.625.937 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 44924, progress = 0.96, t = 63.66 s / 705.73 tokens per second
llama-server | 10977.14.908.965 I slot print_timing: id 1 | task 2776451 | n_gen = 12341, tg = 16.62 t/s, tg_3s = 2.29 t/s
llama-server | 10977.14.917.846 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 46399, progress = 0.99, t = 65.98 s / 703.20 tokens per second
llama-server | 10977.16.111.021 I slot print_timing: id 0 | task 2780029 | prompt processing, n_tokens = 46911, progress = 1.00, t = 67.24 s / 697.70 tokens per second
llama-server | 10977.18.001.936 I slot print_timing: id 1 | task 2776451 | n_gen = 12417, tg = 16.65 t/s, tg_3s = 24.57 t/s
llama-server | 10977.19.539.390 I slot print_timing: id 0 | task 2780029 | prompt eval time = 67823.81 ms / 46915 tokens ( 1.45 ms per token, 691.72 tokens per second)
llama-server | 10977.19.539.393 I slot print_timing: id 0 | task 2780029 | eval time = 2893.49 ms / 97 tokens ( 30.14 ms per token, 33.18 tokens per second)
llama-server | 10977.19.539.394 I slot print_timing: id 0 | task 2780029 | total time = 70717.30 ms / 47012 tokens
llama-server | 10977.19.539.395 I slot print_timing: id 0 | task 2780029 | graphs reused = 2692354
llama-server | 10977.19.539.397 I slot print_timing: id 0 | task 2780029 | draft acceptance = 0.48571 ( 68 accepted / 140 generated), mean len = 3.43
llama-server | 10977.19.540.635 I slot release: id 0 | task 2780029 | stop processing: n_tokens = 47011, truncated = 0
llama-server | 10977.20.789.583 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658655380687
llama-server | 10977.20.793.742 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1873.773 MiB)
llama-server | 10977.25.050.069 I slot launch_slot_: id 0 | task 2780095 | processing task, is_child = 0
llama-server | 10977.28.055.819 I slot print_timing: id 1 | task 2776451 | n_gen = 12556, tg = 16.61 t/s, tg_3s = 13.83 t/s
llama-server | 10977.31.024.283 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 4084, progress = 0.09, t = 5.81 s / 703.26 tokens per second
llama-server | 10977.33.996.338 I slot print_timing: id 1 | task 2776451 | n_gen = 12562, tg = 16.49 t/s, tg_3s = 1.01 t/s
llama-server | 10977.34.005.004 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 6126, progress = 0.13, t = 8.79 s / 696.84 tokens per second
llama-server | 10977.36.960.697 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 8168, progress = 0.17, t = 11.75 s / 695.28 tokens per second
llama-server | 10977.39.914.777 I slot print_timing: id 1 | task 2776451 | n_gen = 12569, tg = 16.37 t/s, tg_3s = 1.18 t/s
llama-server | 10977.39.924.056 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 10210, progress = 0.22, t = 14.71 s / 694.12 tokens per second
llama-server | 10977.42.890.657 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 12252, progress = 0.26, t = 17.68 s / 693.16 tokens per second
llama-server | 10977.45.846.396 I slot print_timing: id 1 | task 2776451 | n_gen = 12581, tg = 16.26 t/s, tg_3s = 2.02 t/s
llama-server | 10977.45.855.499 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 14294, progress = 0.30, t = 20.64 s / 692.51 tokens per second
llama-server | 10977.48.824.763 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 16336, progress = 0.35, t = 23.61 s / 691.96 tokens per second
llama-server | 10977.51.782.717 I slot print_timing: id 1 | task 2776451 | n_gen = 12593, tg = 16.15 t/s, tg_3s = 2.02 t/s
llama-server | 10977.51.791.595 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 18378, progress = 0.39, t = 26.58 s / 691.50 tokens per second
llama-server | 10977.54.760.178 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 20420, progress = 0.43, t = 29.55 s / 691.11 tokens per second
llama-server | 10977.57.717.935 I slot print_timing: id 1 | task 2776451 | n_gen = 12598, tg = 16.04 t/s, tg_3s = 0.84 t/s
llama-server | 10977.57.726.455 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 22462, progress = 0.48, t = 32.51 s / 690.85 tokens per second
llama-server | 10978.00.695.818 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 24504, progress = 0.52, t = 35.48 s / 690.58 tokens per second
llama-server | 10978.03.656.279 I slot print_timing: id 1 | task 2776451 | n_gen = 12605, tg = 15.93 t/s, tg_3s = 1.18 t/s
llama-server | 10978.03.665.137 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 26546, progress = 0.56, t = 38.45 s / 690.38 tokens per second
llama-server | 10978.06.636.556 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 28588, progress = 0.61, t = 41.42 s / 690.17 tokens per second
llama-server | 10978.09.602.521 I slot print_timing: id 1 | task 2776451 | n_gen = 12617, tg = 15.82 t/s, tg_3s = 2.02 t/s
llama-server | 10978.09.611.400 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 30630, progress = 0.65, t = 44.40 s / 689.91 tokens per second
llama-server | 10978.12.584.554 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 32672, progress = 0.69, t = 47.37 s / 689.71 tokens per second
llama-server | 10978.15.550.314 I slot print_timing: id 1 | task 2776451 | n_gen = 12629, tg = 15.72 t/s, tg_3s = 2.02 t/s
llama-server | 10978.15.559.437 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 34714, progress = 0.74, t = 50.34 s / 689.52 tokens per second
llama-server | 10978.18.536.885 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 36756, progress = 0.78, t = 53.32 s / 689.34 tokens per second
llama-server | 10978.21.503.200 I slot print_timing: id 1 | task 2776451 | n_gen = 12637, tg = 15.61 t/s, tg_3s = 1.34 t/s
llama-server | 10978.21.512.485 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 38798, progress = 0.82, t = 56.30 s / 689.15 tokens per second
llama-server | 10978.24.490.763 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 40840, progress = 0.87, t = 59.28 s / 688.98 tokens per second
llama-server | 10978.27.457.386 I slot print_timing: id 1 | task 2776451 | n_gen = 12649, tg = 15.52 t/s, tg_3s = 2.02 t/s
llama-server | 10978.27.466.708 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 42882, progress = 0.91, t = 62.25 s / 688.84 tokens per second
llama-server | 10978.30.444.370 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 44924, progress = 0.95, t = 65.23 s / 688.70 tokens per second
llama-server | 10978.33.072.948 I slot print_timing: id 1 | task 2776451 | n_gen = 12661, tg = 15.42 t/s, tg_3s = 2.14 t/s
llama-server | 10978.33.081.804 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 46646, progress = 0.99, t = 67.88 s / 687.16 tokens per second
llama-server | 10978.34.287.574 I slot print_timing: id 0 | task 2780095 | prompt processing, n_tokens = 47158, progress = 1.00, t = 69.17 s / 681.78 tokens per second
llama-server | 10978.36.173.347 I slot print_timing: id 1 | task 2776451 | n_gen = 12751, tg = 15.48 t/s, tg_3s = 29.03 t/s
llama-server | 10978.38.484.147 I slot print_timing: id 0 | task 2780095 | n_gen = 104, tg = 27.89 t/s, tg_3s = 28.16 t/s
llama-server | 10978.39.189.164 I slot print_timing: id 1 | task 2776451 | n_gen = 12834, tg = 15.52 t/s, tg_3s = 27.52 t/s
llama-server | 10978.41.531.192 I slot print_timing: id 0 | task 2780095 | n_gen = 197, tg = 29.08 t/s, tg_3s = 30.52 t/s
llama-server | 10978.42.243.166 I slot print_timing: id 1 | task 2776451 | n_gen = 12914, tg = 15.56 t/s, tg_3s = 26.20 t/s
llama-server | 10978.44.592.483 I slot print_timing: id 0 | task 2780095 | n_gen = 309, tg = 31.42 t/s, tg_3s = 36.59 t/s
llama-server | 10978.45.303.457 I slot print_timing: id 1 | task 2776451 | n_gen = 13002, tg = 15.61 t/s, tg_3s = 28.76 t/s
llama-server | 10978.46.115.629 I slot print_timing: id 0 | task 2780095 | prompt eval time = 69729.28 ms / 47162 tokens ( 1.48 ms per token, 676.36 tokens per second)
llama-server | 10978.46.115.633 I slot print_timing: id 0 | task 2780095 | eval time = 11324.64 ms / 380 tokens ( 29.88 ms per token, 33.47 tokens per second)
llama-server | 10978.46.115.633 I slot print_timing: id 0 | task 2780095 | total time = 81053.92 ms / 47542 tokens
llama-server | 10978.46.115.634 I slot print_timing: id 0 | task 2780095 | graphs reused = 2692518
llama-server | 10978.46.115.638 I slot print_timing: id 0 | task 2780095 | draft acceptance = 0.48468 ( 269 accepted / 555 generated), mean len = 3.42
llama-server | 10978.46.117.115 I slot release: id 0 | task 2780095 | stop processing: n_tokens = 47542, truncated = 0
llama-server | 10978.47.467.240 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658741957168
llama-server | 10978.47.469.652 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1929.346 MiB)
llama-server | 10978.51.079.692 I slot launch_slot_: id 0 | task 2780245 | processing task, is_child = 0
llama-server | 10978.54.130.663 I slot print_timing: id 1 | task 2776451 | n_gen = 13070, tg = 15.52 t/s, tg_3s = 7.70 t/s
llama-server | 10978.57.112.295 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 4084, progress = 0.09, t = 5.87 s / 695.38 tokens per second
llama-server | 10979.00.100.611 I slot print_timing: id 1 | task 2776451 | n_gen = 13077, tg = 15.42 t/s, tg_3s = 1.17 t/s
llama-server | 10979.00.109.463 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 6126, progress = 0.13, t = 8.87 s / 690.66 tokens per second
llama-server | 10979.03.085.492 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 8168, progress = 0.17, t = 11.85 s / 689.48 tokens per second
llama-server | 10979.06.052.619 I slot print_timing: id 1 | task 2776451 | n_gen = 13082, tg = 15.32 t/s, tg_3s = 0.84 t/s
llama-server | 10979.06.061.355 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 10210, progress = 0.22, t = 14.82 s / 688.82 tokens per second
llama-server | 10979.09.043.516 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 12252, progress = 0.26, t = 17.80 s / 688.20 tokens per second
llama-server | 10979.12.013.273 I slot print_timing: id 1 | task 2776451 | n_gen = 13086, tg = 15.22 t/s, tg_3s = 0.67 t/s
llama-server | 10979.12.021.820 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 14294, progress = 0.30, t = 20.78 s / 687.75 tokens per second
llama-server | 10979.15.004.454 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 16336, progress = 0.35, t = 23.76 s / 687.43 tokens per second
llama-server | 10979.17.980.200 I slot print_timing: id 1 | task 2776451 | n_gen = 13089, tg = 15.12 t/s, tg_3s = 0.50 t/s
llama-server | 10979.17.989.008 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 18378, progress = 0.39, t = 26.75 s / 687.05 tokens per second
llama-server | 10979.20.971.198 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 20420, progress = 0.43, t = 29.73 s / 686.81 tokens per second
llama-server | 10979.23.947.893 I slot print_timing: id 1 | task 2776451 | n_gen = 13094, tg = 15.02 t/s, tg_3s = 0.84 t/s
llama-server | 10979.23.956.772 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 22462, progress = 0.47, t = 32.72 s / 686.52 tokens per second
llama-server | 10979.26.940.093 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 24504, progress = 0.52, t = 35.70 s / 686.35 tokens per second
llama-server | 10979.29.915.235 I slot print_timing: id 1 | task 2776451 | n_gen = 13099, tg = 14.92 t/s, tg_3s = 0.84 t/s
llama-server | 10979.29.924.995 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 26546, progress = 0.56, t = 38.68 s / 686.21 tokens per second
llama-server | 10979.32.910.516 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 28588, progress = 0.60, t = 41.67 s / 686.04 tokens per second
llama-server | 10979.35.887.187 I slot print_timing: id 1 | task 2776451 | n_gen = 13105, tg = 14.83 t/s, tg_3s = 1.00 t/s
llama-server | 10979.35.895.807 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 30630, progress = 0.65, t = 44.66 s / 685.89 tokens per second
llama-server | 10979.38.882.481 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 32672, progress = 0.69, t = 47.64 s / 685.76 tokens per second
llama-server | 10979.41.861.701 I slot print_timing: id 1 | task 2776451 | n_gen = 13111, tg = 14.74 t/s, tg_3s = 1.00 t/s
llama-server | 10979.41.870.558 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 34714, progress = 0.73, t = 50.63 s / 685.62 tokens per second
llama-server | 10979.44.858.553 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 36756, progress = 0.78, t = 53.62 s / 685.51 tokens per second
llama-server | 10979.47.841.524 I slot print_timing: id 1 | task 2776451 | n_gen = 13123, tg = 14.65 t/s, tg_3s = 2.01 t/s
llama-server | 10979.47.850.306 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 38798, progress = 0.82, t = 56.61 s / 685.36 tokens per second
llama-server | 10979.50.839.177 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 40840, progress = 0.86, t = 59.60 s / 685.24 tokens per second
llama-server | 10979.53.821.821 I slot print_timing: id 1 | task 2776451 | n_gen = 13128, tg = 14.56 t/s, tg_3s = 0.84 t/s
llama-server | 10979.53.830.710 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 42882, progress = 0.91, t = 62.59 s / 685.11 tokens per second
llama-server | 10979.56.821.799 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 44924, progress = 0.95, t = 65.58 s / 685.00 tokens per second
llama-server | 10979.59.686.933 I slot print_timing: id 1 | task 2776451 | n_gen = 13132, tg = 14.47 t/s, tg_3s = 0.68 t/s
llama-server | 10979.59.695.716 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 46818, progress = 0.99, t = 68.47 s / 683.82 tokens per second
llama-server | 10980.00.779.196 I slot print_timing: id 0 | task 2780245 | prompt processing, n_tokens = 47330, progress = 1.00, t = 69.64 s / 679.68 tokens per second
llama-server | 10980.02.783.706 I slot print_timing: id 1 | task 2776451 | n_gen = 13175, tg = 14.47 t/s, tg_3s = 13.89 t/s
llama-server | 10980.05.727.911 I slot print_timing: id 0 | task 2780245 | n_gen = 103, tg = 22.67 t/s, tg_3s = 22.89 t/s
llama-server | 10980.05.830.598 I slot print_timing: id 1 | task 2776451 | n_gen = 13259, tg = 14.51 t/s, tg_3s = 27.57 t/s
llama-server | 10980.08.765.376 I slot print_timing: id 0 | task 2780245 | n_gen = 180, tg = 23.75 t/s, tg_3s = 25.35 t/s
llama-server | 10980.08.867.663 I slot print_timing: id 1 | task 2776451 | n_gen = 13370, tg = 14.59 t/s, tg_3s = 36.55 t/s
llama-server | 10980.11.820.381 I slot print_timing: id 0 | task 2780245 | n_gen = 255, tg = 23.98 t/s, tg_3s = 24.55 t/s
llama-server | 10980.11.922.896 I slot print_timing: id 1 | task 2776451 | n_gen = 13456, tg = 14.63 t/s, tg_3s = 28.15 t/s
llama-server | 10980.14.893.460 I slot print_timing: id 0 | task 2780245 | n_gen = 325, tg = 23.71 t/s, tg_3s = 22.78 t/s
llama-server | 10980.14.996.189 I slot print_timing: id 1 | task 2776451 | n_gen = 13557, tg = 14.69 t/s, tg_3s = 32.86 t/s
llama-server | 10980.17.947.664 I slot print_timing: id 0 | task 2780245 | n_gen = 407, tg = 24.28 t/s, tg_3s = 26.85 t/s
llama-server | 10980.18.050.702 I slot print_timing: id 1 | task 2776451 | n_gen = 13682, tg = 14.78 t/s, tg_3s = 40.92 t/s
llama-server | 10980.21.029.025 I slot print_timing: id 0 | task 2780245 | n_gen = 482, tg = 24.29 t/s, tg_3s = 24.34 t/s
llama-server | 10980.21.132.364 I slot print_timing: id 1 | task 2776451 | n_gen = 13836, tg = 14.89 t/s, tg_3s = 49.97 t/s
llama-server | 10980.24.122.688 I slot print_timing: id 0 | task 2780245 | n_gen = 557, tg = 24.29 t/s, tg_3s = 24.24 t/s
llama-server | 10980.24.227.274 I slot print_timing: id 1 | task 2776451 | n_gen = 14013, tg = 15.04 t/s, tg_3s = 57.19 t/s
llama-server | 10980.27.208.222 I slot print_timing: id 0 | task 2780245 | n_gen = 629, tg = 24.17 t/s, tg_3s = 23.33 t/s
llama-server | 10980.27.311.414 I slot print_timing: id 1 | task 2776451 | n_gen = 14122, tg = 15.10 t/s, tg_3s = 35.34 t/s
llama-server | 10980.30.300.466 I slot print_timing: id 0 | task 2780245 | n_gen = 693, tg = 23.80 t/s, tg_3s = 20.70 t/s
llama-server | 10980.30.403.315 I slot print_timing: id 1 | task 2776451 | n_gen = 14217, tg = 15.15 t/s, tg_3s = 30.73 t/s
llama-server | 10980.33.374.117 I slot print_timing: id 0 | task 2780245 | n_gen = 760, tg = 23.61 t/s, tg_3s = 21.80 t/s
llama-server | 10980.33.478.756 I slot print_timing: id 1 | task 2776451 | n_gen = 14327, tg = 15.22 t/s, tg_3s = 35.77 t/s
llama-server | 10980.36.379.562 I slot print_timing: id 0 | task 2780245 | n_gen = 832, tg = 23.64 t/s, tg_3s = 23.96 t/s
llama-server | 10980.36.484.453 I slot print_timing: id 1 | task 2776451 | n_gen = 14479, tg = 15.33 t/s, tg_3s = 50.57 t/s
llama-server | 10980.39.392.248 I slot print_timing: id 0 | task 2780245 | n_gen = 921, tg = 24.11 t/s, tg_3s = 29.54 t/s
llama-server | 10980.39.494.996 I slot print_timing: id 1 | task 2776451 | n_gen = 14591, tg = 15.40 t/s, tg_3s = 37.20 t/s
llama-server | 10980.42.292.086 I slot print_timing: id 0 | task 2780245 | prompt eval time = 70137.22 ms / 47334 tokens ( 1.48 ms per token, 674.88 tokens per second)
llama-server | 10980.42.292.090 I slot print_timing: id 0 | task 2780245 | eval time = 41063.33 ms / 1004 tokens ( 40.94 ms per token, 24.43 tokens per second)
llama-server | 10980.42.292.090 I slot print_timing: id 0 | task 2780245 | total time = 111200.55 ms / 48338 tokens
llama-server | 10980.42.292.091 I slot print_timing: id 0 | task 2780245 | graphs reused = 2692965
llama-server | 10980.42.292.094 I slot print_timing: id 0 | task 2780245 | draft acceptance = 0.30200 ( 604 accepted / 2000 generated), mean len = 2.51
llama-server | 10980.42.293.365 I slot release: id 0 | task 2780245 | stop processing: n_tokens = 48338, truncated = 0
llama-server | 10980.42.525.383 I slot print_timing: id 1 | task 2776451 | n_gen = 14691, tg = 15.46 t/s, tg_3s = 33.00 t/s
llama-server | 10980.44.282.587 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658858133417
llama-server | 10980.44.286.181 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1896.948 MiB)
llama-server | 10980.44.463.422 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1933.322 MiB)
llama-server | 10980.48.723.472 I slot launch_slot_: id 0 | task 2780690 | processing task, is_child = 0
llama-server | 10980.51.797.474 I slot print_timing: id 1 | task 2776451 | n_gen = 14739, tg = 15.36 t/s, tg_3s = 5.18 t/s
llama-server | 10980.54.817.007 I slot print_timing: id 1 | task 2776451 | n_gen = 14740, tg = 15.31 t/s, tg_3s = 0.33 t/s
llama-server | 10980.54.825.699 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.94 s / 687.17 tokens per second
llama-server | 10980.57.866.174 I slot print_timing: id 1 | task 2776451 | n_gen = 14743, tg = 15.27 t/s, tg_3s = 0.98 t/s
llama-server | 10980.57.875.051 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.99 s / 681.28 tokens per second
llama-server | 10981.00.889.781 I slot print_timing: id 1 | task 2776451 | n_gen = 14744, tg = 15.22 t/s, tg_3s = 0.33 t/s
llama-server | 10981.00.898.678 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 8168, progress = 0.20, t = 12.02 s / 679.77 tokens per second
llama-server | 10981.03.918.696 I slot print_timing: id 1 | task 2776451 | n_gen = 14746, tg = 15.18 t/s, tg_3s = 0.66 t/s
llama-server | 10981.03.927.398 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 10210, progress = 0.25, t = 15.04 s / 678.67 tokens per second
llama-server | 10981.06.946.402 I slot print_timing: id 1 | task 2776451 | n_gen = 14751, tg = 15.13 t/s, tg_3s = 1.65 t/s
llama-server | 10981.06.955.445 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 12252, progress = 0.30, t = 18.07 s / 677.96 tokens per second
llama-server | 10981.09.973.665 I slot print_timing: id 1 | task 2776451 | n_gen = 14754, tg = 15.09 t/s, tg_3s = 0.99 t/s
llama-server | 10981.09.982.814 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 14294, progress = 0.35, t = 21.10 s / 677.48 tokens per second
llama-server | 10981.13.003.515 I slot print_timing: id 1 | task 2776451 | n_gen = 14756, tg = 15.04 t/s, tg_3s = 0.66 t/s
llama-server | 10981.13.012.385 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 16336, progress = 0.40, t = 24.13 s / 677.04 tokens per second
llama-server | 10981.16.030.284 I slot print_timing: id 1 | task 2776451 | n_gen = 14758, tg = 15.00 t/s, tg_3s = 0.66 t/s
llama-server | 10981.16.039.270 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 18378, progress = 0.45, t = 27.16 s / 676.74 tokens per second
llama-server | 10981.19.057.549 I slot print_timing: id 1 | task 2776451 | n_gen = 14761, tg = 14.96 t/s, tg_3s = 0.99 t/s
llama-server | 10981.19.066.739 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 20420, progress = 0.50, t = 30.18 s / 676.51 tokens per second
llama-server | 10981.22.085.744 I slot print_timing: id 1 | task 2776451 | n_gen = 14762, tg = 14.91 t/s, tg_3s = 0.33 t/s
llama-server | 10981.22.094.636 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 22462, progress = 0.55, t = 33.21 s / 676.31 tokens per second
llama-server | 10981.25.116.678 I slot print_timing: id 1 | task 2776451 | n_gen = 14764, tg = 14.87 t/s, tg_3s = 0.66 t/s
llama-server | 10981.25.125.512 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 24504, progress = 0.60, t = 36.24 s / 676.11 tokens per second
llama-server | 10981.28.147.127 I slot print_timing: id 1 | task 2776451 | n_gen = 14766, tg = 14.83 t/s, tg_3s = 0.66 t/s
llama-server | 10981.28.155.901 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 26546, progress = 0.65, t = 39.27 s / 675.94 tokens per second
llama-server | 10981.31.180.232 I slot print_timing: id 1 | task 2776451 | n_gen = 14772, tg = 14.79 t/s, tg_3s = 1.98 t/s
llama-server | 10981.31.189.048 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 28588, progress = 0.70, t = 42.31 s / 675.75 tokens per second
llama-server | 10981.34.212.038 I slot print_timing: id 1 | task 2776451 | n_gen = 14778, tg = 14.75 t/s, tg_3s = 1.98 t/s
llama-server | 10981.34.220.836 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 30630, progress = 0.75, t = 45.34 s / 675.60 tokens per second
llama-server | 10981.37.243.397 I slot print_timing: id 1 | task 2776451 | n_gen = 14784, tg = 14.71 t/s, tg_3s = 1.98 t/s
llama-server | 10981.37.252.098 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 32672, progress = 0.80, t = 48.37 s / 675.48 tokens per second
llama-server | 10981.40.275.443 I slot print_timing: id 1 | task 2776451 | n_gen = 14790, tg = 14.67 t/s, tg_3s = 1.98 t/s
llama-server | 10981.40.284.213 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 34714, progress = 0.85, t = 51.40 s / 675.36 tokens per second
llama-server | 10981.43.305.547 I slot print_timing: id 1 | task 2776451 | n_gen = 14796, tg = 14.63 t/s, tg_3s = 1.98 t/s
llama-server | 10981.43.314.361 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 36756, progress = 0.90, t = 54.43 s / 675.27 tokens per second
llama-server | 10981.46.338.168 I slot print_timing: id 1 | task 2776451 | n_gen = 14801, tg = 14.59 t/s, tg_3s = 1.65 t/s
llama-server | 10981.46.347.458 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 38798, progress = 0.95, t = 57.46 s / 675.18 tokens per second
llama-server | 10981.48.434.177 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 40147, progress = 0.99, t = 59.59 s / 673.68 tokens per second
llama-server | 10981.49.581.414 I slot print_timing: id 1 | task 2776451 | n_gen = 14809, tg = 14.56 t/s, tg_3s = 2.47 t/s
llama-server | 10981.49.590.280 I slot print_timing: id 0 | task 2780690 | prompt processing, n_tokens = 40659, progress = 1.00, t = 60.80 s / 668.69 tokens per second
llama-server | 10981.52.677.708 I slot print_timing: id 1 | task 2776451 | n_gen = 14912, tg = 14.61 t/s, tg_3s = 33.27 t/s
llama-server | 10981.54.826.934 I slot print_timing: id 0 | task 2780690 | n_gen = 103, tg = 21.48 t/s, tg_3s = 21.69 t/s
llama-server | 10981.55.752.948 I slot print_timing: id 1 | task 2776451 | n_gen = 15055, tg = 14.71 t/s, tg_3s = 46.50 t/s
llama-server | 10981.57.909.292 I slot print_timing: id 0 | task 2780690 | n_gen = 239, tg = 30.39 t/s, tg_3s = 44.12 t/s
llama-server | 10981.58.835.377 I slot print_timing: id 1 | task 2776451 | n_gen = 15205, tg = 14.81 t/s, tg_3s = 48.66 t/s
llama-server | 10982.00.985.566 I slot print_timing: id 0 | task 2780690 | n_gen = 324, tg = 29.61 t/s, tg_3s = 27.63 t/s
llama-server | 10982.01.915.803 I slot print_timing: id 1 | task 2776451 | n_gen = 15351, tg = 14.91 t/s, tg_3s = 47.40 t/s
llama-server | 10982.04.077.275 I slot print_timing: id 0 | task 2780690 | n_gen = 415, tg = 29.57 t/s, tg_3s = 29.43 t/s
llama-server | 10982.05.002.115 I slot print_timing: id 1 | task 2776451 | n_gen = 15454, tg = 14.96 t/s, tg_3s = 33.37 t/s
llama-server | 10982.07.150.743 I slot print_timing: id 0 | task 2780690 | n_gen = 555, tg = 32.45 t/s, tg_3s = 45.55 t/s
llama-server | 10982.07.764.932 I slot print_timing: id 0 | task 2780690 | prompt eval time = 61343.84 ms / 40663 tokens ( 1.51 ms per token, 662.87 tokens per second)
llama-server | 10982.07.764.935 I slot print_timing: id 0 | task 2780690 | eval time = 17686.38 ms / 586 tokens ( 30.23 ms per token, 33.08 tokens per second)
llama-server | 10982.07.764.936 I slot print_timing: id 0 | task 2780690 | total time = 79030.21 ms / 41249 tokens
llama-server | 10982.07.764.936 I slot print_timing: id 0 | task 2780690 | graphs reused = 2693193
llama-server | 10982.07.764.939 I slot print_timing: id 0 | task 2780690 | draft acceptance = 0.48140 ( 414 accepted / 860 generated), mean len = 3.41
llama-server | 10982.07.766.186 I slot release: id 0 | task 2780690 | stop processing: n_tokens = 41249, truncated = 0
llama-server | 10982.08.100.676 I slot print_timing: id 1 | task 2776451 | n_gen = 15528, tg = 14.99 t/s, tg_3s = 23.88 t/s
llama-server | 10982.11.190.929 I slot print_timing: id 1 | task 2776451 | n_gen = 15619, tg = 15.03 t/s, tg_3s = 29.45 t/s
llama-server | 10982.14.280.291 I slot print_timing: id 1 | task 2776451 | n_gen = 15712, tg = 15.08 t/s, tg_3s = 30.10 t/s
llama-server | 10982.17.364.347 I slot print_timing: id 1 | task 2776451 | n_gen = 15793, tg = 15.11 t/s, tg_3s = 26.26 t/s
llama-server | 10982.20.453.255 I slot print_timing: id 1 | task 2776451 | n_gen = 15879, tg = 15.15 t/s, tg_3s = 27.84 t/s
llama-server | 10982.23.543.142 I slot print_timing: id 1 | task 2776451 | n_gen = 15968, tg = 15.19 t/s, tg_3s = 28.80 t/s
llama-server | 10982.24.889.430 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 658943606238
llama-server | 10982.24.891.611 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2132.084 MiB)
llama-server | 10982.28.812.191 I slot launch_slot_: id 0 | task 2781051 | processing task, is_child = 0
llama-server | 10982.31.886.645 I slot print_timing: id 1 | task 2776451 | n_gen = 16026, tg = 15.12 t/s, tg_3s = 6.95 t/s
llama-server | 10982.34.910.600 I slot print_timing: id 1 | task 2776451 | n_gen = 16027, tg = 15.08 t/s, tg_3s = 0.33 t/s
llama-server | 10982.34.919.548 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.95 s / 686.67 tokens per second
llama-server | 10982.37.961.543 I slot print_timing: id 1 | task 2776451 | n_gen = 16029, tg = 15.04 t/s, tg_3s = 0.66 t/s
llama-server | 10982.37.970.846 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 6126, progress = 0.15, t = 9.00 s / 680.79 tokens per second
llama-server | 10982.40.989.937 I slot print_timing: id 1 | task 2776451 | n_gen = 16033, tg = 15.00 t/s, tg_3s = 1.32 t/s
llama-server | 10982.40.999.041 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 8168, progress = 0.20, t = 12.03 s / 679.13 tokens per second
llama-server | 10982.44.015.091 I slot print_timing: id 1 | task 2776451 | n_gen = 16038, tg = 14.96 t/s, tg_3s = 1.65 t/s
llama-server | 10982.44.024.068 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 10210, progress = 0.25, t = 15.05 s / 678.30 tokens per second
llama-server | 10982.47.039.605 I slot print_timing: id 1 | task 2776451 | n_gen = 16040, tg = 14.92 t/s, tg_3s = 0.66 t/s
llama-server | 10982.47.048.774 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 12252, progress = 0.30, t = 18.08 s / 677.76 tokens per second
llama-server | 10982.50.065.019 I slot print_timing: id 1 | task 2776451 | n_gen = 16045, tg = 14.89 t/s, tg_3s = 1.65 t/s
llama-server | 10982.50.074.254 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 14294, progress = 0.35, t = 21.10 s / 677.36 tokens per second
llama-server | 10982.53.092.218 I slot print_timing: id 1 | task 2776451 | n_gen = 16047, tg = 14.85 t/s, tg_3s = 0.66 t/s
llama-server | 10982.53.101.398 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 16336, progress = 0.40, t = 24.13 s / 677.01 tokens per second
llama-server | 10982.56.118.024 I slot print_timing: id 1 | task 2776451 | n_gen = 16050, tg = 14.81 t/s, tg_3s = 0.99 t/s
llama-server | 10982.56.126.777 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 18378, progress = 0.45, t = 27.16 s / 676.75 tokens per second
llama-server | 10982.59.145.190 I slot print_timing: id 1 | task 2776451 | n_gen = 16051, tg = 14.77 t/s, tg_3s = 0.33 t/s
llama-server | 10982.59.154.182 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 20420, progress = 0.50, t = 30.18 s / 676.55 tokens per second
llama-server | 10983.02.174.381 I slot print_timing: id 1 | task 2776451 | n_gen = 16053, tg = 14.73 t/s, tg_3s = 0.66 t/s
llama-server | 10983.02.183.239 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 22462, progress = 0.55, t = 33.21 s / 676.36 tokens per second
llama-server | 10983.05.204.106 I slot print_timing: id 1 | task 2776451 | n_gen = 16059, tg = 14.69 t/s, tg_3s = 1.98 t/s
llama-server | 10983.05.213.314 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 24504, progress = 0.60, t = 36.24 s / 676.14 tokens per second
llama-server | 10983.08.234.036 I slot print_timing: id 1 | task 2776451 | n_gen = 16065, tg = 14.66 t/s, tg_3s = 1.98 t/s
llama-server | 10983.08.243.389 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 26546, progress = 0.65, t = 39.27 s / 675.98 tokens per second
llama-server | 10983.11.266.505 I slot print_timing: id 1 | task 2776451 | n_gen = 16069, tg = 14.62 t/s, tg_3s = 1.32 t/s
llama-server | 10983.11.275.224 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 28588, progress = 0.70, t = 42.30 s / 675.79 tokens per second
llama-server | 10983.14.302.407 I slot print_timing: id 1 | task 2776451 | n_gen = 16071, tg = 14.58 t/s, tg_3s = 0.66 t/s
llama-server | 10983.14.311.242 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 30630, progress = 0.75, t = 45.34 s / 675.64 tokens per second
llama-server | 10983.17.336.064 I slot print_timing: id 1 | task 2776451 | n_gen = 16073, tg = 14.54 t/s, tg_3s = 0.66 t/s
llama-server | 10983.17.345.108 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 32672, progress = 0.80, t = 48.37 s / 675.44 tokens per second
llama-server | 10983.20.369.092 I slot print_timing: id 1 | task 2776451 | n_gen = 16078, tg = 14.51 t/s, tg_3s = 1.65 t/s
llama-server | 10983.20.378.265 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 34714, progress = 0.85, t = 51.41 s / 675.30 tokens per second
llama-server | 10983.23.399.475 I slot print_timing: id 1 | task 2776451 | n_gen = 16079, tg = 14.47 t/s, tg_3s = 0.33 t/s
llama-server | 10983.23.408.611 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 36756, progress = 0.90, t = 54.44 s / 675.19 tokens per second
llama-server | 10983.26.432.893 I slot print_timing: id 1 | task 2776451 | n_gen = 16081, tg = 14.43 t/s, tg_3s = 0.66 t/s
llama-server | 10983.26.442.201 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 38798, progress = 0.95, t = 57.47 s / 675.10 tokens per second
llama-server | 10983.29.122.852 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 40503, progress = 0.99, t = 60.17 s / 673.13 tokens per second
llama-server | 10983.30.192.580 I slot print_timing: id 1 | task 2776451 | n_gen = 16087, tg = 14.39 t/s, tg_3s = 1.60 t/s
llama-server | 10983.30.201.729 I slot print_timing: id 0 | task 2781051 | prompt processing, n_tokens = 41015, progress = 1.00, t = 61.33 s / 668.80 tokens per second
llama-server | 10983.33.289.144 I slot print_timing: id 1 | task 2776451 | n_gen = 16193, tg = 14.44 t/s, tg_3s = 34.23 t/s
llama-server | 10983.34.413.939 I slot print_timing: id 0 | task 2781051 | n_gen = 102, tg = 27.08 t/s, tg_3s = 27.35 t/s
llama-server | 10983.36.361.619 I slot print_timing: id 1 | task 2776451 | n_gen = 16281, tg = 14.48 t/s, tg_3s = 28.64 t/s
llama-server | 10983.37.485.692 I slot print_timing: id 0 | task 2781051 | n_gen = 203, tg = 29.70 t/s, tg_3s = 32.88 t/s
llama-server | 10983.39.426.523 I slot print_timing: id 1 | task 2776451 | n_gen = 16356, tg = 14.51 t/s, tg_3s = 24.47 t/s
llama-server | 10983.40.549.580 I slot print_timing: id 0 | task 2781051 | n_gen = 289, tg = 29.19 t/s, tg_3s = 28.07 t/s
llama-server | 10983.42.509.003 I slot print_timing: id 1 | task 2776451 | n_gen = 16464, tg = 14.57 t/s, tg_3s = 35.04 t/s
llama-server | 10983.43.632.097 I slot print_timing: id 0 | task 2781051 | n_gen = 380, tg = 29.27 t/s, tg_3s = 29.52 t/s
llama-server | 10983.45.582.435 I slot print_timing: id 1 | task 2776451 | n_gen = 16595, tg = 14.64 t/s, tg_3s = 42.62 t/s
llama-server | 10983.46.704.647 I slot print_timing: id 0 | task 2781051 | n_gen = 458, tg = 28.53 t/s, tg_3s = 25.39 t/s
llama-server | 10983.48.648.285 I slot print_timing: id 1 | task 2776451 | n_gen = 16697, tg = 14.69 t/s, tg_3s = 33.27 t/s
llama-server | 10983.49.774.429 I slot print_timing: id 0 | task 2781051 | n_gen = 537, tg = 28.08 t/s, tg_3s = 25.73 t/s
llama-server | 10983.51.724.306 I slot print_timing: id 1 | task 2776451 | n_gen = 16784, tg = 14.73 t/s, tg_3s = 28.28 t/s
llama-server | 10983.52.853.933 I slot print_timing: id 0 | task 2781051 | n_gen = 638, tg = 28.73 t/s, tg_3s = 32.80 t/s
llama-server | 10983.54.803.292 I slot print_timing: id 1 | task 2776451 | n_gen = 16901, tg = 14.79 t/s, tg_3s = 38.00 t/s
llama-server | 10983.55.934.792 I slot print_timing: id 0 | task 2781051 | n_gen = 698, tg = 27.60 t/s, tg_3s = 19.48 t/s
llama-server | 10983.57.883.890 I slot print_timing: id 1 | task 2776451 | n_gen = 17019, tg = 14.86 t/s, tg_3s = 38.30 t/s
llama-server | 10983.59.013.498 I slot print_timing: id 0 | task 2781051 | n_gen = 807, tg = 28.45 t/s, tg_3s = 35.40 t/s
llama-server | 10984.00.968.709 I slot print_timing: id 1 | task 2776451 | n_gen = 17136, tg = 14.92 t/s, tg_3s = 37.93 t/s
llama-server | 10984.02.091.999 I slot print_timing: id 0 | task 2781051 | n_gen = 925, tg = 29.42 t/s, tg_3s = 38.33 t/s
llama-server | 10984.04.043.452 I slot print_timing: id 1 | task 2776451 | n_gen = 17258, tg = 14.98 t/s, tg_3s = 39.68 t/s
llama-server | 10984.05.168.347 I slot print_timing: id 0 | task 2781051 | n_gen = 1023, tg = 29.64 t/s, tg_3s = 31.86 t/s
llama-server | 10984.07.126.590 I slot print_timing: id 1 | task 2776451 | n_gen = 17390, tg = 15.06 t/s, tg_3s = 42.81 t/s
llama-server | 10984.08.254.460 I slot print_timing: id 0 | task 2781051 | n_gen = 1139, tg = 30.29 t/s, tg_3s = 37.59 t/s
llama-server | 10984.10.199.671 I slot print_timing: id 1 | task 2776451 | n_gen = 17502, tg = 15.11 t/s, tg_3s = 36.45 t/s
llama-server | 10984.11.327.690 I slot print_timing: id 0 | task 2781051 | n_gen = 1215, tg = 29.87 t/s, tg_3s = 24.73 t/s
llama-server | 10984.13.277.375 I slot print_timing: id 1 | task 2776451 | n_gen = 17615, tg = 15.17 t/s, tg_3s = 36.72 t/s
llama-server | 10984.14.400.086 I slot print_timing: id 0 | task 2781051 | n_gen = 1289, tg = 29.46 t/s, tg_3s = 24.09 t/s
llama-server | 10984.16.351.017 I slot print_timing: id 1 | task 2776451 | n_gen = 17741, tg = 15.24 t/s, tg_3s = 40.99 t/s
llama-server | 10984.17.480.725 I slot print_timing: id 0 | task 2781051 | n_gen = 1379, tg = 29.45 t/s, tg_3s = 29.21 t/s
llama-server | 10984.19.436.420 I slot print_timing: id 1 | task 2776451 | n_gen = 17878, tg = 15.32 t/s, tg_3s = 44.40 t/s
llama-server | 10984.20.560.560 I slot print_timing: id 0 | task 2781051 | n_gen = 1453, tg = 29.11 t/s, tg_3s = 24.03 t/s
llama-server | 10984.22.507.069 I slot print_timing: id 1 | task 2776451 | n_gen = 17990, tg = 15.37 t/s, tg_3s = 36.47 t/s
llama-server | 10984.23.634.723 I slot print_timing: id 0 | task 2781051 | n_gen = 1539, tg = 29.05 t/s, tg_3s = 27.98 t/s
llama-server | 10984.25.583.717 I slot print_timing: id 1 | task 2776451 | n_gen = 18108, tg = 15.43 t/s, tg_3s = 38.35 t/s
llama-server | 10984.26.303.301 I slot print_timing: id 0 | task 2781051 | prompt eval time = 61860.96 ms / 41019 tokens ( 1.51 ms per token, 663.08 tokens per second)
llama-server | 10984.26.303.304 I slot print_timing: id 0 | task 2781051 | eval time = 55618.78 ms / 1626 tokens ( 34.23 ms per token, 29.22 tokens per second)
llama-server | 10984.26.303.305 I slot print_timing: id 0 | task 2781051 | total time = 117479.75 ms / 42645 tokens
llama-server | 10984.26.303.306 I slot print_timing: id 0 | task 2781051 | graphs reused = 2693939
llama-server | 10984.26.303.309 I slot print_timing: id 0 | task 2781051 | draft acceptance = 0.39963 ( 1083 accepted / 2710 generated), mean len = 3.00
llama-server | 10984.26.304.575 I slot release: id 0 | task 2781051 | stop processing: n_tokens = 42644, truncated = 0
llama-server | 10984.27.677.852 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 659082144627
llama-server | 10984.27.680.119 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2149.739 MiB)
llama-server | 10984.32.651.867 I slot launch_slot_: id 0 | task 2781629 | processing task, is_child = 0
llama-server | 10984.35.728.628 I slot print_timing: id 1 | task 2776451 | n_gen = 18201, tg = 15.38 t/s, tg_3s = 9.17 t/s
llama-server | 10984.38.756.071 I slot print_timing: id 1 | task 2776451 | n_gen = 18207, tg = 15.34 t/s, tg_3s = 1.98 t/s
llama-server | 10984.38.764.889 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.95 s / 686.74 tokens per second
llama-server | 10984.41.807.450 I slot print_timing: id 1 | task 2776451 | n_gen = 18211, tg = 15.31 t/s, tg_3s = 1.31 t/s
llama-server | 10984.41.816.239 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 6126, progress = 0.15, t = 9.00 s / 680.63 tokens per second
llama-server | 10984.44.835.488 I slot print_timing: id 1 | task 2776451 | n_gen = 18213, tg = 15.27 t/s, tg_3s = 0.66 t/s
llama-server | 10984.44.844.263 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 8168, progress = 0.20, t = 12.03 s / 679.06 tokens per second
llama-server | 10984.47.871.492 I slot print_timing: id 1 | task 2776451 | n_gen = 18219, tg = 15.24 t/s, tg_3s = 1.98 t/s
llama-server | 10984.47.880.521 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 10210, progress = 0.25, t = 15.06 s / 678.09 tokens per second
llama-server | 10984.50.904.285 I slot print_timing: id 1 | task 2776451 | n_gen = 18225, tg = 15.20 t/s, tg_3s = 1.98 t/s
llama-server | 10984.50.913.164 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 12252, progress = 0.30, t = 18.10 s / 677.01 tokens per second
llama-server | 10984.53.939.554 I slot print_timing: id 1 | task 2776451 | n_gen = 18231, tg = 15.17 t/s, tg_3s = 1.98 t/s
llama-server | 10984.53.948.369 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 14294, progress = 0.35, t = 21.13 s / 676.52 tokens per second
llama-server | 10984.56.972.874 I slot print_timing: id 1 | task 2776451 | n_gen = 18237, tg = 15.14 t/s, tg_3s = 1.98 t/s
llama-server | 10984.56.981.575 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 16336, progress = 0.40, t = 24.16 s / 676.03 tokens per second
llama-server | 10985.00.007.909 I slot print_timing: id 1 | task 2776451 | n_gen = 18242, tg = 15.10 t/s, tg_3s = 1.65 t/s
llama-server | 10985.00.016.727 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 18378, progress = 0.45, t = 27.20 s / 675.69 tokens per second
llama-server | 10985.03.041.462 I slot print_timing: id 1 | task 2776451 | n_gen = 18245, tg = 15.07 t/s, tg_3s = 0.99 t/s
llama-server | 10985.03.050.817 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 20420, progress = 0.50, t = 30.23 s / 675.41 tokens per second
llama-server | 10985.06.076.312 I slot print_timing: id 1 | task 2776451 | n_gen = 18251, tg = 15.04 t/s, tg_3s = 1.98 t/s
llama-server | 10985.06.085.556 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 22462, progress = 0.55, t = 33.27 s / 675.17 tokens per second
llama-server | 10985.09.112.862 I slot print_timing: id 1 | task 2776451 | n_gen = 18257, tg = 15.00 t/s, tg_3s = 1.98 t/s
llama-server | 10985.09.121.759 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 24504, progress = 0.60, t = 36.30 s / 674.98 tokens per second
llama-server | 10985.12.145.171 I slot print_timing: id 1 | task 2776451 | n_gen = 18263, tg = 14.97 t/s, tg_3s = 1.98 t/s
llama-server | 10985.12.154.024 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 26546, progress = 0.65, t = 39.34 s / 674.81 tokens per second
llama-server | 10985.15.179.107 I slot print_timing: id 1 | task 2776451 | n_gen = 18269, tg = 14.94 t/s, tg_3s = 1.98 t/s
llama-server | 10985.15.188.029 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 28588, progress = 0.70, t = 42.37 s / 674.69 tokens per second
llama-server | 10985.18.213.578 I slot print_timing: id 1 | task 2776451 | n_gen = 18275, tg = 14.91 t/s, tg_3s = 1.98 t/s
llama-server | 10985.18.222.413 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 30630, progress = 0.75, t = 45.41 s / 674.57 tokens per second
llama-server | 10985.21.248.449 I slot print_timing: id 1 | task 2776451 | n_gen = 18277, tg = 14.87 t/s, tg_3s = 0.66 t/s
llama-server | 10985.21.257.145 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 32672, progress = 0.80, t = 48.44 s / 674.46 tokens per second
llama-server | 10985.24.285.381 I slot print_timing: id 1 | task 2776451 | n_gen = 18283, tg = 14.84 t/s, tg_3s = 1.98 t/s
llama-server | 10985.24.294.182 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 34714, progress = 0.85, t = 51.48 s / 674.35 tokens per second
llama-server | 10985.27.322.540 I slot print_timing: id 1 | task 2776451 | n_gen = 18289, tg = 14.81 t/s, tg_3s = 1.98 t/s
llama-server | 10985.27.331.323 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 36756, progress = 0.90, t = 54.51 s / 674.24 tokens per second
llama-server | 10985.30.362.338 I slot print_timing: id 1 | task 2776451 | n_gen = 18295, tg = 14.78 t/s, tg_3s = 1.97 t/s
llama-server | 10985.30.371.216 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 38798, progress = 0.95, t = 57.55 s / 674.11 tokens per second
llama-server | 10985.32.913.298 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 40432, progress = 0.99, t = 60.12 s / 672.48 tokens per second
llama-server | 10985.34.108.352 I slot print_timing: id 1 | task 2776451 | n_gen = 18307, tg = 14.74 t/s, tg_3s = 3.20 t/s
llama-server | 10985.34.117.442 I slot print_timing: id 0 | task 2781629 | prompt processing, n_tokens = 40944, progress = 1.00, t = 61.40 s / 666.87 tokens per second
llama-server | 10985.37.135.173 I slot print_timing: id 1 | task 2776451 | n_gen = 18414, tg = 14.79 t/s, tg_3s = 35.35 t/s
llama-server | 10985.38.463.260 I slot print_timing: id 0 | task 2781629 | n_gen = 101, tg = 26.18 t/s, tg_3s = 26.44 t/s
llama-server | 10985.40.204.378 I slot print_timing: id 1 | task 2776451 | n_gen = 18557, tg = 14.87 t/s, tg_3s = 46.59 t/s
llama-server | 10985.41.534.934 I slot print_timing: id 0 | task 2781629 | n_gen = 192, tg = 27.71 t/s, tg_3s = 29.63 t/s
llama-server | 10985.43.277.239 I slot print_timing: id 1 | task 2776451 | n_gen = 18720, tg = 14.96 t/s, tg_3s = 53.04 t/s
llama-server | 10985.44.608.240 I slot print_timing: id 0 | task 2781629 | n_gen = 279, tg = 27.90 t/s, tg_3s = 28.31 t/s
llama-server | 10985.46.364.197 I slot print_timing: id 1 | task 2776451 | n_gen = 18867, tg = 15.04 t/s, tg_3s = 47.62 t/s
llama-server | 10985.47.693.038 I slot print_timing: id 0 | task 2781629 | n_gen = 372, tg = 28.43 t/s, tg_3s = 30.15 t/s
llama-server | 10985.49.431.028 I slot print_timing: id 1 | task 2776451 | n_gen = 18962, tg = 15.08 t/s, tg_3s = 30.98 t/s
llama-server | 10985.50.763.822 I slot print_timing: id 0 | task 2781629 | n_gen = 447, tg = 27.67 t/s, tg_3s = 24.42 t/s
llama-server | 10985.52.302.515 W srv stop: cancel task, id_task = 2776451
llama-server | 10985.52.405.397 I slot release: id 1 | task 2776451 | stop processing: n_tokens = 26763, truncated = 0
llama-server | 10985.53.458.089 I slot print_timing: id 0 | task 2781629 | prompt eval time = 61979.39 ms / 40948 tokens ( 1.51 ms per token, 660.67 tokens per second)
llama-server | 10985.53.458.093 I slot print_timing: id 0 | task 2781629 | eval time = 18814.90 ms / 541 tokens ( 34.84 ms per token, 28.70 tokens per second)
llama-server | 10985.53.458.093 I slot print_timing: id 0 | task 2781629 | total time = 80794.29 ms / 41489 tokens
llama-server | 10985.53.458.094 I slot print_timing: id 0 | task 2781629 | graphs reused = 2694172
llama-server | 10985.53.458.097 I slot print_timing: id 0 | task 2781629 | draft acceptance = 0.39016 ( 357 accepted / 915 generated), mean len = 2.95
llama-server | 10985.53.459.222 I slot release: id 0 | task 2781629 | stop processing: n_tokens = 41488, truncated = 0
llama-server | 10985.54.637.773 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659168245449
llama-server | 10985.59.108.039 I slot launch_slot_: id 1 | task 2781836 | processing task, is_child = 0
llama-server | 10985.59.110.305 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2176.205 MiB)
llama-server | 10986.03.218.404 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 659169299274
llama-server | 10986.03.662.793 I slot launch_slot_: id 0 | task 2781837 | processing task, is_child = 0
llama-server | 10986.08.217.496 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 4086, progress = 0.10, t = 3.87 s / 1055.72 tokens per second
llama-server | 10986.10.232.729 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 6128, progress = 0.15, t = 5.88 s / 1042.46 tokens per second
llama-server | 10986.12.279.662 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 8170, progress = 0.20, t = 7.93 s / 1030.13 tokens per second
llama-server | 10986.14.367.371 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 10212, progress = 0.25, t = 10.02 s / 1019.20 tokens per second
llama-server | 10986.16.495.481 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 12254, progress = 0.30, t = 12.15 s / 1008.68 tokens per second
llama-server | 10986.18.662.117 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 14296, progress = 0.35, t = 14.32 s / 998.66 tokens per second
llama-server | 10986.20.868.257 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 16338, progress = 0.40, t = 16.52 s / 989.01 tokens per second
llama-server | 10986.23.136.423 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 18380, progress = 0.45, t = 18.79 s / 978.24 tokens per second
llama-server | 10986.25.428.919 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 20422, progress = 0.50, t = 21.08 s / 968.66 tokens per second
llama-server | 10986.27.759.787 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 22464, progress = 0.55, t = 23.41 s / 959.45 tokens per second
llama-server | 10986.30.124.484 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 24506, progress = 0.60, t = 25.78 s / 950.64 tokens per second
llama-server | 10986.32.564.345 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 26548, progress = 0.65, t = 28.22 s / 940.87 tokens per second
llama-server | 10986.35.005.091 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 28590, progress = 0.70, t = 30.66 s / 932.55 tokens per second
llama-server | 10986.37.484.970 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 30632, progress = 0.75, t = 33.14 s / 924.41 tokens per second
llama-server | 10986.39.996.389 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 32674, progress = 0.80, t = 35.65 s / 916.52 tokens per second
llama-server | 10986.42.566.623 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 34716, progress = 0.85, t = 38.22 s / 908.40 tokens per second
llama-server | 10986.45.153.866 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 36758, progress = 0.90, t = 40.81 s / 900.78 tokens per second
llama-server | 10986.47.777.400 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 38800, progress = 0.95, t = 43.43 s / 893.38 tokens per second
llama-server | 10986.50.117.898 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 40530, progress = 0.99, t = 45.79 s / 885.15 tokens per second
llama-server | 10986.51.214.801 I slot print_timing: id 1 | task 2781836 | prompt processing, n_tokens = 41042, progress = 1.00, t = 46.97 s / 873.86 tokens per second
llama-server | 10986.52.877.875 I slot print_timing: id 0 | task 2781837 | n_gen = 102, tg = 2.17 t/s, tg_3s = 2.19 t/s
llama-server | 10986.53.452.057 I slot print_timing: id 1 | task 2781836 | prompt eval time = 47478.18 ms / 41046 tokens ( 1.16 ms per token, 864.52 tokens per second)
llama-server | 10986.53.452.061 I slot print_timing: id 1 | task 2781836 | eval time = 1775.10 ms / 83 tokens ( 21.65 ms per token, 46.19 tokens per second)
llama-server | 10986.53.452.061 I slot print_timing: id 1 | task 2781836 | total time = 49253.28 ms / 41129 tokens
llama-server | 10986.53.452.062 I slot print_timing: id 1 | task 2781836 | graphs reused = 2694190
llama-server | 10986.53.452.066 I slot print_timing: id 1 | task 2781836 | draft acceptance = 0.67368 ( 64 accepted / 95 generated), mean len = 4.37
llama-server | 10986.53.453.209 I slot release: id 1 | task 2781836 | stop processing: n_tokens = 41129, truncated = 0
llama-server | 10986.54.680.093 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659229293260
llama-server | 10986.56.251.976 I slot launch_slot_: id 1 | task 2781892 | processing task, is_child = 0
llama-server | 10986.59.105.147 I slot print_timing: id 0 | task 2781837 | n_gen = 214, tg = 4.03 t/s, tg_3s = 17.99 t/s
llama-server | 10987.01.920.413 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.51 s / 741.31 tokens per second
llama-server | 10987.04.740.413 I slot print_timing: id 0 | task 2781837 | n_gen = 226, tg = 3.85 t/s, tg_3s = 2.13 t/s
llama-server | 10987.04.750.056 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.34 s / 734.78 tokens per second
llama-server | 10987.07.553.544 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.14 s / 732.97 tokens per second
llama-server | 10987.10.355.522 I slot print_timing: id 0 | task 2781837 | n_gen = 231, tg = 3.59 t/s, tg_3s = 0.89 t/s
llama-server | 10987.10.365.827 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 10210, progress = 0.25, t = 13.95 s / 731.81 tokens per second
llama-server | 10987.13.174.897 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.76 s / 730.96 tokens per second
llama-server | 10987.15.974.642 I slot print_timing: id 0 | task 2781837 | n_gen = 234, tg = 3.34 t/s, tg_3s = 0.53 t/s
llama-server | 10987.15.984.992 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.57 s / 730.24 tokens per second
llama-server | 10987.18.794.449 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.38 s / 729.83 tokens per second
llama-server | 10987.21.594.109 I slot print_timing: id 0 | task 2781837 | n_gen = 237, tg = 3.13 t/s, tg_3s = 0.53 t/s
llama-server | 10987.21.604.277 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.19 s / 729.47 tokens per second
llama-server | 10987.24.423.770 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 20420, progress = 0.50, t = 28.01 s / 729.15 tokens per second
llama-server | 10987.27.226.933 I slot print_timing: id 0 | task 2781837 | n_gen = 242, tg = 2.98 t/s, tg_3s = 0.89 t/s
llama-server | 10987.27.237.515 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 22462, progress = 0.55, t = 30.83 s / 728.68 tokens per second
llama-server | 10987.30.051.215 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 24504, progress = 0.60, t = 33.64 s / 728.40 tokens per second
llama-server | 10987.32.853.487 I slot print_timing: id 0 | task 2781837 | n_gen = 244, tg = 2.81 t/s, tg_3s = 0.36 t/s
llama-server | 10987.32.864.185 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 26546, progress = 0.65, t = 36.45 s / 728.21 tokens per second
llama-server | 10987.35.679.457 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 28588, progress = 0.70, t = 39.27 s / 728.03 tokens per second
llama-server | 10987.38.484.824 I slot print_timing: id 0 | task 2781837 | n_gen = 247, tg = 2.67 t/s, tg_3s = 0.53 t/s
llama-server | 10987.38.495.168 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 30630, progress = 0.75, t = 42.08 s / 727.83 tokens per second
llama-server | 10987.41.312.614 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 32672, progress = 0.80, t = 44.90 s / 727.67 tokens per second
llama-server | 10987.44.119.513 I slot print_timing: id 0 | task 2781837 | n_gen = 253, tg = 2.57 t/s, tg_3s = 1.06 t/s
llama-server | 10987.44.129.756 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 34714, progress = 0.85, t = 47.72 s / 727.46 tokens per second
llama-server | 10987.46.947.075 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 36756, progress = 0.90, t = 50.54 s / 727.32 tokens per second
llama-server | 10987.49.752.353 I slot print_timing: id 0 | task 2781837 | n_gen = 261, tg = 2.51 t/s, tg_3s = 1.42 t/s
llama-server | 10987.49.762.965 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 38798, progress = 0.95, t = 53.35 s / 727.20 tokens per second
llama-server | 10987.51.683.345 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 40136, progress = 0.99, t = 55.32 s / 725.57 tokens per second
llama-server | 10987.52.760.775 I slot print_timing: id 1 | task 2781892 | prompt processing, n_tokens = 40648, progress = 1.00, t = 56.45 s / 720.11 tokens per second
llama-server | 10987.53.290.633 I slot print_timing: id 0 | task 2781837 | n_gen = 275, tg = 2.56 t/s, tg_3s = 3.96 t/s
llama-server | 10987.56.321.339 I slot print_timing: id 0 | task 2781837 | n_gen = 363, tg = 3.29 t/s, tg_3s = 29.04 t/s
llama-server | 10987.56.322.155 I slot print_timing: id 1 | task 2781892 | n_gen = 103, tg = 33.63 t/s, tg_3s = 33.96 t/s
llama-server | 10987.58.406.817 I slot print_timing: id 1 | task 2781892 | prompt eval time = 57025.20 ms / 40652 tokens ( 1.40 ms per token, 712.88 tokens per second)
llama-server | 10987.58.406.820 I slot print_timing: id 1 | task 2781892 | eval time = 5117.65 ms / 200 tokens ( 25.72 ms per token, 38.88 tokens per second)
llama-server | 10987.58.406.821 I slot print_timing: id 1 | task 2781892 | total time = 62142.85 ms / 40852 tokens
llama-server | 10987.58.406.821 I slot print_timing: id 1 | task 2781892 | graphs reused = 2694296
llama-server | 10987.58.406.824 I slot print_timing: id 1 | task 2781892 | draft acceptance = 0.51429 ( 144 accepted / 280 generated), mean len = 3.57
llama-server | 10987.58.407.946 I slot release: id 1 | task 2781892 | stop processing: n_tokens = 40852, truncated = 0
llama-server | 10987.59.352.809 I slot print_timing: id 0 | task 2781837 | n_gen = 478, tg = 4.22 t/s, tg_3s = 37.94 t/s
llama-server | 10987.59.538.879 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659294247998
llama-server | 10987.59.540.891 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1940.504 MiB)
llama-server | 10988.01.925.866 I slot launch_slot_: id 1 | task 2781983 | processing task, is_child = 0
llama-server | 10988.04.775.002 I slot print_timing: id 0 | task 2781837 | n_gen = 488, tg = 4.11 t/s, tg_3s = 1.84 t/s
llama-server | 10988.07.591.499 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.51 s / 741.73 tokens per second
llama-server | 10988.10.409.774 I slot print_timing: id 0 | task 2781837 | n_gen = 492, tg = 3.95 t/s, tg_3s = 0.71 t/s
llama-server | 10988.10.419.929 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.33 s / 735.17 tokens per second
llama-server | 10988.13.223.376 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.14 s / 733.20 tokens per second
llama-server | 10988.16.019.265 I slot print_timing: id 0 | task 2781837 | n_gen = 500, tg = 3.84 t/s, tg_3s = 1.43 t/s
llama-server | 10988.16.029.407 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 10210, progress = 0.25, t = 13.95 s / 732.10 tokens per second
llama-server | 10988.18.836.079 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.75 s / 731.39 tokens per second
llama-server | 10988.21.630.762 I slot print_timing: id 0 | task 2781837 | n_gen = 505, tg = 3.72 t/s, tg_3s = 0.89 t/s
llama-server | 10988.21.641.168 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.56 s / 730.85 tokens per second
llama-server | 10988.24.449.906 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.37 s / 730.41 tokens per second
llama-server | 10988.27.251.947 I slot print_timing: id 0 | task 2781837 | n_gen = 511, tg = 3.62 t/s, tg_3s = 1.07 t/s
llama-server | 10988.27.262.145 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.18 s / 729.90 tokens per second
llama-server | 10988.30.072.270 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 20420, progress = 0.51, t = 27.99 s / 729.56 tokens per second
llama-server | 10988.32.873.519 I slot print_timing: id 0 | task 2781837 | n_gen = 519, tg = 3.53 t/s, tg_3s = 1.42 t/s
llama-server | 10988.32.883.772 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 22462, progress = 0.56, t = 30.80 s / 729.28 tokens per second
llama-server | 10988.35.695.196 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 24504, progress = 0.61, t = 33.61 s / 729.03 tokens per second
llama-server | 10988.38.500.000 I slot print_timing: id 0 | task 2781837 | n_gen = 527, tg = 3.45 t/s, tg_3s = 1.42 t/s
llama-server | 10988.38.510.260 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 26546, progress = 0.66, t = 36.43 s / 728.77 tokens per second
llama-server | 10988.41.327.389 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 28588, progress = 0.71, t = 39.24 s / 728.50 tokens per second
llama-server | 10988.44.128.648 I slot print_timing: id 0 | task 2781837 | n_gen = 529, tg = 3.34 t/s, tg_3s = 0.36 t/s
llama-server | 10988.44.139.228 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 30630, progress = 0.76, t = 42.06 s / 728.32 tokens per second
llama-server | 10988.46.954.327 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 32672, progress = 0.81, t = 44.87 s / 728.15 tokens per second
llama-server | 10988.49.759.134 I slot print_timing: id 0 | task 2781837 | n_gen = 536, tg = 3.27 t/s, tg_3s = 1.24 t/s
llama-server | 10988.49.768.624 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 34714, progress = 0.86, t = 47.68 s / 728.01 tokens per second
llama-server | 10988.52.584.133 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 36756, progress = 0.91, t = 50.50 s / 727.82 tokens per second
llama-server | 10988.55.390.154 I slot print_timing: id 0 | task 2781837 | n_gen = 548, tg = 3.23 t/s, tg_3s = 2.13 t/s
llama-server | 10988.55.399.565 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 38798, progress = 0.96, t = 53.32 s / 727.69 tokens per second
llama-server | 10988.57.066.590 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 39911, progress = 0.99, t = 55.04 s / 725.10 tokens per second
llama-server | 10988.58.137.209 I slot print_timing: id 1 | task 2781983 | prompt processing, n_tokens = 40423, progress = 1.00, t = 56.15 s / 719.91 tokens per second
llama-server | 10988.58.599.754 I slot print_timing: id 0 | task 2781837 | n_gen = 563, tg = 3.26 t/s, tg_3s = 4.67 t/s
llama-server | 10989.01.627.444 I slot print_timing: id 0 | task 2781837 | n_gen = 662, tg = 3.77 t/s, tg_3s = 32.70 t/s
llama-server | 10989.01.720.110 I slot print_timing: id 1 | task 2781983 | n_gen = 103, tg = 32.67 t/s, tg_3s = 32.99 t/s
llama-server | 10989.02.450.166 I slot print_timing: id 1 | task 2781983 | prompt eval time = 56661.05 ms / 40427 tokens ( 1.40 ms per token, 713.49 tokens per second)
llama-server | 10989.02.450.169 I slot print_timing: id 1 | task 2781983 | eval time = 3851.75 ms / 137 tokens ( 28.32 ms per token, 35.31 tokens per second)
llama-server | 10989.02.450.169 I slot print_timing: id 1 | task 2781983 | total time = 60512.81 ms / 40564 tokens
llama-server | 10989.02.450.170 I slot print_timing: id 1 | task 2781983 | graphs reused = 2694387
llama-server | 10989.02.450.173 I slot print_timing: id 1 | task 2781983 | draft acceptance = 0.45238 ( 95 accepted / 210 generated), mean len = 3.26
llama-server | 10989.02.451.412 I slot release: id 1 | task 2781983 | stop processing: n_tokens = 40564, truncated = 0
llama-server | 10989.03.591.686 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659358291464
llama-server | 10989.03.593.715 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1986.886 MiB)
llama-server | 10989.05.709.366 I slot launch_slot_: id 1 | task 2782060 | processing task, is_child = 0
llama-server | 10989.08.560.561 I slot print_timing: id 0 | task 2781837 | n_gen = 750, tg = 4.11 t/s, tg_3s = 12.69 t/s
llama-server | 10989.11.378.586 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.51 s / 741.42 tokens per second
llama-server | 10989.14.195.414 I slot print_timing: id 0 | task 2781837 | n_gen = 755, tg = 4.01 t/s, tg_3s = 0.89 t/s
llama-server | 10989.14.205.414 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.34 s / 734.71 tokens per second
llama-server | 10989.17.010.560 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.14 s / 732.97 tokens per second
llama-server | 10989.19.809.532 I slot print_timing: id 0 | task 2781837 | n_gen = 758, tg = 3.91 t/s, tg_3s = 0.53 t/s
llama-server | 10989.19.819.936 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 10210, progress = 0.25, t = 13.95 s / 731.72 tokens per second
llama-server | 10989.22.627.758 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.76 s / 731.00 tokens per second
llama-server | 10989.25.428.441 I slot print_timing: id 0 | task 2781837 | n_gen = 762, tg = 3.82 t/s, tg_3s = 0.71 t/s
llama-server | 10989.25.438.511 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.57 s / 730.33 tokens per second
llama-server | 10989.28.247.863 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.38 s / 729.92 tokens per second
llama-server | 10989.31.045.351 I slot print_timing: id 0 | task 2781837 | n_gen = 771, tg = 3.76 t/s, tg_3s = 1.60 t/s
llama-server | 10989.31.055.397 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.19 s / 729.62 tokens per second
llama-server | 10989.33.863.991 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 20420, progress = 0.51, t = 28.00 s / 729.38 tokens per second
llama-server | 10989.36.666.619 I slot print_timing: id 0 | task 2781837 | n_gen = 774, tg = 3.67 t/s, tg_3s = 0.53 t/s
llama-server | 10989.36.676.848 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 22462, progress = 0.56, t = 30.81 s / 729.04 tokens per second
llama-server | 10989.39.492.999 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 24504, progress = 0.61, t = 33.62 s / 728.85 tokens per second
llama-server | 10989.42.293.285 I slot print_timing: id 0 | task 2781837 | n_gen = 779, tg = 3.60 t/s, tg_3s = 0.89 t/s
llama-server | 10989.42.303.704 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 26546, progress = 0.66, t = 36.44 s / 728.54 tokens per second
llama-server | 10989.45.117.371 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 28588, progress = 0.71, t = 39.25 s / 728.34 tokens per second
llama-server | 10989.47.920.125 I slot print_timing: id 0 | task 2781837 | n_gen = 791, tg = 3.56 t/s, tg_3s = 2.13 t/s
llama-server | 10989.47.929.738 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 30630, progress = 0.76, t = 42.06 s / 728.20 tokens per second
llama-server | 10989.50.746.283 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 32672, progress = 0.81, t = 44.88 s / 728.04 tokens per second
llama-server | 10989.53.553.992 I slot print_timing: id 0 | task 2781837 | n_gen = 803, tg = 3.53 t/s, tg_3s = 2.13 t/s
llama-server | 10989.53.563.943 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 34714, progress = 0.86, t = 47.70 s / 727.83 tokens per second
llama-server | 10989.56.379.880 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 36756, progress = 0.91, t = 50.51 s / 727.66 tokens per second
llama-server | 10989.59.186.433 I slot print_timing: id 0 | task 2781837 | n_gen = 813, tg = 3.49 t/s, tg_3s = 1.78 t/s
llama-server | 10989.59.196.372 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 38798, progress = 0.96, t = 53.33 s / 727.52 tokens per second
llama-server | 10990.00.853.238 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 39908, progress = 0.99, t = 55.05 s / 725.01 tokens per second
llama-server | 10990.01.897.081 I slot print_timing: id 1 | task 2782060 | prompt processing, n_tokens = 40420, progress = 1.00, t = 56.13 s / 720.16 tokens per second
llama-server | 10990.02.347.734 I slot print_timing: id 0 | task 2781837 | n_gen = 824, tg = 3.49 t/s, tg_3s = 3.48 t/s
llama-server | 10990.05.381.864 I slot print_timing: id 0 | task 2781837 | n_gen = 933, tg = 3.90 t/s, tg_3s = 35.92 t/s
llama-server | 10990.05.679.047 I slot print_timing: id 1 | task 2782060 | n_gen = 105, tg = 31.21 t/s, tg_3s = 31.50 t/s
llama-server | 10990.06.226.719 I slot print_timing: id 1 | task 2782060 | prompt eval time = 56625.48 ms / 40424 tokens ( 1.40 ms per token, 713.88 tokens per second)
llama-server | 10990.06.226.723 I slot print_timing: id 1 | task 2782060 | eval time = 3880.42 ms / 137 tokens ( 28.53 ms per token, 35.05 tokens per second)
llama-server | 10990.06.226.723 I slot print_timing: id 1 | task 2782060 | total time = 60505.90 ms / 40561 tokens
llama-server | 10990.06.226.724 I slot print_timing: id 1 | task 2782060 | graphs reused = 2694477
llama-server | 10990.06.226.727 I slot print_timing: id 1 | task 2782060 | draft acceptance = 0.44762 ( 94 accepted / 210 generated), mean len = 3.24
llama-server | 10990.06.227.989 I slot release: id 1 | task 2782060 | stop processing: n_tokens = 40560, truncated = 0
llama-server | 10990.07.267.605 I slot get_availabl: id 1 | task -1 | selected slot by LCP similarity, f_sim_best = 0.997 (> 0.100 thold), f_keep = 0.997
llama-server | 10990.07.268.196 I slot launch_slot_: id 1 | task 2782136 | processing task, is_child = 0
llama-server | 10990.08.426.239 I slot print_timing: id 0 | task 2781837 | n_gen = 1009, tg = 4.16 t/s, tg_3s = 24.96 t/s
llama-server | 10990.11.269.423 I slot print_timing: id 1 | task 2782136 | n_gen = 116, tg = 37.57 t/s, tg_3s = 37.89 t/s
llama-server | 10990.11.360.496 I slot print_timing: id 1 | task 2782136 | prompt eval time = 931.41 ms / 115 tokens ( 8.10 ms per token, 123.47 tokens per second)
llama-server | 10990.11.360.499 I slot print_timing: id 1 | task 2782136 | eval time = 3152.22 ms / 120 tokens ( 26.49 ms per token, 37.75 tokens per second)
llama-server | 10990.11.360.500 I slot print_timing: id 1 | task 2782136 | total time = 4083.64 ms / 235 tokens
llama-server | 10990.11.360.501 I slot print_timing: id 1 | task 2782136 | graphs reused = 2694519
llama-server | 10990.11.360.503 I slot print_timing: id 1 | task 2782136 | draft acceptance = 0.50000 ( 85 accepted / 170 generated), mean len = 3.50
llama-server | 10990.11.361.628 I slot release: id 1 | task 2782136 | stop processing: n_tokens = 40654, truncated = 0
llama-server | 10990.11.456.463 I slot print_timing: id 0 | task 2781837 | n_gen = 1115, tg = 4.54 t/s, tg_3s = 34.98 t/s
llama-server | 10990.12.401.028 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659427201680
llama-server | 10990.12.403.068 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1948.450 MiB)
llama-server | 10990.14.057.334 I slot launch_slot_: id 1 | task 2782184 | processing task, is_child = 0
llama-server | 10990.16.797.635 I slot print_timing: id 0 | task 2781837 | n_gen = 1141, tg = 4.55 t/s, tg_3s = 4.87 t/s
llama-server | 10990.19.496.582 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.28 s / 773.44 tokens per second
llama-server | 10990.22.198.918 I slot print_timing: id 0 | task 2781837 | n_gen = 1148, tg = 4.48 t/s, tg_3s = 1.30 t/s
llama-server | 10990.22.208.989 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 6126, progress = 0.15, t = 7.99 s / 766.32 tokens per second
llama-server | 10990.24.896.684 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 8168, progress = 0.20, t = 10.68 s / 764.64 tokens per second
llama-server | 10990.27.577.842 I slot print_timing: id 0 | task 2781837 | n_gen = 1153, tg = 4.41 t/s, tg_3s = 0.93 t/s
llama-server | 10990.27.587.780 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 10210, progress = 0.25, t = 13.37 s / 763.52 tokens per second
llama-server | 10990.30.279.376 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.06 s / 762.66 tokens per second
llama-server | 10990.32.964.234 I slot print_timing: id 0 | task 2781837 | n_gen = 1158, tg = 4.34 t/s, tg_3s = 0.93 t/s
llama-server | 10990.32.974.466 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 14294, progress = 0.35, t = 18.76 s / 761.97 tokens per second
llama-server | 10990.35.668.408 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 16336, progress = 0.40, t = 21.45 s / 761.50 tokens per second
llama-server | 10990.38.354.983 I slot print_timing: id 0 | task 2781837 | n_gen = 1166, tg = 4.28 t/s, tg_3s = 1.48 t/s
llama-server | 10990.38.365.067 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 18378, progress = 0.45, t = 24.15 s / 761.00 tokens per second
llama-server | 10990.41.059.638 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 20420, progress = 0.51, t = 26.84 s / 760.68 tokens per second
llama-server | 10990.43.742.039 I slot print_timing: id 0 | task 2781837 | n_gen = 1169, tg = 4.21 t/s, tg_3s = 0.56 t/s
llama-server | 10990.43.752.326 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 22462, progress = 0.56, t = 29.54 s / 760.44 tokens per second
llama-server | 10990.46.446.820 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 24504, progress = 0.61, t = 32.23 s / 760.24 tokens per second
llama-server | 10990.49.132.406 I slot print_timing: id 0 | task 2781837 | n_gen = 1175, tg = 4.15 t/s, tg_3s = 1.11 t/s
llama-server | 10990.49.142.565 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 26546, progress = 0.66, t = 34.93 s / 760.02 tokens per second
llama-server | 10990.51.836.841 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 28588, progress = 0.71, t = 37.62 s / 759.86 tokens per second
llama-server | 10990.54.527.294 I slot print_timing: id 0 | task 2781837 | n_gen = 1183, tg = 4.10 t/s, tg_3s = 1.48 t/s
llama-server | 10990.54.537.154 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 30630, progress = 0.76, t = 40.32 s / 759.63 tokens per second
llama-server | 10990.57.234.324 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 32672, progress = 0.81, t = 43.02 s / 759.48 tokens per second
llama-server | 10990.59.924.176 I slot print_timing: id 0 | task 2781837 | n_gen = 1191, tg = 4.05 t/s, tg_3s = 1.48 t/s
llama-server | 10990.59.934.431 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 34714, progress = 0.86, t = 45.72 s / 759.30 tokens per second
llama-server | 10991.02.632.046 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 36756, progress = 0.91, t = 48.42 s / 759.17 tokens per second
llama-server | 10991.05.319.008 I slot print_timing: id 0 | task 2781837 | n_gen = 1199, tg = 4.01 t/s, tg_3s = 1.48 t/s
llama-server | 10991.05.329.413 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 38798, progress = 0.96, t = 51.11 s / 759.06 tokens per second
llama-server | 10991.06.936.729 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 39911, progress = 0.99, t = 52.78 s / 756.19 tokens per second
llama-server | 10991.07.915.323 I slot print_timing: id 1 | task 2782184 | prompt processing, n_tokens = 40423, progress = 1.00, t = 53.80 s / 751.40 tokens per second
llama-server | 10991.08.386.662 I slot print_timing: id 0 | task 2781837 | n_gen = 1209, tg = 4.00 t/s, tg_3s = 3.26 t/s
llama-server | 10991.10.702.396 I slot print_timing: id 1 | task 2782184 | prompt eval time = 54223.19 ms / 40427 tokens ( 1.34 ms per token, 745.57 tokens per second)
llama-server | 10991.10.702.400 I slot print_timing: id 1 | task 2782184 | eval time = 2410.43 ms / 108 tokens ( 22.53 ms per token, 44.39 tokens per second)
llama-server | 10991.10.702.401 I slot print_timing: id 1 | task 2782184 | total time = 56633.62 ms / 40535 tokens
llama-server | 10991.10.702.401 I slot print_timing: id 1 | task 2782184 | graphs reused = 2694593
llama-server | 10991.10.702.405 I slot print_timing: id 1 | task 2782184 | draft acceptance = 0.63077 ( 82 accepted / 130 generated), mean len = 4.15
llama-server | 10991.10.703.537 I slot release: id 1 | task 2782184 | stop processing: n_tokens = 40535, truncated = 0
llama-server | 10991.11.465.929 I slot print_timing: id 0 | task 2781837 | n_gen = 1293, tg = 4.23 t/s, tg_3s = 27.28 t/s
llama-server | 10991.11.835.126 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659486543589
llama-server | 10991.11.837.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1936.514 MiB)
llama-server | 10991.13.776.836 I slot launch_slot_: id 1 | task 2782245 | processing task, is_child = 0
llama-server | 10991.16.506.749 I slot print_timing: id 0 | task 2781837 | n_gen = 1305, tg = 4.20 t/s, tg_3s = 2.38 t/s
llama-server | 10991.19.204.580 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 4084, progress = 0.09, t = 5.27 s / 775.23 tokens per second
llama-server | 10991.21.905.066 I slot print_timing: id 0 | task 2781837 | n_gen = 1310, tg = 4.15 t/s, tg_3s = 0.93 t/s
llama-server | 10991.21.915.014 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 6126, progress = 0.13, t = 7.98 s / 767.63 tokens per second
llama-server | 10991.24.600.700 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 8168, progress = 0.18, t = 10.67 s / 765.81 tokens per second
llama-server | 10991.27.280.359 I slot print_timing: id 0 | task 2781837 | n_gen = 1316, tg = 4.10 t/s, tg_3s = 1.12 t/s
llama-server | 10991.27.290.784 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 10210, progress = 0.22, t = 13.36 s / 764.45 tokens per second
llama-server | 10991.29.979.404 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 12252, progress = 0.26, t = 16.04 s / 763.61 tokens per second
llama-server | 10991.32.657.691 I slot print_timing: id 0 | task 2781837 | n_gen = 1322, tg = 4.05 t/s, tg_3s = 1.12 t/s
llama-server | 10991.32.668.061 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 14294, progress = 0.31, t = 18.73 s / 763.03 tokens per second
llama-server | 10991.35.361.197 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 16336, progress = 0.35, t = 21.43 s / 762.42 tokens per second
llama-server | 10991.38.044.087 I slot print_timing: id 0 | task 2781837 | n_gen = 1330, tg = 4.01 t/s, tg_3s = 1.49 t/s
llama-server | 10991.38.054.052 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 18378, progress = 0.40, t = 24.12 s / 761.97 tokens per second
llama-server | 10991.40.747.002 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 20420, progress = 0.44, t = 26.81 s / 761.62 tokens per second
llama-server | 10991.43.428.688 I slot print_timing: id 0 | task 2781837 | n_gen = 1333, tg = 3.95 t/s, tg_3s = 0.56 t/s
llama-server | 10991.43.439.161 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 22462, progress = 0.48, t = 29.50 s / 761.30 tokens per second
llama-server | 10991.46.131.973 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 24504, progress = 0.53, t = 32.20 s / 761.06 tokens per second
llama-server | 10991.48.815.760 I slot print_timing: id 0 | task 2781837 | n_gen = 1340, tg = 3.91 t/s, tg_3s = 1.30 t/s
llama-server | 10991.48.825.460 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 26546, progress = 0.57, t = 34.89 s / 760.84 tokens per second
llama-server | 10991.51.520.526 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 28588, progress = 0.61, t = 37.59 s / 760.62 tokens per second
llama-server | 10991.54.205.770 I slot print_timing: id 0 | task 2781837 | n_gen = 1344, tg = 3.86 t/s, tg_3s = 0.74 t/s
llama-server | 10991.54.216.128 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 30630, progress = 0.66, t = 40.28 s / 760.40 tokens per second
llama-server | 10991.56.913.366 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 32672, progress = 0.70, t = 42.98 s / 760.20 tokens per second
llama-server | 10991.59.599.655 I slot print_timing: id 0 | task 2781837 | n_gen = 1347, tg = 3.81 t/s, tg_3s = 0.56 t/s
llama-server | 10991.59.609.789 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 34714, progress = 0.75, t = 45.68 s / 760.01 tokens per second
llama-server | 10992.02.307.318 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 36756, progress = 0.79, t = 48.37 s / 759.85 tokens per second
llama-server | 10992.04.996.582 I slot print_timing: id 0 | task 2781837 | n_gen = 1359, tg = 3.79 t/s, tg_3s = 2.22 t/s
llama-server | 10992.05.006.130 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 38798, progress = 0.83, t = 51.07 s / 759.68 tokens per second
llama-server | 10992.07.699.581 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 40840, progress = 0.88, t = 53.77 s / 759.59 tokens per second
llama-server | 10992.10.377.924 I slot print_timing: id 0 | task 2781837 | n_gen = 1367, tg = 3.75 t/s, tg_3s = 1.49 t/s
llama-server | 10992.10.388.069 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 42882, progress = 0.92, t = 56.45 s / 759.60 tokens per second
llama-server | 10992.13.109.730 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 44924, progress = 0.97, t = 59.18 s / 759.16 tokens per second
llama-server | 10992.14.619.014 I slot print_timing: id 0 | task 2781837 | n_gen = 1372, tg = 3.72 t/s, tg_3s = 1.18 t/s
llama-server | 10992.14.627.668 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 45974, progress = 0.99, t = 60.75 s / 756.72 tokens per second
llama-server | 10992.15.655.286 I slot print_timing: id 1 | task 2782245 | prompt processing, n_tokens = 46486, progress = 1.00, t = 61.82 s / 752.01 tokens per second
llama-server | 10992.17.621.187 I slot print_timing: id 0 | task 2781837 | n_gen = 1417, tg = 3.81 t/s, tg_3s = 14.99 t/s
llama-server | 10992.19.693.897 I slot print_timing: id 1 | task 2782245 | n_gen = 104, tg = 28.50 t/s, tg_3s = 28.78 t/s
llama-server | 10992.20.474.638 I slot print_timing: id 1 | task 2782245 | prompt eval time = 62291.66 ms / 46490 tokens ( 1.34 ms per token, 746.33 tokens per second)
llama-server | 10992.20.474.641 I slot print_timing: id 1 | task 2782245 | eval time = 4394.39 ms / 140 tokens ( 31.61 ms per token, 31.63 tokens per second)
llama-server | 10992.20.474.642 I slot print_timing: id 1 | task 2782245 | total time = 66686.05 ms / 46630 tokens
llama-server | 10992.20.474.643 I slot print_timing: id 1 | task 2782245 | graphs reused = 2694688
llama-server | 10992.20.474.646 I slot print_timing: id 1 | task 2782245 | draft acceptance = 0.40870 ( 94 accepted / 230 generated), mean len = 3.04
llama-server | 10992.20.476.027 I slot release: id 1 | task 2782245 | stop processing: n_tokens = 46630, truncated = 0
llama-server | 10992.20.692.003 I slot print_timing: id 0 | task 2781837 | n_gen = 1521, tg = 4.06 t/s, tg_3s = 33.87 t/s
llama-server | 10992.21.741.827 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659556316079
llama-server | 10992.21.744.073 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1927.304 MiB)
llama-server | 10992.24.394.179 I slot launch_slot_: id 1 | task 2782330 | processing task, is_child = 0
llama-server | 10992.27.203.004 I slot print_timing: id 0 | task 2781837 | n_gen = 1546, tg = 4.06 t/s, tg_3s = 3.84 t/s
llama-server | 10992.29.982.973 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 4084, progress = 0.09, t = 5.43 s / 751.98 tokens per second
llama-server | 10992.32.761.968 I slot print_timing: id 0 | task 2781837 | n_gen = 1552, tg = 4.01 t/s, tg_3s = 1.08 t/s
llama-server | 10992.32.771.726 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 6126, progress = 0.13, t = 8.22 s / 745.15 tokens per second
llama-server | 10992.35.539.996 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 8168, progress = 0.18, t = 10.99 s / 743.25 tokens per second
llama-server | 10992.38.301.524 I slot print_timing: id 0 | task 2781837 | n_gen = 1557, tg = 3.97 t/s, tg_3s = 0.90 t/s
llama-server | 10992.38.311.791 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 10210, progress = 0.22, t = 13.76 s / 741.93 tokens per second
llama-server | 10992.41.085.989 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 12252, progress = 0.26, t = 16.53 s / 741.00 tokens per second
llama-server | 10992.43.851.844 I slot print_timing: id 0 | task 2781837 | n_gen = 1563, tg = 3.93 t/s, tg_3s = 1.08 t/s
llama-server | 10992.43.861.587 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 14294, progress = 0.31, t = 19.31 s / 740.23 tokens per second
llama-server | 10992.46.638.117 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 16336, progress = 0.35, t = 22.09 s / 739.65 tokens per second
llama-server | 10992.49.407.242 I slot print_timing: id 0 | task 2781837 | n_gen = 1575, tg = 3.90 t/s, tg_3s = 2.16 t/s
llama-server | 10992.49.416.842 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 18378, progress = 0.40, t = 24.86 s / 739.11 tokens per second
llama-server | 10992.52.192.083 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 20420, progress = 0.44, t = 27.64 s / 738.75 tokens per second
llama-server | 10992.54.960.702 I slot print_timing: id 0 | task 2781837 | n_gen = 1582, tg = 3.87 t/s, tg_3s = 1.26 t/s
llama-server | 10992.54.970.709 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 22462, progress = 0.48, t = 30.42 s / 738.41 tokens per second
llama-server | 10992.57.748.383 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 24504, progress = 0.53, t = 33.20 s / 738.14 tokens per second
llama-server | 10993.00.517.814 I slot print_timing: id 0 | task 2781837 | n_gen = 1585, tg = 3.82 t/s, tg_3s = 0.54 t/s
llama-server | 10993.00.528.656 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 26546, progress = 0.57, t = 35.98 s / 737.87 tokens per second
llama-server | 10993.03.306.632 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 28588, progress = 0.61, t = 38.76 s / 737.65 tokens per second
llama-server | 10993.06.079.287 I slot print_timing: id 0 | task 2781837 | n_gen = 1592, tg = 3.79 t/s, tg_3s = 1.26 t/s
llama-server | 10993.06.088.442 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 30630, progress = 0.66, t = 41.54 s / 737.41 tokens per second
llama-server | 10993.08.872.066 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 32672, progress = 0.70, t = 44.32 s / 737.20 tokens per second
llama-server | 10993.11.643.352 I slot print_timing: id 0 | task 2781837 | n_gen = 1595, tg = 3.75 t/s, tg_3s = 0.54 t/s
llama-server | 10993.11.653.895 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 34714, progress = 0.75, t = 47.10 s / 736.99 tokens per second
llama-server | 10993.14.435.906 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 36756, progress = 0.79, t = 49.88 s / 736.82 tokens per second
llama-server | 10993.17.210.539 I slot print_timing: id 0 | task 2781837 | n_gen = 1599, tg = 3.71 t/s, tg_3s = 0.72 t/s
llama-server | 10993.17.220.828 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 38798, progress = 0.83, t = 52.67 s / 736.64 tokens per second
llama-server | 10993.20.007.442 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 40840, progress = 0.88, t = 55.46 s / 736.44 tokens per second
llama-server | 10993.22.781.895 I slot print_timing: id 0 | task 2781837 | n_gen = 1603, tg = 3.67 t/s, tg_3s = 0.72 t/s
llama-server | 10993.22.792.682 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 42882, progress = 0.92, t = 58.24 s / 736.28 tokens per second
llama-server | 10993.25.579.030 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 44924, progress = 0.97, t = 61.03 s / 736.13 tokens per second
llama-server | 10993.27.124.803 I slot print_timing: id 0 | task 2781837 | n_gen = 1610, tg = 3.65 t/s, tg_3s = 1.61 t/s
llama-server | 10993.27.133.937 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 45986, progress = 0.99, t = 62.64 s / 734.10 tokens per second
llama-server | 10993.28.132.813 I slot print_timing: id 1 | task 2782330 | prompt processing, n_tokens = 46498, progress = 1.00, t = 63.68 s / 730.22 tokens per second
llama-server | 10993.30.196.239 I slot print_timing: id 0 | task 2781837 | n_gen = 1672, tg = 3.76 t/s, tg_3s = 20.19 t/s
llama-server | 10993.33.230.747 I slot print_timing: id 0 | task 2781837 | n_gen = 1782, tg = 3.98 t/s, tg_3s = 36.25 t/s
llama-server | 10993.33.231.913 I slot print_timing: id 1 | task 2782330 | n_gen = 101, tg = 21.37 t/s, tg_3s = 21.58 t/s
llama-server | 10993.36.254.540 I slot print_timing: id 0 | task 2781837 | n_gen = 1910, tg = 4.24 t/s, tg_3s = 42.33 t/s
llama-server | 10993.36.255.383 I slot print_timing: id 1 | task 2782330 | n_gen = 185, tg = 23.89 t/s, tg_3s = 27.78 t/s
llama-server | 10993.39.315.578 I slot print_timing: id 0 | task 2781837 | n_gen = 2049, tg = 4.52 t/s, tg_3s = 45.41 t/s
llama-server | 10993.39.316.564 I slot print_timing: id 1 | task 2782330 | n_gen = 264, tg = 24.43 t/s, tg_3s = 25.81 t/s
llama-server | 10993.42.320.986 I slot print_timing: id 0 | task 2781837 | n_gen = 2160, tg = 4.73 t/s, tg_3s = 36.93 t/s
llama-server | 10993.42.322.607 I slot print_timing: id 1 | task 2782330 | n_gen = 373, tg = 27.02 t/s, tg_3s = 36.26 t/s
llama-server | 10993.43.558.136 I slot print_timing: id 1 | task 2782330 | prompt eval time = 64147.33 ms / 46502 tokens ( 1.38 ms per token, 724.92 tokens per second)
llama-server | 10993.43.558.139 I slot print_timing: id 1 | task 2782330 | eval time = 15005.53 ms / 420 tokens ( 35.81 ms per token, 27.92 tokens per second)
llama-server | 10993.43.558.139 I slot print_timing: id 1 | task 2782330 | total time = 79152.86 ms / 46922 tokens
llama-server | 10993.43.558.140 I slot print_timing: id 1 | task 2782330 | graphs reused = 2694898
llama-server | 10993.43.558.143 I slot print_timing: id 1 | task 2782330 | draft acceptance = 0.33503 ( 263 accepted / 785 generated), mean len = 2.68
llama-server | 10993.43.559.564 I slot release: id 1 | task 2782330 | stop processing: n_tokens = 46922, truncated = 0
llama-server | 10993.44.951.062 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659639399616
llama-server | 10993.44.953.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1917.728 MiB)
llama-server | 10993.45.113.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2110.394 MiB)
llama-server | 10993.47.213.542 I slot launch_slot_: id 1 | task 2782527 | processing task, is_child = 0
llama-server | 10993.50.062.161 I slot print_timing: id 0 | task 2781837 | n_gen = 2234, tg = 4.81 t/s, tg_3s = 9.56 t/s
llama-server | 10993.52.883.721 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 4084, progress = 0.09, t = 5.50 s / 742.96 tokens per second
llama-server | 10993.55.701.488 I slot print_timing: id 0 | task 2781837 | n_gen = 2238, tg = 4.76 t/s, tg_3s = 0.71 t/s
llama-server | 10993.55.711.755 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 6126, progress = 0.13, t = 8.33 s / 735.63 tokens per second
llama-server | 10993.58.515.493 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 8168, progress = 0.18, t = 11.13 s / 733.82 tokens per second
llama-server | 10994.01.309.960 I slot print_timing: id 0 | task 2781837 | n_gen = 2246, tg = 4.73 t/s, tg_3s = 1.43 t/s
llama-server | 10994.01.320.100 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 10210, progress = 0.22, t = 13.94 s / 732.64 tokens per second
llama-server | 10994.04.126.037 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 12252, progress = 0.26, t = 16.74 s / 731.90 tokens per second
llama-server | 10994.06.921.106 I slot print_timing: id 0 | task 2781837 | n_gen = 2251, tg = 4.68 t/s, tg_3s = 0.89 t/s
llama-server | 10994.06.931.352 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 14294, progress = 0.31, t = 19.55 s / 731.30 tokens per second
llama-server | 10994.09.735.110 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 16336, progress = 0.35, t = 22.35 s / 730.89 tokens per second
llama-server | 10994.12.528.349 I slot print_timing: id 0 | task 2781837 | n_gen = 2256, tg = 4.64 t/s, tg_3s = 0.89 t/s
llama-server | 10994.12.538.536 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 18378, progress = 0.40, t = 25.15 s / 730.61 tokens per second
llama-server | 10994.15.345.063 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 20420, progress = 0.44, t = 27.96 s / 730.29 tokens per second
llama-server | 10994.18.140.189 I slot print_timing: id 0 | task 2781837 | n_gen = 2259, tg = 4.59 t/s, tg_3s = 0.53 t/s
llama-server | 10994.18.150.848 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 22462, progress = 0.48, t = 30.77 s / 730.07 tokens per second
llama-server | 10994.20.961.312 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 24504, progress = 0.53, t = 33.57 s / 729.83 tokens per second
llama-server | 10994.23.759.231 I slot print_timing: id 0 | task 2781837 | n_gen = 2269, tg = 4.56 t/s, tg_3s = 1.78 t/s
llama-server | 10994.23.768.873 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 26546, progress = 0.57, t = 36.38 s / 729.61 tokens per second
llama-server | 10994.26.577.550 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 28588, progress = 0.62, t = 39.19 s / 729.41 tokens per second
llama-server | 10994.29.373.833 I slot print_timing: id 0 | task 2781837 | n_gen = 2276, tg = 4.52 t/s, tg_3s = 1.25 t/s
llama-server | 10994.29.384.160 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 30630, progress = 0.66, t = 42.00 s / 729.27 tokens per second
llama-server | 10994.32.193.459 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 32672, progress = 0.70, t = 44.81 s / 729.15 tokens per second
llama-server | 10994.34.994.811 I slot print_timing: id 0 | task 2781837 | n_gen = 2286, tg = 4.49 t/s, tg_3s = 1.78 t/s
llama-server | 10994.35.004.422 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 34714, progress = 0.75, t = 47.62 s / 729.02 tokens per second
llama-server | 10994.37.812.889 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 36756, progress = 0.79, t = 50.43 s / 728.86 tokens per second
llama-server | 10994.40.615.553 I slot print_timing: id 0 | task 2781837 | n_gen = 2291, tg = 4.45 t/s, tg_3s = 0.89 t/s
llama-server | 10994.40.625.643 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 38798, progress = 0.84, t = 53.24 s / 728.73 tokens per second
llama-server | 10994.43.438.550 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 40840, progress = 0.88, t = 56.05 s / 728.58 tokens per second
llama-server | 10994.46.241.679 I slot print_timing: id 0 | task 2781837 | n_gen = 2301, tg = 4.42 t/s, tg_3s = 1.78 t/s
llama-server | 10994.46.251.602 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 42882, progress = 0.92, t = 58.87 s / 728.44 tokens per second
llama-server | 10994.49.065.974 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 44924, progress = 0.97, t = 61.68 s / 728.33 tokens per second
llama-server | 10994.50.494.082 I slot print_timing: id 0 | task 2781837 | n_gen = 2310, tg = 4.40 t/s, tg_3s = 2.12 t/s
llama-server | 10994.50.504.158 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 45914, progress = 0.99, t = 63.19 s / 726.55 tokens per second
llama-server | 10994.51.561.598 I slot print_timing: id 1 | task 2782527 | prompt processing, n_tokens = 46426, progress = 1.00, t = 64.29 s / 722.18 tokens per second
llama-server | 10994.53.525.487 I slot print_timing: id 0 | task 2781837 | n_gen = 2365, tg = 4.48 t/s, tg_3s = 18.14 t/s
llama-server | 10994.55.048.591 I slot print_timing: id 1 | task 2782527 | n_gen = 102, tg = 32.65 t/s, tg_3s = 32.97 t/s
llama-server | 10994.56.567.645 I slot print_timing: id 0 | task 2781837 | n_gen = 2460, tg = 4.64 t/s, tg_3s = 31.23 t/s
llama-server | 10994.58.086.067 I slot print_timing: id 1 | task 2782527 | n_gen = 199, tg = 32.30 t/s, tg_3s = 31.93 t/s
llama-server | 10994.59.603.830 I slot print_timing: id 0 | task 2781837 | n_gen = 2562, tg = 4.80 t/s, tg_3s = 33.59 t/s
llama-server | 10995.01.129.994 I slot print_timing: id 1 | task 2782527 | n_gen = 291, tg = 31.61 t/s, tg_3s = 30.22 t/s
llama-server | 10995.02.678.989 I slot print_timing: id 0 | task 2781837 | n_gen = 2681, tg = 5.00 t/s, tg_3s = 38.70 t/s
llama-server | 10995.04.203.171 I slot print_timing: id 1 | task 2782527 | n_gen = 375, tg = 30.54 t/s, tg_3s = 27.33 t/s
llama-server | 10995.05.747.676 I slot print_timing: id 0 | task 2781837 | n_gen = 2777, tg = 5.15 t/s, tg_3s = 31.28 t/s
llama-server | 10995.07.204.476 I slot print_timing: id 1 | task 2782527 | n_gen = 488, tg = 31.94 t/s, tg_3s = 37.65 t/s
llama-server | 10995.08.831.030 I slot print_timing: id 0 | task 2781837 | n_gen = 2881, tg = 5.31 t/s, tg_3s = 33.73 t/s
llama-server | 10995.10.207.416 I slot print_timing: id 1 | task 2782527 | n_gen = 622, tg = 34.02 t/s, tg_3s = 44.62 t/s
llama-server | 10995.11.833.504 I slot print_timing: id 0 | task 2781837 | n_gen = 2999, tg = 5.49 t/s, tg_3s = 39.30 t/s
llama-server | 10995.13.269.040 I slot print_timing: id 1 | task 2782527 | n_gen = 701, tg = 32.84 t/s, tg_3s = 25.80 t/s
llama-server | 10995.14.917.585 I slot print_timing: id 0 | task 2781837 | n_gen = 3079, tg = 5.61 t/s, tg_3s = 25.94 t/s
llama-server | 10995.16.354.416 I slot print_timing: id 1 | task 2782527 | n_gen = 806, tg = 32.99 t/s, tg_3s = 34.03 t/s
llama-server | 10995.18.008.767 I slot print_timing: id 0 | task 2781837 | n_gen = 3187, tg = 5.77 t/s, tg_3s = 34.94 t/s
llama-server | 10995.19.446.548 I slot print_timing: id 1 | task 2782527 | n_gen = 872, tg = 31.68 t/s, tg_3s = 21.34 t/s
llama-server | 10995.21.074.051 I slot print_timing: id 0 | task 2781837 | n_gen = 3293, tg = 5.93 t/s, tg_3s = 34.58 t/s
llama-server | 10995.22.537.573 I slot print_timing: id 1 | task 2782527 | n_gen = 954, tg = 31.16 t/s, tg_3s = 26.53 t/s
llama-server | 10995.24.077.598 I slot print_timing: id 0 | task 2781837 | n_gen = 3396, tg = 6.09 t/s, tg_3s = 34.29 t/s
llama-server | 10995.25.613.581 I slot print_timing: id 1 | task 2782527 | n_gen = 1024, tg = 30.39 t/s, tg_3s = 22.76 t/s
llama-server | 10995.27.172.357 I slot print_timing: id 0 | task 2781837 | n_gen = 3487, tg = 6.21 t/s, tg_3s = 29.40 t/s
llama-server | 10995.28.619.097 I slot print_timing: id 1 | task 2782527 | n_gen = 1115, tg = 30.38 t/s, tg_3s = 30.28 t/s
llama-server | 10995.29.871.718 I slot print_timing: id 1 | task 2782527 | prompt eval time = 64730.17 ms / 46430 tokens ( 1.39 ms per token, 717.29 tokens per second)
llama-server | 10995.29.871.721 I slot print_timing: id 1 | task 2782527 | eval time = 37916.44 ms / 1153 tokens ( 32.91 ms per token, 30.38 tokens per second)
llama-server | 10995.29.871.722 I slot print_timing: id 1 | task 2782527 | total time = 102646.61 ms / 47583 tokens
llama-server | 10995.29.871.722 I slot print_timing: id 1 | task 2782527 | graphs reused = 2695340
llama-server | 10995.29.871.726 I slot print_timing: id 1 | task 2782527 | draft acceptance = 0.38528 ( 759 accepted / 1970 generated), mean len = 2.93
llama-server | 10995.29.873.117 I slot release: id 1 | task 2782527 | stop processing: n_tokens = 47583, truncated = 0
llama-server | 10995.30.189.635 I slot print_timing: id 0 | task 2781837 | n_gen = 3595, tg = 6.37 t/s, tg_3s = 35.79 t/s
llama-server | 10995.31.086.436 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659745713169
llama-server | 10995.31.088.834 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1916.764 MiB)
llama-server | 10995.34.081.174 I slot launch_slot_: id 1 | task 2782959 | processing task, is_child = 0
llama-server | 10995.36.960.306 I slot print_timing: id 0 | task 2781837 | n_gen = 3634, tg = 6.37 t/s, tg_3s = 5.76 t/s
llama-server | 10995.39.803.457 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.56 s / 734.93 tokens per second
llama-server | 10995.42.649.045 I slot print_timing: id 0 | task 2781837 | n_gen = 3640, tg = 6.31 t/s, tg_3s = 1.05 t/s
llama-server | 10995.42.659.260 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.41 s / 728.03 tokens per second
llama-server | 10995.45.491.675 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.25 s / 726.26 tokens per second
llama-server | 10995.48.313.352 I slot print_timing: id 0 | task 2781837 | n_gen = 3647, tg = 6.26 t/s, tg_3s = 1.24 t/s
llama-server | 10995.48.322.971 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.08 s / 725.24 tokens per second
llama-server | 10995.51.156.296 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.91 s / 724.49 tokens per second
llama-server | 10995.53.980.190 I slot print_timing: id 0 | task 2781837 | n_gen = 3657, tg = 6.22 t/s, tg_3s = 1.76 t/s
llama-server | 10995.53.989.836 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.74 s / 723.94 tokens per second
llama-server | 10995.56.825.450 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.58 s / 723.53 tokens per second
llama-server | 10995.59.647.666 I slot print_timing: id 0 | task 2781837 | n_gen = 3666, tg = 6.18 t/s, tg_3s = 1.59 t/s
llama-server | 10995.59.657.827 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.41 s / 723.18 tokens per second
llama-server | 10996.02.493.553 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 20420, progress = 0.50, t = 28.25 s / 722.88 tokens per second
llama-server | 10996.05.322.124 I slot print_timing: id 0 | task 2781837 | n_gen = 3676, tg = 6.13 t/s, tg_3s = 1.76 t/s
llama-server | 10996.05.331.562 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 22462, progress = 0.55, t = 31.08 s / 722.64 tokens per second
llama-server | 10996.08.165.657 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 24504, progress = 0.60, t = 33.92 s / 722.38 tokens per second
llama-server | 10996.10.992.585 I slot print_timing: id 0 | task 2781837 | n_gen = 3681, tg = 6.09 t/s, tg_3s = 0.88 t/s
llama-server | 10996.11.002.361 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 26546, progress = 0.65, t = 36.76 s / 722.24 tokens per second
llama-server | 10996.13.838.113 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 28588, progress = 0.70, t = 39.59 s / 722.05 tokens per second
llama-server | 10996.16.666.279 I slot print_timing: id 0 | task 2781837 | n_gen = 3685, tg = 6.04 t/s, tg_3s = 0.71 t/s
llama-server | 10996.16.676.655 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 30630, progress = 0.75, t = 42.43 s / 721.89 tokens per second
llama-server | 10996.19.515.430 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 32672, progress = 0.80, t = 45.27 s / 721.73 tokens per second
llama-server | 10996.22.344.673 I slot print_timing: id 0 | task 2781837 | n_gen = 3694, tg = 5.99 t/s, tg_3s = 1.58 t/s
llama-server | 10996.22.353.776 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 34714, progress = 0.85, t = 48.11 s / 721.59 tokens per second
llama-server | 10996.25.190.534 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 36756, progress = 0.90, t = 50.95 s / 721.48 tokens per second
llama-server | 10996.28.020.028 I slot print_timing: id 0 | task 2781837 | n_gen = 3706, tg = 5.96 t/s, tg_3s = 2.11 t/s
llama-server | 10996.28.029.534 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 38798, progress = 0.95, t = 53.78 s / 721.36 tokens per second
llama-server | 10996.30.143.687 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 40254, progress = 0.99, t = 55.94 s / 719.64 tokens per second
llama-server | 10996.31.267.930 I slot print_timing: id 0 | task 2781837 | n_gen = 3713, tg = 5.94 t/s, tg_3s = 2.16 t/s
llama-server | 10996.31.278.412 I slot print_timing: id 1 | task 2782959 | prompt processing, n_tokens = 40766, progress = 1.00, t = 57.13 s / 713.56 tokens per second
llama-server | 10996.34.360.896 I slot print_timing: id 0 | task 2781837 | n_gen = 3793, tg = 6.04 t/s, tg_3s = 25.87 t/s
llama-server | 10996.35.613.605 I slot print_timing: id 1 | task 2782959 | n_gen = 105, tg = 27.47 t/s, tg_3s = 27.73 t/s
llama-server | 10996.37.439.742 I slot print_timing: id 0 | task 2781837 | n_gen = 3913, tg = 6.20 t/s, tg_3s = 38.98 t/s
llama-server | 10996.38.693.182 I slot print_timing: id 1 | task 2782959 | n_gen = 212, tg = 30.73 t/s, tg_3s = 34.75 t/s
llama-server | 10996.40.514.791 I slot print_timing: id 0 | task 2781837 | n_gen = 4026, tg = 6.35 t/s, tg_3s = 36.75 t/s
llama-server | 10996.41.779.872 I slot print_timing: id 1 | task 2782959 | n_gen = 292, tg = 29.24 t/s, tg_3s = 25.92 t/s
llama-server | 10996.43.607.613 I slot print_timing: id 0 | task 2781837 | n_gen = 4120, tg = 6.46 t/s, tg_3s = 30.39 t/s
llama-server | 10996.44.854.991 I slot print_timing: id 1 | task 2782959 | n_gen = 404, tg = 30.93 t/s, tg_3s = 36.42 t/s
llama-server | 10996.46.684.370 I slot print_timing: id 0 | task 2781837 | n_gen = 4211, tg = 6.57 t/s, tg_3s = 29.58 t/s
llama-server | 10996.47.938.726 I slot print_timing: id 1 | task 2782959 | n_gen = 529, tg = 32.77 t/s, tg_3s = 40.54 t/s
llama-server | 10996.49.767.794 I slot print_timing: id 0 | task 2781837 | n_gen = 4333, tg = 6.73 t/s, tg_3s = 39.57 t/s
llama-server | 10996.51.020.918 I slot print_timing: id 1 | task 2782959 | n_gen = 626, tg = 32.56 t/s, tg_3s = 31.47 t/s
llama-server | 10996.52.854.047 I slot print_timing: id 0 | task 2781837 | n_gen = 4465, tg = 6.90 t/s, tg_3s = 42.77 t/s
llama-server | 10996.54.106.391 I slot print_timing: id 1 | task 2782959 | n_gen = 744, tg = 33.35 t/s, tg_3s = 38.24 t/s
llama-server | 10996.55.935.079 I slot print_timing: id 0 | task 2781837 | n_gen = 4573, tg = 7.04 t/s, tg_3s = 35.05 t/s
llama-server | 10996.57.187.931 I slot print_timing: id 1 | task 2782959 | n_gen = 835, tg = 32.89 t/s, tg_3s = 29.53 t/s
llama-server | 10996.59.014.815 I slot print_timing: id 0 | task 2781837 | n_gen = 4668, tg = 7.15 t/s, tg_3s = 30.85 t/s
llama-server | 10997.00.265.731 I slot print_timing: id 1 | task 2782959 | n_gen = 928, tg = 32.60 t/s, tg_3s = 30.22 t/s
llama-server | 10997.02.089.722 I slot print_timing: id 0 | task 2781837 | n_gen = 4761, tg = 7.26 t/s, tg_3s = 30.24 t/s
llama-server | 10997.03.340.379 I slot print_timing: id 1 | task 2782959 | n_gen = 1007, tg = 31.92 t/s, tg_3s = 25.69 t/s
llama-server | 10997.05.168.208 I slot print_timing: id 0 | task 2781837 | n_gen = 4871, tg = 7.39 t/s, tg_3s = 35.73 t/s
llama-server | 10997.06.413.523 I slot print_timing: id 1 | task 2782959 | n_gen = 1090, tg = 31.49 t/s, tg_3s = 27.01 t/s
llama-server | 10997.08.239.770 I slot print_timing: id 0 | task 2781837 | n_gen = 4946, tg = 7.47 t/s, tg_3s = 24.42 t/s
llama-server | 10997.09.485.225 I slot print_timing: id 1 | task 2782959 | n_gen = 1172, tg = 31.10 t/s, tg_3s = 26.70 t/s
llama-server | 10997.11.316.544 I slot print_timing: id 0 | task 2781837 | n_gen = 5039, tg = 7.58 t/s, tg_3s = 30.23 t/s
llama-server | 10997.12.565.089 I slot print_timing: id 1 | task 2782959 | n_gen = 1282, tg = 31.45 t/s, tg_3s = 35.72 t/s
llama-server | 10997.14.391.063 I slot print_timing: id 0 | task 2781837 | n_gen = 5123, tg = 7.67 t/s, tg_3s = 27.32 t/s
llama-server | 10997.15.067.251 I slot print_timing: id 1 | task 2782959 | prompt eval time = 57734.43 ms / 40770 tokens ( 1.42 ms per token, 706.16 tokens per second)
llama-server | 10997.15.067.254 I slot print_timing: id 1 | task 2782959 | eval time = 43239.81 ms / 1376 tokens ( 31.45 ms per token, 31.80 tokens per second)
llama-server | 10997.15.067.255 I slot print_timing: id 1 | task 2782959 | total time = 100974.24 ms / 42146 tokens
llama-server | 10997.15.067.255 I slot print_timing: id 1 | task 2782959 | graphs reused = 2695837
llama-server | 10997.15.067.258 I slot print_timing: id 1 | task 2782959 | draft acceptance = 0.41292 ( 927 accepted / 2245 generated), mean len = 3.06
llama-server | 10997.15.068.532 I slot release: id 1 | task 2782959 | stop processing: n_tokens = 42146, truncated = 0
llama-server | 10997.16.361.136 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659850908585
llama-server | 10997.16.363.273 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2119.416 MiB)
llama-server | 10997.19.488.064 I slot launch_slot_: id 1 | task 2783444 | processing task, is_child = 0
llama-server | 10997.22.365.633 I slot print_timing: id 0 | task 2781837 | n_gen = 5186, tg = 7.67 t/s, tg_3s = 7.90 t/s
llama-server | 10997.25.201.976 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.55 s / 735.26 tokens per second
llama-server | 10997.28.051.565 I slot print_timing: id 0 | task 2781837 | n_gen = 5192, tg = 7.61 t/s, tg_3s = 1.06 t/s
llama-server | 10997.28.061.655 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.41 s / 728.77 tokens per second
llama-server | 10997.30.888.415 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.24 s / 726.58 tokens per second
llama-server | 10997.33.705.018 I slot print_timing: id 0 | task 2781837 | n_gen = 5195, tg = 7.56 t/s, tg_3s = 0.53 t/s
llama-server | 10997.33.715.276 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.07 s / 725.69 tokens per second
llama-server | 10997.36.543.488 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.90 s / 725.09 tokens per second
llama-server | 10997.39.361.485 I slot print_timing: id 0 | task 2781837 | n_gen = 5200, tg = 7.50 t/s, tg_3s = 0.88 t/s
llama-server | 10997.39.371.382 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.72 s / 724.70 tokens per second
llama-server | 10997.42.199.544 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.55 s / 724.32 tokens per second
llama-server | 10997.45.018.815 I slot print_timing: id 0 | task 2781837 | n_gen = 5203, tg = 7.44 t/s, tg_3s = 0.53 t/s
llama-server | 10997.45.028.806 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.38 s / 724.06 tokens per second
llama-server | 10997.47.858.494 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 20420, progress = 0.50, t = 28.21 s / 723.80 tokens per second
llama-server | 10997.50.678.019 I slot print_timing: id 0 | task 2781837 | n_gen = 5206, tg = 7.39 t/s, tg_3s = 0.53 t/s
llama-server | 10997.50.688.220 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 22462, progress = 0.55, t = 31.04 s / 723.63 tokens per second
llama-server | 10997.53.516.693 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 24504, progress = 0.60, t = 33.87 s / 723.48 tokens per second
llama-server | 10997.56.337.436 I slot print_timing: id 0 | task 2781837 | n_gen = 5210, tg = 7.34 t/s, tg_3s = 0.71 t/s
llama-server | 10997.56.347.650 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 26546, progress = 0.65, t = 36.70 s / 723.31 tokens per second
llama-server | 10997.59.182.096 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 28588, progress = 0.70, t = 39.53 s / 723.14 tokens per second
llama-server | 10998.02.003.613 I slot print_timing: id 0 | task 2781837 | n_gen = 5216, tg = 7.29 t/s, tg_3s = 1.06 t/s
llama-server | 10998.02.013.401 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 30630, progress = 0.75, t = 42.37 s / 722.97 tokens per second
llama-server | 10998.04.848.369 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 32672, progress = 0.80, t = 45.20 s / 722.82 tokens per second
llama-server | 10998.07.670.921 I slot print_timing: id 0 | task 2781837 | n_gen = 5220, tg = 7.23 t/s, tg_3s = 0.71 t/s
llama-server | 10998.07.681.094 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 34714, progress = 0.85, t = 48.03 s / 722.69 tokens per second
llama-server | 10998.10.515.526 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 36756, progress = 0.90, t = 50.87 s / 722.58 tokens per second
llama-server | 10998.13.340.489 I slot print_timing: id 0 | task 2781837 | n_gen = 5224, tg = 7.18 t/s, tg_3s = 0.71 t/s
llama-server | 10998.13.350.839 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 38798, progress = 0.95, t = 53.70 s / 722.45 tokens per second
llama-server | 10998.15.510.120 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 40333, progress = 0.99, t = 55.89 s / 721.60 tokens per second
llama-server | 10998.16.647.008 I slot print_timing: id 0 | task 2781837 | n_gen = 5236, tg = 7.17 t/s, tg_3s = 3.63 t/s
llama-server | 10998.16.656.040 I slot print_timing: id 1 | task 2783444 | prompt processing, n_tokens = 40845, progress = 1.00, t = 57.11 s / 715.25 tokens per second
llama-server | 10998.19.732.714 I slot print_timing: id 0 | task 2781837 | n_gen = 5324, tg = 7.26 t/s, tg_3s = 28.52 t/s
llama-server | 10998.21.365.784 I slot print_timing: id 1 | task 2783444 | n_gen = 102, tg = 24.22 t/s, tg_3s = 24.46 t/s
llama-server | 10998.22.804.430 I slot print_timing: id 0 | task 2781837 | n_gen = 5429, tg = 7.37 t/s, tg_3s = 34.18 t/s
llama-server | 10998.24.446.972 I slot print_timing: id 1 | task 2783444 | n_gen = 218, tg = 29.93 t/s, tg_3s = 37.65 t/s
llama-server | 10998.25.886.939 I slot print_timing: id 0 | task 2781837 | n_gen = 5549, tg = 7.50 t/s, tg_3s = 38.93 t/s
llama-server | 10998.27.527.935 I slot print_timing: id 1 | task 2783444 | n_gen = 347, tg = 33.49 t/s, tg_3s = 41.87 t/s
llama-server | 10998.28.976.769 I slot print_timing: id 0 | task 2781837 | n_gen = 5671, tg = 7.63 t/s, tg_3s = 39.48 t/s
llama-server | 10998.30.625.362 I slot print_timing: id 1 | task 2783444 | n_gen = 509, tg = 37.83 t/s, tg_3s = 52.30 t/s
llama-server | 10998.31.989.185 I slot print_timing: id 0 | task 2781837 | n_gen = 5773, tg = 7.74 t/s, tg_3s = 33.86 t/s
llama-server | 10998.33.439.796 I slot print_timing: id 1 | task 2783444 | prompt eval time = 57696.03 ms / 40849 tokens ( 1.41 ms per token, 708.00 tokens per second)
llama-server | 10998.33.439.799 I slot print_timing: id 1 | task 2783444 | eval time = 16244.10 ms / 640 tokens ( 25.42 ms per token, 39.34 tokens per second)
llama-server | 10998.33.439.800 I slot print_timing: id 1 | task 2783444 | total time = 73940.13 ms / 41489 tokens
llama-server | 10998.33.439.800 I slot print_timing: id 1 | task 2783444 | graphs reused = 2696055
llama-server | 10998.33.439.804 I slot print_timing: id 1 | task 2783444 | draft acceptance = 0.56071 ( 471 accepted / 840 generated), mean len = 3.80
llama-server | 10998.33.441.061 I slot release: id 1 | task 2783444 | stop processing: n_tokens = 41488, truncated = 0
llama-server | 10998.35.025.861 I slot print_timing: id 0 | task 2781837 | n_gen = 5886, tg = 7.86 t/s, tg_3s = 37.21 t/s
llama-server | 10998.38.058.615 I slot print_timing: id 0 | task 2781837 | n_gen = 6067, tg = 8.07 t/s, tg_3s = 59.68 t/s
llama-server | 10998.41.083.497 I slot print_timing: id 0 | task 2781837 | n_gen = 6194, tg = 8.20 t/s, tg_3s = 41.99 t/s
llama-server | 10998.44.106.393 I slot print_timing: id 0 | task 2781837 | n_gen = 6302, tg = 8.31 t/s, tg_3s = 35.73 t/s
llama-server | 10998.47.129.509 I slot print_timing: id 0 | task 2781837 | n_gen = 6429, tg = 8.45 t/s, tg_3s = 42.01 t/s
llama-server | 10998.50.150.407 I slot print_timing: id 0 | task 2781837 | n_gen = 6544, tg = 8.57 t/s, tg_3s = 38.07 t/s
llama-server | 10998.52.790.943 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 659929281113
llama-server | 10998.52.793.092 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2129.125 MiB)
llama-server | 10998.55.108.345 I slot launch_slot_: id 1 | task 2783833 | processing task, is_child = 0
llama-server | 10998.57.983.420 I slot print_timing: id 0 | task 2781837 | n_gen = 6665, tg = 8.63 t/s, tg_3s = 15.45 t/s
llama-server | 10999.00.822.520 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.55 s / 735.27 tokens per second
llama-server | 10999.03.665.431 I slot print_timing: id 0 | task 2781837 | n_gen = 6673, tg = 8.58 t/s, tg_3s = 1.41 t/s
llama-server | 10999.03.675.739 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.41 s / 728.57 tokens per second
llama-server | 10999.06.501.616 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.23 s / 727.07 tokens per second
llama-server | 10999.09.318.028 I slot print_timing: id 0 | task 2781837 | n_gen = 6685, tg = 8.54 t/s, tg_3s = 2.12 t/s
llama-server | 10999.09.327.776 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.06 s / 726.09 tokens per second
llama-server | 10999.12.163.091 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.89 s / 725.51 tokens per second
llama-server | 10999.14.982.561 I slot print_timing: id 0 | task 2781837 | n_gen = 6697, tg = 8.49 t/s, tg_3s = 2.12 t/s
llama-server | 10999.14.992.338 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.72 s / 724.68 tokens per second
llama-server | 10999.17.821.855 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.55 s / 724.32 tokens per second
llama-server | 10999.20.641.042 I slot print_timing: id 0 | task 2781837 | n_gen = 6709, tg = 8.44 t/s, tg_3s = 2.12 t/s
llama-server | 10999.20.650.933 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.38 s / 724.06 tokens per second
llama-server | 10999.23.481.178 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 20420, progress = 0.50, t = 28.21 s / 723.78 tokens per second
llama-server | 10999.26.299.666 I slot print_timing: id 0 | task 2781837 | n_gen = 6721, tg = 8.40 t/s, tg_3s = 2.12 t/s
llama-server | 10999.26.309.577 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 22462, progress = 0.55, t = 31.04 s / 723.60 tokens per second
llama-server | 10999.29.139.420 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 24504, progress = 0.60, t = 33.87 s / 723.44 tokens per second
llama-server | 10999.31.958.139 I slot print_timing: id 0 | task 2781837 | n_gen = 6733, tg = 8.36 t/s, tg_3s = 2.12 t/s
llama-server | 10999.31.967.835 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 26546, progress = 0.65, t = 36.70 s / 723.32 tokens per second
llama-server | 10999.34.799.333 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 28588, progress = 0.70, t = 39.53 s / 723.21 tokens per second
llama-server | 10999.37.623.130 I slot print_timing: id 0 | task 2781837 | n_gen = 6745, tg = 8.31 t/s, tg_3s = 2.12 t/s
llama-server | 10999.37.632.753 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 30630, progress = 0.75, t = 42.36 s / 723.04 tokens per second
llama-server | 10999.40.465.170 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 32672, progress = 0.80, t = 45.20 s / 722.88 tokens per second
llama-server | 10999.43.285.662 I slot print_timing: id 0 | task 2781837 | n_gen = 6757, tg = 8.27 t/s, tg_3s = 2.12 t/s
llama-server | 10999.43.295.624 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 34714, progress = 0.85, t = 48.03 s / 722.79 tokens per second
llama-server | 10999.46.129.663 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 36756, progress = 0.90, t = 50.86 s / 722.69 tokens per second
llama-server | 10999.48.953.758 I slot print_timing: id 0 | task 2781837 | n_gen = 6769, tg = 8.23 t/s, tg_3s = 2.12 t/s
llama-server | 10999.48.963.216 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 38798, progress = 0.95, t = 53.70 s / 722.55 tokens per second
llama-server | 10999.51.015.172 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 40212, progress = 0.99, t = 55.79 s / 720.82 tokens per second
llama-server | 10999.52.097.396 I slot print_timing: id 0 | task 2781837 | n_gen = 6781, tg = 8.21 t/s, tg_3s = 3.82 t/s
llama-server | 10999.52.106.555 I slot print_timing: id 1 | task 2783833 | prompt processing, n_tokens = 40724, progress = 1.00, t = 56.94 s / 715.27 tokens per second
llama-server | 10999.55.185.250 I slot print_timing: id 0 | task 2781837 | n_gen = 6900, tg = 8.32 t/s, tg_3s = 38.54 t/s
llama-server | 10999.56.245.811 I slot print_timing: id 1 | task 2783833 | n_gen = 100, tg = 26.73 t/s, tg_3s = 27.00 t/s
llama-server | 10999.58.267.011 I slot print_timing: id 0 | task 2781837 | n_gen = 7080, tg = 8.51 t/s, tg_3s = 58.41 t/s
llama-server | 10999.59.329.089 I slot print_timing: id 1 | task 2783833 | n_gen = 188, tg = 27.55 t/s, tg_3s = 28.54 t/s
llama-server | 11000.01.353.687 I slot print_timing: id 0 | task 2781837 | n_gen = 7268, tg = 8.70 t/s, tg_3s = 60.91 t/s
llama-server | 11000.02.416.293 I slot print_timing: id 1 | task 2783833 | n_gen = 259, tg = 26.13 t/s, tg_3s = 23.00 t/s
llama-server | 11000.04.443.946 I slot print_timing: id 0 | task 2781837 | n_gen = 7460, tg = 8.90 t/s, tg_3s = 62.13 t/s
llama-server | 11000.05.506.313 I slot print_timing: id 1 | task 2783833 | n_gen = 328, tg = 25.22 t/s, tg_3s = 22.33 t/s
llama-server | 11000.07.536.660 I slot print_timing: id 0 | task 2781837 | n_gen = 7602, tg = 9.03 t/s, tg_3s = 45.91 t/s
llama-server | 11000.08.593.341 I slot print_timing: id 1 | task 2783833 | n_gen = 399, tg = 24.80 t/s, tg_3s = 23.00 t/s
llama-server | 11000.10.616.190 I slot print_timing: id 0 | task 2781837 | n_gen = 7691, tg = 9.11 t/s, tg_3s = 28.90 t/s
llama-server | 11000.11.677.381 I slot print_timing: id 1 | task 2783833 | n_gen = 510, tg = 26.60 t/s, tg_3s = 35.99 t/s
llama-server | 11000.13.692.083 I slot print_timing: id 0 | task 2781837 | n_gen = 7794, tg = 9.20 t/s, tg_3s = 33.49 t/s
llama-server | 11000.14.754.602 I slot print_timing: id 1 | task 2783833 | n_gen = 617, tg = 27.73 t/s, tg_3s = 34.77 t/s
llama-server | 11000.16.770.927 I slot print_timing: id 0 | task 2781837 | n_gen = 7877, tg = 9.26 t/s, tg_3s = 26.96 t/s
llama-server | 11000.17.831.141 I slot print_timing: id 1 | task 2783833 | n_gen = 716, tg = 28.27 t/s, tg_3s = 32.18 t/s
llama-server | 11000.19.847.114 I slot print_timing: id 0 | task 2781837 | n_gen = 7976, tg = 9.34 t/s, tg_3s = 32.18 t/s
llama-server | 11000.20.906.233 I slot print_timing: id 1 | task 2783833 | n_gen = 808, tg = 28.45 t/s, tg_3s = 29.92 t/s
llama-server | 11000.22.922.712 I slot print_timing: id 0 | task 2781837 | n_gen = 8062, tg = 9.41 t/s, tg_3s = 27.96 t/s
llama-server | 11000.23.984.114 I slot print_timing: id 1 | task 2783833 | n_gen = 906, tg = 28.78 t/s, tg_3s = 31.84 t/s
llama-server | 11000.26.002.315 I slot print_timing: id 0 | task 2781837 | n_gen = 8157, tg = 9.49 t/s, tg_3s = 30.85 t/s
llama-server | 11000.27.059.694 I slot print_timing: id 1 | task 2783833 | n_gen = 993, tg = 28.74 t/s, tg_3s = 28.29 t/s
llama-server | 11000.29.083.669 I slot print_timing: id 0 | task 2781837 | n_gen = 8289, tg = 9.61 t/s, tg_3s = 42.84 t/s
llama-server | 11000.30.150.509 I slot print_timing: id 1 | task 2783833 | n_gen = 1092, tg = 29.01 t/s, tg_3s = 32.03 t/s
llama-server | 11000.32.178.083 I slot print_timing: id 0 | task 2781837 | n_gen = 8477, tg = 9.79 t/s, tg_3s = 60.75 t/s
llama-server | 11000.33.243.640 I slot print_timing: id 1 | task 2783833 | n_gen = 1184, tg = 29.07 t/s, tg_3s = 29.74 t/s
llama-server | 11000.35.272.450 I slot print_timing: id 0 | task 2781837 | n_gen = 8664, tg = 9.97 t/s, tg_3s = 60.43 t/s
llama-server | 11000.36.341.183 I slot print_timing: id 1 | task 2783833 | n_gen = 1273, tg = 29.04 t/s, tg_3s = 28.73 t/s
llama-server | 11000.38.275.839 I slot print_timing: id 0 | task 2781837 | n_gen = 8850, tg = 10.15 t/s, tg_3s = 61.93 t/s
llama-server | 11000.39.342.759 I slot print_timing: id 1 | task 2783833 | n_gen = 1367, tg = 29.19 t/s, tg_3s = 31.32 t/s
llama-server | 11000.41.278.407 I slot print_timing: id 0 | task 2781837 | n_gen = 9036, tg = 10.33 t/s, tg_3s = 61.95 t/s
llama-server | 11000.42.343.402 I slot print_timing: id 1 | task 2783833 | n_gen = 1473, tg = 29.56 t/s, tg_3s = 35.33 t/s
llama-server | 11000.44.362.386 I slot print_timing: id 0 | task 2781837 | n_gen = 9165, tg = 10.44 t/s, tg_3s = 41.83 t/s
llama-server | 11000.45.352.638 I slot print_timing: id 1 | task 2783833 | n_gen = 1580, tg = 29.90 t/s, tg_3s = 35.56 t/s
llama-server | 11000.47.389.739 I slot print_timing: id 0 | task 2781837 | n_gen = 9294, tg = 10.55 t/s, tg_3s = 42.61 t/s
llama-server | 11000.48.382.677 I slot print_timing: id 1 | task 2783833 | n_gen = 1675, tg = 29.98 t/s, tg_3s = 31.35 t/s
llama-server | 11000.50.411.189 I slot print_timing: id 0 | task 2781837 | n_gen = 9395, tg = 10.62 t/s, tg_3s = 33.43 t/s
llama-server | 11000.51.474.989 I slot print_timing: id 1 | task 2783833 | n_gen = 1770, tg = 30.02 t/s, tg_3s = 30.72 t/s
llama-server | 11000.53.432.682 I slot print_timing: id 0 | task 2781837 | n_gen = 9487, tg = 10.69 t/s, tg_3s = 30.45 t/s
llama-server | 11000.54.500.489 I slot print_timing: id 1 | task 2783833 | n_gen = 1838, tg = 29.65 t/s, tg_3s = 22.48 t/s
llama-server | 11000.55.664.625 I slot print_timing: id 1 | task 2783833 | prompt eval time = 57421.92 ms / 40728 tokens ( 1.41 ms per token, 709.28 tokens per second)
llama-server | 11000.55.664.629 I slot print_timing: id 1 | task 2783833 | eval time = 63122.31 ms / 1878 tokens ( 33.63 ms per token, 29.74 tokens per second)
llama-server | 11000.55.664.630 I slot print_timing: id 1 | task 2783833 | total time = 120544.22 ms / 42606 tokens
llama-server | 11000.55.664.630 I slot print_timing: id 1 | task 2783833 | graphs reused = 2696940
llama-server | 11000.55.664.633 I slot print_timing: id 1 | task 2783833 | draft acceptance = 0.37519 ( 1225 accepted / 3265 generated), mean len = 2.88
llama-server | 11000.55.665.778 I slot release: id 1 | task 2783833 | stop processing: n_tokens = 42606, truncated = 0
llama-server | 11000.56.475.632 I slot print_timing: id 0 | task 2781837 | n_gen = 9591, tg = 10.77 t/s, tg_3s = 34.18 t/s
llama-server | 11000.57.085.678 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 660071505829
llama-server | 11000.59.927.560 I slot launch_slot_: id 1 | task 2784523 | processing task, is_child = 0
llama-server | 11001.02.852.596 I slot print_timing: id 0 | task 2781837 | n_gen = 9613, tg = 10.72 t/s, tg_3s = 3.45 t/s
llama-server | 11001.05.732.086 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.64 s / 723.52 tokens per second
llama-server | 11001.08.617.113 I slot print_timing: id 0 | task 2781837 | n_gen = 9616, tg = 10.66 t/s, tg_3s = 0.52 t/s
llama-server | 11001.08.627.399 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.54 s / 717.26 tokens per second
llama-server | 11001.11.498.407 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.41 s / 715.76 tokens per second
llama-server | 11001.14.358.655 I slot print_timing: id 0 | task 2781837 | n_gen = 9620, tg = 10.59 t/s, tg_3s = 0.70 t/s
llama-server | 11001.14.368.512 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.28 s / 714.86 tokens per second
llama-server | 11001.17.247.204 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 12252, progress = 0.30, t = 17.15 s / 714.32 tokens per second
llama-server | 11001.20.105.048 I slot print_timing: id 0 | task 2781837 | n_gen = 9626, tg = 10.53 t/s, tg_3s = 1.04 t/s
llama-server | 11001.20.115.139 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 14294, progress = 0.35, t = 20.03 s / 713.63 tokens per second
llama-server | 11001.22.987.155 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.90 s / 713.35 tokens per second
llama-server | 11001.25.848.590 I slot print_timing: id 0 | task 2781837 | n_gen = 9633, tg = 10.47 t/s, tg_3s = 1.22 t/s
llama-server | 11001.25.858.561 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.77 s / 713.10 tokens per second
llama-server | 11001.28.727.172 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 20420, progress = 0.50, t = 28.64 s / 712.95 tokens per second
llama-server | 11001.31.586.252 I slot print_timing: id 0 | task 2781837 | n_gen = 9640, tg = 10.42 t/s, tg_3s = 1.22 t/s
llama-server | 11001.31.595.764 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 22462, progress = 0.55, t = 31.51 s / 712.85 tokens per second
llama-server | 11001.34.465.981 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 24504, progress = 0.60, t = 34.38 s / 712.75 tokens per second
llama-server | 11001.37.325.576 I slot print_timing: id 0 | task 2781837 | n_gen = 9649, tg = 10.36 t/s, tg_3s = 1.57 t/s
llama-server | 11001.37.335.768 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 26546, progress = 0.65, t = 37.25 s / 712.64 tokens per second
llama-server | 11001.40.206.476 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 28588, progress = 0.70, t = 40.12 s / 712.56 tokens per second
llama-server | 11001.43.067.600 I slot print_timing: id 0 | task 2781837 | n_gen = 9658, tg = 10.31 t/s, tg_3s = 1.57 t/s
llama-server | 11001.43.077.741 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 30630, progress = 0.75, t = 42.99 s / 712.46 tokens per second
llama-server | 11001.45.948.652 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 32672, progress = 0.80, t = 45.86 s / 712.39 tokens per second
llama-server | 11001.48.811.146 I slot print_timing: id 0 | task 2781837 | n_gen = 9661, tg = 10.25 t/s, tg_3s = 0.52 t/s
llama-server | 11001.48.821.346 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 34714, progress = 0.86, t = 48.73 s / 712.34 tokens per second
llama-server | 11001.51.692.923 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 36756, progress = 0.91, t = 51.61 s / 712.23 tokens per second
llama-server | 11001.54.554.752 I slot print_timing: id 0 | task 2781837 | n_gen = 9673, tg = 10.20 t/s, tg_3s = 2.09 t/s
llama-server | 11001.54.564.477 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 38798, progress = 0.96, t = 54.48 s / 712.16 tokens per second
llama-server | 11001.56.468.301 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 40073, progress = 0.99, t = 56.43 s / 710.13 tokens per second
llama-server | 11001.57.642.706 I slot print_timing: id 0 | task 2781837 | n_gen = 9675, tg = 10.17 t/s, tg_3s = 0.65 t/s
llama-server | 11001.57.653.081 I slot print_timing: id 1 | task 2784523 | prompt processing, n_tokens = 40585, progress = 1.00, t = 57.66 s / 703.83 tokens per second
llama-server | 11002.00.658.794 I slot print_timing: id 0 | task 2781837 | n_gen = 9755, tg = 10.22 t/s, tg_3s = 26.52 t/s
llama-server | 11002.01.817.154 I slot print_timing: id 1 | task 2784523 | n_gen = 102, tg = 27.91 t/s, tg_3s = 28.18 t/s
llama-server | 11002.03.739.145 I slot print_timing: id 0 | task 2781837 | n_gen = 9839, tg = 10.27 t/s, tg_3s = 27.27 t/s
llama-server | 11002.04.893.393 I slot print_timing: id 1 | task 2784523 | n_gen = 167, tg = 24.79 t/s, tg_3s = 21.13 t/s
llama-server | 11002.06.820.243 I slot print_timing: id 0 | task 2781837 | n_gen = 9955, tg = 10.36 t/s, tg_3s = 37.65 t/s
llama-server | 11002.07.977.172 I slot print_timing: id 1 | task 2784523 | n_gen = 240, tg = 24.44 t/s, tg_3s = 23.67 t/s
llama-server | 11002.09.907.122 I slot print_timing: id 0 | task 2781837 | n_gen = 10081, tg = 10.46 t/s, tg_3s = 40.82 t/s
llama-server | 11002.11.066.838 I slot print_timing: id 1 | task 2784523 | n_gen = 334, tg = 25.88 t/s, tg_3s = 30.42 t/s
llama-server | 11002.12.920.715 I slot print_timing: id 0 | task 2781837 | n_gen = 10193, tg = 10.54 t/s, tg_3s = 37.16 t/s
llama-server | 11002.14.081.956 I slot print_timing: id 1 | task 2784523 | n_gen = 455, tg = 28.58 t/s, tg_3s = 40.13 t/s
llama-server | 11002.16.016.841 I slot print_timing: id 0 | task 2781837 | n_gen = 10353, tg = 10.67 t/s, tg_3s = 51.68 t/s
llama-server | 11002.17.083.286 I slot print_timing: id 1 | task 2784523 | n_gen = 563, tg = 29.76 t/s, tg_3s = 35.98 t/s
llama-server | 11002.19.031.431 I slot print_timing: id 0 | task 2781837 | n_gen = 10504, tg = 10.80 t/s, tg_3s = 50.09 t/s
llama-server | 11002.19.131.282 I slot print_timing: id 1 | task 2784523 | prompt eval time = 58258.66 ms / 40589 tokens ( 1.44 ms per token, 696.70 tokens per second)
llama-server | 11002.19.131.284 I slot print_timing: id 1 | task 2784523 | eval time = 20932.90 ms / 675 tokens ( 31.06 ms per token, 32.20 tokens per second)
llama-server | 11002.19.131.285 I slot print_timing: id 1 | task 2784523 | total time = 79191.56 ms / 41264 tokens
llama-server | 11002.19.131.286 I slot print_timing: id 1 | task 2784523 | graphs reused = 2697206
llama-server | 11002.19.131.289 I slot print_timing: id 1 | task 2784523 | draft acceptance = 0.42500 ( 459 accepted / 1080 generated), mean len = 3.12
llama-server | 11002.19.132.583 I slot release: id 1 | task 2784523 | stop processing: n_tokens = 41264, truncated = 0
llama-server | 11002.22.086.944 I slot print_timing: id 0 | task 2781837 | n_gen = 10617, tg = 10.88 t/s, tg_3s = 36.98 t/s
llama-server | 11002.25.111.773 I slot print_timing: id 0 | task 2781837 | n_gen = 10704, tg = 10.93 t/s, tg_3s = 28.76 t/s
llama-server | 11002.28.139.055 I slot print_timing: id 0 | task 2781837 | n_gen = 10804, tg = 11.00 t/s, tg_3s = 33.03 t/s
llama-server | 11002.31.167.872 I slot print_timing: id 0 | task 2781837 | n_gen = 10888, tg = 11.05 t/s, tg_3s = 27.73 t/s
llama-server | 11002.34.219.000 I slot print_timing: id 0 | task 2781837 | n_gen = 10994, tg = 11.13 t/s, tg_3s = 34.74 t/s
llama-server | 11002.36.478.130 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 660154972634
llama-server | 11002.36.480.260 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2151.102 MiB)
llama-server | 11002.39.400.379 I slot launch_slot_: id 1 | task 2784939 | processing task, is_child = 0
llama-server | 11002.42.293.870 I slot print_timing: id 0 | task 2781837 | n_gen = 11076, tg = 11.12 t/s, tg_3s = 10.15 t/s
llama-server | 11002.45.144.885 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.59 s / 731.07 tokens per second
llama-server | 11002.48.000.731 I slot print_timing: id 0 | task 2781837 | n_gen = 11083, tg = 11.06 t/s, tg_3s = 1.23 t/s
llama-server | 11002.48.011.478 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.45 s / 724.73 tokens per second
llama-server | 11002.50.853.715 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.30 s / 723.11 tokens per second
llama-server | 11002.53.683.422 I slot print_timing: id 0 | task 2781837 | n_gen = 11090, tg = 11.01 t/s, tg_3s = 1.23 t/s
llama-server | 11002.53.693.553 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.14 s / 722.27 tokens per second
llama-server | 11002.56.535.672 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.98 s / 721.62 tokens per second
llama-server | 11002.59.368.729 I slot print_timing: id 0 | task 2781837 | n_gen = 11093, tg = 10.95 t/s, tg_3s = 0.53 t/s
llama-server | 11002.59.378.873 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.82 s / 721.16 tokens per second
llama-server | 11003.02.224.481 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.66 s / 720.78 tokens per second
llama-server | 11003.05.058.594 I slot print_timing: id 0 | task 2781837 | n_gen = 11101, tg = 10.89 t/s, tg_3s = 1.41 t/s
llama-server | 11003.05.068.843 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.51 s / 720.43 tokens per second
llama-server | 11003.07.912.750 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 20420, progress = 0.50, t = 28.35 s / 720.16 tokens per second
llama-server | 11003.10.746.883 I slot print_timing: id 0 | task 2781837 | n_gen = 11108, tg = 10.84 t/s, tg_3s = 1.23 t/s
llama-server | 11003.10.757.383 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 22462, progress = 0.55, t = 31.20 s / 719.95 tokens per second
llama-server | 11003.13.601.697 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 24504, progress = 0.60, t = 34.04 s / 719.78 tokens per second
llama-server | 11003.16.436.368 I slot print_timing: id 0 | task 2781837 | n_gen = 11113, tg = 10.79 t/s, tg_3s = 0.88 t/s
llama-server | 11003.16.447.158 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 26546, progress = 0.65, t = 36.89 s / 719.62 tokens per second
llama-server | 11003.19.295.092 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 28588, progress = 0.70, t = 39.74 s / 719.46 tokens per second
llama-server | 11003.22.136.436 I slot print_timing: id 0 | task 2781837 | n_gen = 11117, tg = 10.73 t/s, tg_3s = 0.70 t/s
llama-server | 11003.22.146.579 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 30630, progress = 0.75, t = 42.58 s / 719.28 tokens per second
llama-server | 11003.24.994.336 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 32672, progress = 0.80, t = 45.44 s / 719.08 tokens per second
llama-server | 11003.27.828.608 I slot print_timing: id 0 | task 2781837 | n_gen = 11123, tg = 10.68 t/s, tg_3s = 1.05 t/s
llama-server | 11003.27.839.308 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 34714, progress = 0.85, t = 48.28 s / 718.99 tokens per second
llama-server | 11003.30.687.401 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 36756, progress = 0.90, t = 51.13 s / 718.88 tokens per second
llama-server | 11003.33.525.913 I slot print_timing: id 0 | task 2781837 | n_gen = 11130, tg = 10.63 t/s, tg_3s = 1.23 t/s
llama-server | 11003.33.536.453 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 38798, progress = 0.95, t = 53.98 s / 718.77 tokens per second
llama-server | 11003.35.701.626 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 40311, progress = 0.99, t = 56.18 s / 717.57 tokens per second
llama-server | 11003.36.800.032 I slot print_timing: id 0 | task 2781837 | n_gen = 11134, tg = 10.60 t/s, tg_3s = 1.22 t/s
llama-server | 11003.36.809.792 I slot print_timing: id 1 | task 2784939 | prompt processing, n_tokens = 40823, progress = 1.00, t = 57.35 s / 711.85 tokens per second
llama-server | 11003.39.819.689 I slot print_timing: id 0 | task 2781837 | n_gen = 11229, tg = 10.66 t/s, tg_3s = 31.46 t/s
llama-server | 11003.40.595.088 I slot print_timing: id 1 | task 2784939 | n_gen = 102, tg = 30.30 t/s, tg_3s = 30.60 t/s
llama-server | 11003.42.911.351 I slot print_timing: id 0 | task 2781837 | n_gen = 11321, tg = 10.71 t/s, tg_3s = 29.76 t/s
llama-server | 11003.43.689.785 I slot print_timing: id 1 | task 2784939 | n_gen = 202, tg = 31.27 t/s, tg_3s = 32.31 t/s
llama-server | 11003.45.942.467 I slot print_timing: id 0 | task 2781837 | n_gen = 11420, tg = 10.78 t/s, tg_3s = 32.66 t/s
llama-server | 11003.46.728.266 I slot print_timing: id 1 | task 2784939 | n_gen = 295, tg = 31.06 t/s, tg_3s = 30.61 t/s
llama-server | 11003.48.982.759 I slot print_timing: id 0 | task 2781837 | n_gen = 11568, tg = 10.88 t/s, tg_3s = 48.68 t/s
llama-server | 11003.49.763.898 I slot print_timing: id 1 | task 2784939 | n_gen = 385, tg = 30.71 t/s, tg_3s = 29.65 t/s
llama-server | 11003.52.027.371 I slot print_timing: id 0 | task 2781837 | n_gen = 11732, tg = 11.01 t/s, tg_3s = 53.87 t/s
llama-server | 11003.52.803.204 I slot print_timing: id 1 | task 2784939 | n_gen = 482, tg = 30.95 t/s, tg_3s = 31.92 t/s
llama-server | 11003.55.036.416 I slot print_timing: id 0 | task 2781837 | n_gen = 11820, tg = 11.06 t/s, tg_3s = 29.25 t/s
llama-server | 11003.55.840.152 I slot print_timing: id 1 | task 2784939 | n_gen = 574, tg = 30.84 t/s, tg_3s = 30.29 t/s
llama-server | 11003.58.080.394 I slot print_timing: id 0 | task 2781837 | n_gen = 11949, tg = 11.15 t/s, tg_3s = 42.38 t/s
llama-server | 11003.58.860.534 I slot print_timing: id 1 | task 2784939 | n_gen = 658, tg = 30.42 t/s, tg_3s = 27.81 t/s
llama-server | 11004.01.125.504 I slot print_timing: id 0 | task 2781837 | n_gen = 12065, tg = 11.22 t/s, tg_3s = 38.09 t/s
llama-server | 11004.01.903.331 I slot print_timing: id 1 | task 2784939 | n_gen = 752, tg = 30.48 t/s, tg_3s = 30.89 t/s
llama-server | 11004.04.175.427 I slot print_timing: id 0 | task 2781837 | n_gen = 12142, tg = 11.26 t/s, tg_3s = 25.25 t/s
llama-server | 11004.04.954.997 I slot print_timing: id 1 | task 2784939 | n_gen = 850, tg = 30.66 t/s, tg_3s = 32.11 t/s
llama-server | 11004.07.195.757 I slot print_timing: id 0 | task 2781837 | n_gen = 12228, tg = 11.31 t/s, tg_3s = 28.47 t/s
llama-server | 11004.08.000.194 I slot print_timing: id 1 | task 2784939 | n_gen = 938, tg = 30.48 t/s, tg_3s = 28.90 t/s
llama-server | 11004.10.245.910 I slot print_timing: id 0 | task 2781837 | n_gen = 12327, tg = 11.37 t/s, tg_3s = 32.46 t/s
llama-server | 11004.11.030.023 I slot print_timing: id 1 | task 2784939 | n_gen = 1046, tg = 30.95 t/s, tg_3s = 35.65 t/s
llama-server | 11004.13.306.270 I slot print_timing: id 0 | task 2781837 | n_gen = 12434, tg = 11.44 t/s, tg_3s = 34.96 t/s
llama-server | 11004.14.089.933 I slot print_timing: id 1 | task 2784939 | n_gen = 1162, tg = 31.52 t/s, tg_3s = 37.91 t/s
llama-server | 11004.16.369.029 I slot print_timing: id 0 | task 2781837 | n_gen = 12526, tg = 11.49 t/s, tg_3s = 30.04 t/s
llama-server | 11004.17.155.249 I slot print_timing: id 1 | task 2784939 | n_gen = 1274, tg = 31.91 t/s, tg_3s = 36.54 t/s
llama-server | 11004.19.434.572 I slot print_timing: id 0 | task 2781837 | n_gen = 12646, tg = 11.57 t/s, tg_3s = 39.14 t/s
llama-server | 11004.20.218.496 I slot print_timing: id 1 | task 2784939 | n_gen = 1349, tg = 31.38 t/s, tg_3s = 24.48 t/s
llama-server | 11004.22.469.734 I slot print_timing: id 0 | task 2781837 | n_gen = 12727, tg = 11.61 t/s, tg_3s = 26.69 t/s
llama-server | 11004.23.258.014 I slot print_timing: id 1 | task 2784939 | n_gen = 1437, tg = 31.22 t/s, tg_3s = 28.95 t/s
llama-server | 11004.25.544.662 I slot print_timing: id 0 | task 2781837 | n_gen = 12862, tg = 11.70 t/s, tg_3s = 43.90 t/s
llama-server | 11004.26.333.058 I slot print_timing: id 1 | task 2784939 | n_gen = 1508, tg = 30.71 t/s, tg_3s = 23.09 t/s
llama-server | 11004.28.621.000 I slot print_timing: id 0 | task 2781837 | n_gen = 13005, tg = 11.80 t/s, tg_3s = 46.48 t/s
llama-server | 11004.29.411.658 I slot print_timing: id 1 | task 2784939 | n_gen = 1595, tg = 30.57 t/s, tg_3s = 28.26 t/s
llama-server | 11004.31.703.096 I slot print_timing: id 0 | task 2781837 | n_gen = 13100, tg = 11.85 t/s, tg_3s = 30.82 t/s
llama-server | 11004.32.493.645 I slot print_timing: id 1 | task 2784939 | n_gen = 1685, tg = 30.49 t/s, tg_3s = 29.20 t/s
llama-server | 11004.32.888.809 I slot print_timing: id 1 | task 2784939 | prompt eval time = 57849.79 ms / 40827 tokens ( 1.42 ms per token, 705.74 tokens per second)
llama-server | 11004.32.888.812 I slot print_timing: id 1 | task 2784939 | eval time = 55627.31 ms / 1703 tokens ( 32.68 ms per token, 30.60 tokens per second)
llama-server | 11004.32.888.813 I slot print_timing: id 1 | task 2784939 | total time = 113477.10 ms / 42530 tokens
llama-server | 11004.32.888.814 I slot print_timing: id 1 | task 2784939 | graphs reused = 2697972
llama-server | 11004.32.888.817 I slot print_timing: id 1 | task 2784939 | draft acceptance = 0.40141 ( 1136 accepted / 2830 generated), mean len = 3.01
llama-server | 11004.32.890.049 I slot release: id 1 | task 2784939 | stop processing: n_tokens = 42529, truncated = 0
llama-server | 11004.34.210.840 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 660288730101
llama-server | 11004.34.213.082 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1970.328 MiB)
llama-server | 11004.37.609.956 I slot launch_slot_: id 1 | task 2785541 | processing task, is_child = 0
llama-server | 11004.40.639.655 I slot print_timing: id 0 | task 2781837 | n_gen = 13199, tg = 11.84 t/s, tg_3s = 11.08 t/s
llama-server | 11004.43.630.897 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.86 s / 696.69 tokens per second
llama-server | 11004.46.627.526 I slot print_timing: id 0 | task 2781837 | n_gen = 13205, tg = 11.79 t/s, tg_3s = 1.00 t/s
llama-server | 11004.46.637.649 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.87 s / 690.68 tokens per second
llama-server | 11004.49.616.281 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.85 s / 689.36 tokens per second
llama-server | 11004.52.586.473 I slot print_timing: id 0 | task 2781837 | n_gen = 13210, tg = 11.73 t/s, tg_3s = 0.84 t/s
llama-server | 11004.52.596.682 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.83 s / 688.51 tokens per second
llama-server | 11004.55.580.163 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 12252, progress = 0.30, t = 17.81 s / 687.89 tokens per second
llama-server | 11004.58.551.096 I slot print_timing: id 0 | task 2781837 | n_gen = 13219, tg = 11.67 t/s, tg_3s = 1.51 t/s
llama-server | 11004.58.560.828 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 14294, progress = 0.35, t = 20.79 s / 687.44 tokens per second
llama-server | 11005.01.544.147 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 16336, progress = 0.40, t = 23.78 s / 687.09 tokens per second
llama-server | 11005.04.514.047 I slot print_timing: id 0 | task 2781837 | n_gen = 13222, tg = 11.61 t/s, tg_3s = 0.50 t/s
llama-server | 11005.04.524.266 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 18378, progress = 0.45, t = 26.76 s / 686.86 tokens per second
llama-server | 11005.07.505.638 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 20420, progress = 0.50, t = 29.74 s / 686.69 tokens per second
llama-server | 11005.10.477.749 I slot print_timing: id 0 | task 2781837 | n_gen = 13225, tg = 11.56 t/s, tg_3s = 0.50 t/s
llama-server | 11005.10.488.074 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 22462, progress = 0.55, t = 32.72 s / 686.49 tokens per second
llama-server | 11005.13.470.909 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 24504, progress = 0.60, t = 35.70 s / 686.33 tokens per second
llama-server | 11005.16.444.099 I slot print_timing: id 0 | task 2781837 | n_gen = 13231, tg = 11.50 t/s, tg_3s = 1.01 t/s
llama-server | 11005.16.454.093 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 26546, progress = 0.65, t = 38.69 s / 686.20 tokens per second
llama-server | 11005.19.440.651 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 28588, progress = 0.70, t = 41.67 s / 686.05 tokens per second
llama-server | 11005.22.414.182 I slot print_timing: id 0 | task 2781837 | n_gen = 13239, tg = 11.45 t/s, tg_3s = 1.34 t/s
llama-server | 11005.22.423.938 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 30630, progress = 0.75, t = 44.66 s / 685.92 tokens per second
llama-server | 11005.25.409.126 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 32672, progress = 0.80, t = 47.64 s / 685.80 tokens per second
llama-server | 11005.28.382.576 I slot print_timing: id 0 | task 2781837 | n_gen = 13244, tg = 11.40 t/s, tg_3s = 0.84 t/s
llama-server | 11005.28.392.804 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 34714, progress = 0.85, t = 50.62 s / 685.71 tokens per second
llama-server | 11005.31.378.174 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 36756, progress = 0.90, t = 53.61 s / 685.62 tokens per second
llama-server | 11005.34.356.877 I slot print_timing: id 0 | task 2781837 | n_gen = 13252, tg = 11.34 t/s, tg_3s = 1.34 t/s
llama-server | 11005.34.367.545 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 38798, progress = 0.95, t = 56.60 s / 685.50 tokens per second
llama-server | 11005.36.898.655 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 40473, progress = 0.99, t = 59.15 s / 684.21 tokens per second
llama-server | 11005.38.115.307 I slot print_timing: id 0 | task 2781837 | n_gen = 13262, tg = 11.32 t/s, tg_3s = 2.66 t/s
llama-server | 11005.38.125.047 I slot print_timing: id 1 | task 2785541 | prompt processing, n_tokens = 40985, progress = 1.00, t = 60.45 s / 678.02 tokens per second
llama-server | 11005.41.210.724 I slot print_timing: id 0 | task 2781837 | n_gen = 13350, tg = 11.36 t/s, tg_3s = 28.43 t/s
llama-server | 11005.41.212.538 I slot print_timing: id 1 | task 2785541 | prompt eval time = 60983.25 ms / 40989 tokens ( 1.49 ms per token, 672.14 tokens per second)
llama-server | 11005.41.212.540 I slot print_timing: id 1 | task 2785541 | eval time = 2607.59 ms / 94 tokens ( 28.04 ms per token, 35.67 tokens per second)
llama-server | 11005.41.212.541 I slot print_timing: id 1 | task 2785541 | total time = 63590.84 ms / 41083 tokens
llama-server | 11005.41.212.541 I slot print_timing: id 1 | task 2785541 | graphs reused = 2698049
llama-server | 11005.41.212.544 I slot print_timing: id 1 | task 2785541 | draft acceptance = 0.51538 ( 67 accepted / 130 generated), mean len = 3.58
llama-server | 11005.41.213.889 I slot release: id 1 | task 2785541 | stop processing: n_tokens = 41082, truncated = 0
llama-server | 11005.42.330.968 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 660357053941
llama-server | 11005.42.333.085 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1948.450 MiB)
llama-server | 11005.44.696.814 I slot launch_slot_: id 1 | task 2785601 | processing task, is_child = 0
llama-server | 11005.47.712.294 I slot print_timing: id 0 | task 2781837 | n_gen = 13376, tg = 11.32 t/s, tg_3s = 4.00 t/s
llama-server | 11005.50.695.512 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.84 s / 699.47 tokens per second
llama-server | 11005.53.682.012 I slot print_timing: id 0 | task 2781837 | n_gen = 13387, tg = 11.27 t/s, tg_3s = 1.84 t/s
llama-server | 11005.53.691.804 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.84 s / 693.13 tokens per second
llama-server | 11005.56.664.001 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.81 s / 691.63 tokens per second
llama-server | 11005.59.629.611 I slot print_timing: id 0 | task 2781837 | n_gen = 13396, tg = 11.22 t/s, tg_3s = 1.51 t/s
llama-server | 11005.59.639.758 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.78 s / 690.58 tokens per second
llama-server | 11006.02.617.676 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 12252, progress = 0.30, t = 17.76 s / 689.77 tokens per second
llama-server | 11006.05.587.914 I slot print_timing: id 0 | task 2781837 | n_gen = 13403, tg = 11.17 t/s, tg_3s = 1.17 t/s
llama-server | 11006.05.597.555 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 14294, progress = 0.35, t = 20.74 s / 689.16 tokens per second
llama-server | 11006.08.576.523 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 16336, progress = 0.40, t = 23.72 s / 688.71 tokens per second
llama-server | 11006.11.544.126 I slot print_timing: id 0 | task 2781837 | n_gen = 13415, tg = 11.13 t/s, tg_3s = 2.01 t/s
llama-server | 11006.11.553.849 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 18378, progress = 0.45, t = 26.70 s / 688.31 tokens per second
llama-server | 11006.14.530.546 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 20420, progress = 0.50, t = 29.68 s / 688.10 tokens per second
llama-server | 11006.17.501.749 I slot print_timing: id 0 | task 2781837 | n_gen = 13427, tg = 11.08 t/s, tg_3s = 2.01 t/s
llama-server | 11006.17.511.463 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 22462, progress = 0.55, t = 32.66 s / 687.82 tokens per second
llama-server | 11006.20.491.914 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 24504, progress = 0.60, t = 35.64 s / 687.60 tokens per second
llama-server | 11006.23.467.735 I slot print_timing: id 0 | task 2781837 | n_gen = 13437, tg = 11.04 t/s, tg_3s = 1.68 t/s
llama-server | 11006.23.477.697 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 26546, progress = 0.66, t = 38.62 s / 687.40 tokens per second
llama-server | 11006.26.459.883 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 28588, progress = 0.71, t = 41.60 s / 687.14 tokens per second
llama-server | 11006.29.431.762 I slot print_timing: id 0 | task 2781837 | n_gen = 13443, tg = 10.99 t/s, tg_3s = 1.01 t/s
llama-server | 11006.29.442.297 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 30630, progress = 0.76, t = 44.59 s / 686.98 tokens per second
llama-server | 11006.32.426.971 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 32672, progress = 0.81, t = 47.57 s / 686.80 tokens per second
llama-server | 11006.35.399.315 I slot print_timing: id 0 | task 2781837 | n_gen = 13448, tg = 10.94 t/s, tg_3s = 0.84 t/s
llama-server | 11006.35.409.646 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 34714, progress = 0.86, t = 50.55 s / 686.67 tokens per second
llama-server | 11006.38.396.014 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 36756, progress = 0.91, t = 53.54 s / 686.51 tokens per second
llama-server | 11006.41.370.740 I slot print_timing: id 0 | task 2781837 | n_gen = 13460, tg = 10.90 t/s, tg_3s = 2.01 t/s
llama-server | 11006.41.380.386 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 38798, progress = 0.96, t = 56.53 s / 686.38 tokens per second
llama-server | 11006.43.289.654 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 39996, progress = 0.99, t = 58.49 s / 683.85 tokens per second
llama-server | 11006.44.454.738 I slot print_timing: id 0 | task 2781837 | n_gen = 13467, tg = 10.88 t/s, tg_3s = 2.27 t/s
llama-server | 11006.44.464.580 I slot print_timing: id 1 | task 2785601 | prompt processing, n_tokens = 40508, progress = 1.00, t = 59.71 s / 678.45 tokens per second
llama-server | 11006.47.551.607 I slot print_timing: id 0 | task 2781837 | n_gen = 13536, tg = 10.90 t/s, tg_3s = 22.28 t/s
llama-server | 11006.48.045.165 I slot print_timing: id 1 | task 2785601 | n_gen = 101, tg = 32.40 t/s, tg_3s = 32.72 t/s
llama-server | 11006.50.601.120 I slot print_timing: id 0 | task 2781837 | n_gen = 13647, tg = 10.97 t/s, tg_3s = 36.40 t/s
llama-server | 11006.51.093.319 I slot print_timing: id 1 | task 2785601 | n_gen = 182, tg = 29.50 t/s, tg_3s = 26.57 t/s
llama-server | 11006.53.648.324 I slot print_timing: id 0 | task 2781837 | n_gen = 13777, tg = 11.04 t/s, tg_3s = 42.66 t/s
llama-server | 11006.54.143.410 I slot print_timing: id 1 | task 2785601 | n_gen = 254, tg = 27.54 t/s, tg_3s = 23.61 t/s
llama-server | 11006.56.704.177 I slot print_timing: id 0 | task 2781837 | n_gen = 13929, tg = 11.14 t/s, tg_3s = 49.74 t/s
llama-server | 11006.57.194.513 I slot print_timing: id 1 | task 2785601 | n_gen = 329, tg = 26.81 t/s, tg_3s = 24.58 t/s
llama-server | 11006.59.771.670 I slot print_timing: id 0 | task 2781837 | n_gen = 14050, tg = 11.21 t/s, tg_3s = 39.45 t/s
llama-server | 11007.00.263.445 I slot print_timing: id 1 | task 2785601 | n_gen = 414, tg = 26.98 t/s, tg_3s = 27.70 t/s
llama-server | 11007.02.826.464 I slot print_timing: id 0 | task 2781837 | n_gen = 14163, tg = 11.27 t/s, tg_3s = 36.99 t/s
llama-server | 11007.03.321.202 I slot print_timing: id 1 | task 2785601 | n_gen = 500, tg = 27.17 t/s, tg_3s = 28.13 t/s
llama-server | 11007.05.882.090 I slot print_timing: id 0 | task 2781837 | n_gen = 14276, tg = 11.33 t/s, tg_3s = 36.98 t/s
llama-server | 11007.06.277.644 W srv stop: cancel task, id_task = 2781837
llama-server | 11007.06.277.977 I slot release: id 0 | task 2781837 | stop processing: n_tokens = 21978, truncated = 0
llama-server | 11007.06.379.421 I slot print_timing: id 1 | task 2785601 | n_gen = 595, tg = 27.73 t/s, tg_3s = 31.06 t/s
llama-server | 11007.09.379.775 I slot print_timing: id 1 | task 2785601 | n_gen = 662, tg = 27.07 t/s, tg_3s = 22.33 t/s
llama-server | 11007.12.467.340 I slot print_timing: id 1 | task 2785601 | n_gen = 776, tg = 28.17 t/s, tg_3s = 36.92 t/s
llama-server | 11007.15.557.898 I slot print_timing: id 1 | task 2785601 | n_gen = 912, tg = 29.77 t/s, tg_3s = 44.00 t/s
llama-server | 11007.16.955.280 I slot print_timing: id 1 | task 2785601 | prompt eval time = 60250.02 ms / 40512 tokens ( 1.49 ms per token, 672.40 tokens per second)
llama-server | 11007.16.955.283 I slot print_timing: id 1 | task 2785601 | eval time = 31996.88 ms / 982 tokens ( 32.62 ms per token, 30.66 tokens per second)
llama-server | 11007.16.955.284 I slot print_timing: id 1 | task 2785601 | total time = 92246.90 ms / 41494 tokens
llama-server | 11007.16.955.284 I slot print_timing: id 1 | task 2785601 | graphs reused = 2698419
llama-server | 11007.16.955.287 I slot print_timing: id 1 | task 2785601 | draft acceptance = 0.40743 ( 658 accepted / 1615 generated), mean len = 3.04
llama-server | 11007.16.956.483 I slot release: id 1 | task 2785601 | stop processing: n_tokens = 41493, truncated = 0
llama-server | 11007.33.618.241 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 660442118029
llama-server | 11007.33.620.104 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1985.623 MiB)
llama-server | 11007.36.224.290 I slot launch_slot_: id 0 | task 2785948 | processing task, is_child = 0
llama-server | 11007.36.226.476 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1941.003 MiB)
llama-server | 11007.43.147.030 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.01 s / 1360.53 tokens per second
llama-server | 11007.44.932.592 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.79 s / 1283.93 tokens per second
llama-server | 11007.46.756.855 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.60 s / 1241.56 tokens per second
llama-server | 11007.48.615.298 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.45 s / 1211.88 tokens per second
llama-server | 11007.50.514.201 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.34 s / 1188.71 tokens per second
llama-server | 11007.52.449.835 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 14336, progress = 0.36, t = 12.26 s / 1168.88 tokens per second
llama-server | 11007.54.428.697 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 16384, progress = 0.41, t = 14.23 s / 1151.33 tokens per second
llama-server | 11007.56.444.261 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 18432, progress = 0.46, t = 16.24 s / 1134.96 tokens per second
llama-server | 11007.58.502.512 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 20480, progress = 0.51, t = 18.29 s / 1119.97 tokens per second
llama-server | 11008.00.606.105 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 22528, progress = 0.56, t = 20.37 s / 1105.70 tokens per second
llama-server | 11008.02.762.581 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 24576, progress = 0.61, t = 22.51 s / 1091.70 tokens per second
llama-server | 11008.04.943.165 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 26624, progress = 0.66, t = 24.70 s / 1078.09 tokens per second
llama-server | 11008.07.161.532 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 28672, progress = 0.71, t = 26.90 s / 1065.76 tokens per second
llama-server | 11008.09.418.553 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 30720, progress = 0.76, t = 29.15 s / 1053.83 tokens per second
llama-server | 11008.11.743.298 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 32768, progress = 0.81, t = 31.43 s / 1042.49 tokens per second
llama-server | 11008.14.076.006 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 34816, progress = 0.86, t = 33.79 s / 1030.49 tokens per second
llama-server | 11008.16.440.011 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 36864, progress = 0.92, t = 36.14 s / 1019.91 tokens per second
llama-server | 11008.18.841.057 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 38912, progress = 0.97, t = 38.54 s / 1009.74 tokens per second
llama-server | 11008.19.913.366 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 39753, progress = 0.99, t = 39.82 s / 998.34 tokens per second
llama-server | 11008.20.647.515 I slot print_timing: id 0 | task 2785948 | prompt processing, n_tokens = 40265, progress = 1.00, t = 40.44 s / 995.68 tokens per second
llama-server | 11008.23.905.798 I slot print_timing: id 0 | task 2785948 | n_gen = 111, tg = 36.45 t/s, tg_3s = 36.78 t/s
llama-server | 11008.26.924.820 I slot print_timing: id 0 | task 2785948 | n_gen = 206, tg = 33.96 t/s, tg_3s = 31.47 t/s
llama-server | 11008.30.012.778 I slot print_timing: id 0 | task 2785948 | n_gen = 291, tg = 31.78 t/s, tg_3s = 27.53 t/s
llama-server | 11008.33.019.879 I slot print_timing: id 0 | task 2785948 | n_gen = 406, tg = 33.38 t/s, tg_3s = 38.24 t/s
llama-server | 11008.36.049.969 I slot print_timing: id 0 | task 2785948 | n_gen = 504, tg = 33.18 t/s, tg_3s = 32.34 t/s
llama-server | 11008.39.061.804 I slot print_timing: id 0 | task 2785948 | n_gen = 606, tg = 33.29 t/s, tg_3s = 33.87 t/s
llama-server | 11008.42.070.842 I slot print_timing: id 0 | task 2785948 | n_gen = 674, tg = 31.77 t/s, tg_3s = 22.60 t/s
llama-server | 11008.45.106.632 I slot print_timing: id 0 | task 2785948 | n_gen = 762, tg = 31.42 t/s, tg_3s = 28.99 t/s
llama-server | 11008.48.125.907 I slot print_timing: id 0 | task 2785948 | n_gen = 851, tg = 31.21 t/s, tg_3s = 29.48 t/s
llama-server | 11008.51.169.707 I slot print_timing: id 0 | task 2785948 | n_gen = 966, tg = 31.87 t/s, tg_3s = 37.78 t/s
llama-server | 11008.53.578.647 I slot print_timing: id 0 | task 2785948 | prompt eval time = 41279.54 ms / 40269 tokens ( 1.03 ms per token, 975.52 tokens per second)
llama-server | 11008.53.578.651 I slot print_timing: id 0 | task 2785948 | eval time = 32690.29 ms / 1079 tokens ( 30.32 ms per token, 32.98 tokens per second)
llama-server | 11008.53.578.651 I slot print_timing: id 0 | task 2785948 | total time = 73969.83 ms / 41348 tokens
llama-server | 11008.53.578.652 I slot print_timing: id 0 | task 2785948 | graphs reused = 2698782
llama-server | 11008.53.578.655 I slot print_timing: id 0 | task 2785948 | draft acceptance = 0.38641 ( 711 accepted / 1840 generated), mean len = 2.93
llama-server | 11008.53.579.884 I slot release: id 0 | task 2785948 | stop processing: n_tokens = 41348, truncated = 0
llama-server | 11008.54.862.682 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 660452796535
llama-server | 11008.54.863.359 I slot launch_slot_: id 1 | task 2786339 | processing task, is_child = 0
llama-server | 11008.54.865.266 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1983.062 MiB)
llama-server | 11009.01.979.602 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1278.81 tokens per second
llama-server | 11009.03.836.778 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1232.54 tokens per second
llama-server | 11009.05.733.335 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.53 s / 1200.42 tokens per second
llama-server | 11009.07.658.163 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.46 s / 1175.23 tokens per second
llama-server | 11009.09.632.429 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 14336, progress = 0.36, t = 12.42 s / 1154.12 tokens per second
llama-server | 11009.11.636.069 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 16384, progress = 0.41, t = 14.41 s / 1136.82 tokens per second
llama-server | 11009.13.674.715 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 18432, progress = 0.46, t = 16.44 s / 1120.89 tokens per second
llama-server | 11009.15.753.282 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.51 s / 1106.38 tokens per second
llama-server | 11009.17.871.088 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 22528, progress = 0.57, t = 20.62 s / 1092.65 tokens per second
llama-server | 11009.20.042.866 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 24576, progress = 0.62, t = 22.77 s / 1079.39 tokens per second
llama-server | 11009.22.238.752 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 26624, progress = 0.67, t = 24.97 s / 1066.43 tokens per second
llama-server | 11009.24.472.297 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 28672, progress = 0.72, t = 27.19 s / 1054.55 tokens per second
llama-server | 11009.26.741.038 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 30720, progress = 0.77, t = 29.45 s / 1043.21 tokens per second
llama-server | 11009.29.076.914 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 32768, progress = 0.83, t = 31.74 s / 1032.32 tokens per second
llama-server | 11009.31.410.488 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 34816, progress = 0.88, t = 34.10 s / 1020.91 tokens per second
llama-server | 11009.33.783.088 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 36864, progress = 0.93, t = 36.46 s / 1010.97 tokens per second
llama-server | 11009.36.188.730 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 38912, progress = 0.98, t = 38.86 s / 1001.27 tokens per second
llama-server | 11009.36.545.673 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 39148, progress = 0.99, t = 39.57 s / 989.26 tokens per second
llama-server | 11009.37.279.975 I slot print_timing: id 1 | task 2786339 | prompt processing, n_tokens = 39660, progress = 1.00, t = 40.06 s / 990.11 tokens per second
llama-server | 11009.39.136.129 I slot print_timing: id 1 | task 2786339 | prompt eval time = 40883.16 ms / 39664 tokens ( 1.03 ms per token, 970.18 tokens per second)
llama-server | 11009.39.136.132 I slot print_timing: id 1 | task 2786339 | eval time = 1623.95 ms / 65 tokens ( 25.37 ms per token, 39.41 tokens per second)
llama-server | 11009.39.136.133 I slot print_timing: id 1 | task 2786339 | total time = 42507.10 ms / 39729 tokens
llama-server | 11009.39.136.134 I slot print_timing: id 1 | task 2786339 | graphs reused = 2698798
llama-server | 11009.39.136.137 I slot print_timing: id 1 | task 2786339 | draft acceptance = 0.51111 ( 46 accepted / 90 generated), mean len = 3.56
llama-server | 11009.39.137.227 I slot release: id 1 | task 2786339 | stop processing: n_tokens = 39728, truncated = 0
llama-server | 11009.40.249.910 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 660549419936
llama-server | 11009.40.250.660 I slot launch_slot_: id 0 | task 2786380 | processing task, is_child = 0
llama-server | 11009.40.252.673 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1934.951 MiB)
llama-server | 11009.46.770.472 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1281.29 tokens per second
llama-server | 11009.48.618.748 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.63 s / 1234.99 tokens per second
llama-server | 11009.50.501.069 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.51 s / 1203.57 tokens per second
llama-server | 11009.52.427.802 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.43 s / 1178.64 tokens per second
llama-server | 11009.54.391.141 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 14336, progress = 0.36, t = 12.38 s / 1158.46 tokens per second
llama-server | 11009.56.391.561 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 16384, progress = 0.41, t = 14.37 s / 1140.43 tokens per second
llama-server | 11009.58.427.736 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 18432, progress = 0.46, t = 16.40 s / 1124.14 tokens per second
llama-server | 11010.00.502.859 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 20480, progress = 0.51, t = 18.46 s / 1109.33 tokens per second
llama-server | 11010.02.617.525 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 22528, progress = 0.57, t = 20.56 s / 1095.49 tokens per second
llama-server | 11010.04.785.153 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 24576, progress = 0.62, t = 22.71 s / 1082.13 tokens per second
llama-server | 11010.06.975.326 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 26624, progress = 0.67, t = 24.90 s / 1069.07 tokens per second
llama-server | 11010.09.205.479 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 28672, progress = 0.72, t = 27.12 s / 1057.13 tokens per second
llama-server | 11010.11.468.598 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 30720, progress = 0.77, t = 29.38 s / 1045.70 tokens per second
llama-server | 11010.13.802.647 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 32768, progress = 0.82, t = 31.67 s / 1034.75 tokens per second
llama-server | 11010.16.136.157 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 34816, progress = 0.87, t = 34.03 s / 1023.14 tokens per second
llama-server | 11010.18.511.379 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 36864, progress = 0.93, t = 36.39 s / 1013.04 tokens per second
llama-server | 11010.20.917.737 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 38912, progress = 0.98, t = 38.79 s / 1003.12 tokens per second
llama-server | 11010.21.423.191 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 39282, progress = 0.99, t = 39.50 s / 994.41 tokens per second
llama-server | 11010.22.146.355 I slot print_timing: id 0 | task 2786380 | prompt processing, n_tokens = 39794, progress = 1.00, t = 40.12 s / 991.94 tokens per second
llama-server | 11010.26.884.927 I slot print_timing: id 0 | task 2786380 | n_gen = 102, tg = 22.42 t/s, tg_3s = 22.64 t/s
llama-server | 11010.29.899.389 I slot print_timing: id 0 | task 2786380 | n_gen = 185, tg = 24.47 t/s, tg_3s = 27.53 t/s
llama-server | 11010.32.983.163 I slot print_timing: id 0 | task 2786380 | n_gen = 283, tg = 26.60 t/s, tg_3s = 31.78 t/s
llama-server | 11010.33.513.430 I slot print_timing: id 0 | task 2786380 | prompt eval time = 40950.69 ms / 39798 tokens ( 1.03 ms per token, 971.85 tokens per second)
llama-server | 11010.33.513.433 I slot print_timing: id 0 | task 2786380 | eval time = 11132.99 ms / 309 tokens ( 36.15 ms per token, 27.67 tokens per second)
llama-server | 11010.33.513.433 I slot print_timing: id 0 | task 2786380 | total time = 52083.68 ms / 40107 tokens
llama-server | 11010.33.513.434 I slot print_timing: id 0 | task 2786380 | graphs reused = 2698922
llama-server | 11010.33.513.437 I slot print_timing: id 0 | task 2786380 | draft acceptance = 0.28889 ( 182 accepted / 630 generated), mean len = 2.44
llama-server | 11010.33.514.626 I slot release: id 0 | task 2786380 | stop processing: n_tokens = 40106, truncated = 0
llama-server | 11010.34.629.031 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 660594977279
llama-server | 11010.34.629.668 I slot launch_slot_: id 1 | task 2786529 | processing task, is_child = 0
llama-server | 11010.34.631.579 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1478.546 MiB)
llama-server | 11010.41.640.087 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1280.62 tokens per second
llama-server | 11010.43.489.768 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.64 s / 1234.38 tokens per second
llama-server | 11010.45.374.016 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.51 s / 1202.96 tokens per second
llama-server | 11010.47.296.491 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 12288, progress = 0.30, t = 10.43 s / 1178.67 tokens per second
llama-server | 11010.49.268.144 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 14336, progress = 0.35, t = 12.38 s / 1157.61 tokens per second
llama-server | 11010.51.268.532 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 16384, progress = 0.41, t = 14.38 s / 1139.63 tokens per second
llama-server | 11010.53.306.568 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 18432, progress = 0.46, t = 16.41 s / 1123.42 tokens per second
llama-server | 11010.55.382.791 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 20480, progress = 0.51, t = 18.47 s / 1108.63 tokens per second
llama-server | 11010.57.499.599 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 22528, progress = 0.56, t = 20.58 s / 1094.75 tokens per second
llama-server | 11010.59.670.338 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 24576, progress = 0.61, t = 22.73 s / 1081.31 tokens per second
llama-server | 11011.01.866.197 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 26624, progress = 0.66, t = 24.92 s / 1068.20 tokens per second
llama-server | 11011.04.096.416 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 28672, progress = 0.71, t = 27.15 s / 1056.23 tokens per second
llama-server | 11011.06.363.393 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 30720, progress = 0.76, t = 29.40 s / 1044.80 tokens per second
llama-server | 11011.08.698.618 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 32768, progress = 0.81, t = 31.69 s / 1033.87 tokens per second
llama-server | 11011.11.032.676 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 34816, progress = 0.86, t = 34.06 s / 1022.31 tokens per second
llama-server | 11011.13.404.359 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 36864, progress = 0.91, t = 36.42 s / 1012.26 tokens per second
llama-server | 11011.15.810.228 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 38912, progress = 0.96, t = 38.82 s / 1002.49 tokens per second
llama-server | 11011.17.012.431 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 39887, progress = 0.99, t = 40.10 s / 994.66 tokens per second
llama-server | 11011.17.746.073 I slot print_timing: id 1 | task 2786529 | prompt processing, n_tokens = 40399, progress = 1.00, t = 40.85 s / 989.03 tokens per second
llama-server | 11011.21.120.399 I slot print_timing: id 1 | task 2786529 | n_gen = 102, tg = 32.24 t/s, tg_3s = 32.55 t/s
llama-server | 11011.24.123.415 I slot print_timing: id 1 | task 2786529 | n_gen = 186, tg = 30.15 t/s, tg_3s = 27.97 t/s
llama-server | 11011.27.129.723 I slot print_timing: id 1 | task 2786529 | n_gen = 274, tg = 29.86 t/s, tg_3s = 29.27 t/s
llama-server | 11011.30.157.308 I slot print_timing: id 1 | task 2786529 | n_gen = 377, tg = 30.90 t/s, tg_3s = 34.02 t/s
llama-server | 11011.33.171.446 I slot print_timing: id 1 | task 2786529 | n_gen = 474, tg = 31.15 t/s, tg_3s = 32.18 t/s
llama-server | 11011.36.204.302 I slot print_timing: id 1 | task 2786529 | n_gen = 574, tg = 31.45 t/s, tg_3s = 32.97 t/s
llama-server | 11011.39.222.605 I slot print_timing: id 1 | task 2786529 | n_gen = 671, tg = 31.55 t/s, tg_3s = 32.14 t/s
llama-server | 11011.42.245.978 I slot print_timing: id 1 | task 2786529 | n_gen = 785, tg = 32.32 t/s, tg_3s = 37.71 t/s
llama-server | 11011.45.283.040 I slot print_timing: id 1 | task 2786529 | n_gen = 884, tg = 32.35 t/s, tg_3s = 32.60 t/s
llama-server | 11011.48.300.411 I slot print_timing: id 1 | task 2786529 | n_gen = 964, tg = 31.77 t/s, tg_3s = 26.51 t/s
llama-server | 11011.51.324.068 I slot print_timing: id 1 | task 2786529 | n_gen = 1049, tg = 31.44 t/s, tg_3s = 28.11 t/s
llama-server | 11011.54.365.120 I slot print_timing: id 1 | task 2786529 | n_gen = 1120, tg = 30.76 t/s, tg_3s = 23.35 t/s
llama-server | 11011.57.397.502 I slot print_timing: id 1 | task 2786529 | n_gen = 1238, tg = 31.39 t/s, tg_3s = 38.91 t/s
llama-server | 11012.00.446.349 I slot print_timing: id 1 | task 2786529 | n_gen = 1328, tg = 31.25 t/s, tg_3s = 29.52 t/s
llama-server | 11012.03.486.785 I slot print_timing: id 1 | task 2786529 | n_gen = 1420, tg = 31.19 t/s, tg_3s = 30.26 t/s
llama-server | 11012.06.531.115 I slot print_timing: id 1 | task 2786529 | n_gen = 1540, tg = 31.70 t/s, tg_3s = 39.42 t/s
llama-server | 11012.07.515.289 I slot print_timing: id 1 | task 2786529 | prompt eval time = 41689.46 ms / 40403 tokens ( 1.03 ms per token, 969.14 tokens per second)
llama-server | 11012.07.515.293 I slot print_timing: id 1 | task 2786529 | eval time = 49527.96 ms / 1577 tokens ( 31.43 ms per token, 31.82 tokens per second)
llama-server | 11012.07.515.294 I slot print_timing: id 1 | task 2786529 | total time = 91217.42 ms / 41980 tokens
llama-server | 11012.07.515.295 I slot print_timing: id 1 | task 2786529 | graphs reused = 2699471
llama-server | 11012.07.515.299 I slot print_timing: id 1 | task 2786529 | draft acceptance = 0.36727 ( 1021 accepted / 2780 generated), mean len = 2.84
llama-server | 11012.07.516.580 I slot release: id 1 | task 2786529 | stop processing: n_tokens = 41980, truncated = 0
llama-server | 11012.08.832.887 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 660649354677
llama-server | 11012.08.833.464 I slot launch_slot_: id 0 | task 2787108 | processing task, is_child = 0
llama-server | 11012.08.835.451 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1948.617 MiB)
llama-server | 11012.16.142.323 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.81 s / 1278.46 tokens per second
llama-server | 11012.17.999.778 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.65 s / 1232.48 tokens per second
llama-server | 11012.19.886.227 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.53 s / 1200.28 tokens per second
llama-server | 11012.21.822.587 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 12288, progress = 0.30, t = 10.46 s / 1174.90 tokens per second
llama-server | 11012.23.791.650 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 14336, progress = 0.35, t = 12.41 s / 1155.15 tokens per second
llama-server | 11012.25.795.282 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 16384, progress = 0.40, t = 14.41 s / 1137.12 tokens per second
llama-server | 11012.27.835.166 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 18432, progress = 0.45, t = 16.44 s / 1121.03 tokens per second
llama-server | 11012.29.913.330 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 20480, progress = 0.50, t = 18.51 s / 1106.41 tokens per second
llama-server | 11012.32.033.050 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 22528, progress = 0.55, t = 20.62 s / 1092.71 tokens per second
llama-server | 11012.34.209.306 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 24576, progress = 0.60, t = 22.77 s / 1079.36 tokens per second
llama-server | 11012.36.405.855 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 26624, progress = 0.65, t = 24.97 s / 1066.22 tokens per second
llama-server | 11012.38.639.400 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 28672, progress = 0.70, t = 27.19 s / 1054.35 tokens per second
llama-server | 11012.40.905.904 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 30720, progress = 0.75, t = 29.45 s / 1042.99 tokens per second
llama-server | 11012.43.242.962 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 32768, progress = 0.81, t = 31.75 s / 1032.18 tokens per second
llama-server | 11012.45.579.717 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 34816, progress = 0.86, t = 34.11 s / 1020.70 tokens per second
llama-server | 11012.47.954.138 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 36864, progress = 0.91, t = 36.47 s / 1010.72 tokens per second
llama-server | 11012.50.361.120 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 38912, progress = 0.96, t = 38.87 s / 1000.99 tokens per second
llama-server | 11012.51.931.387 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 40178, progress = 0.99, t = 40.73 s / 986.40 tokens per second
llama-server | 11012.52.635.981 I slot print_timing: id 0 | task 2787108 | prompt processing, n_tokens = 40690, progress = 1.00, t = 41.25 s / 986.52 tokens per second
llama-server | 11012.56.190.817 I slot print_timing: id 0 | task 2787108 | n_gen = 100, tg = 29.88 t/s, tg_3s = 30.18 t/s
llama-server | 11012.57.165.805 I slot print_timing: id 0 | task 2787108 | prompt eval time = 42085.98 ms / 40694 tokens ( 1.03 ms per token, 966.93 tokens per second)
llama-server | 11012.57.165.808 I slot print_timing: id 0 | task 2787108 | eval time = 4288.66 ms / 136 tokens ( 31.77 ms per token, 31.48 tokens per second)
llama-server | 11012.57.165.809 I slot print_timing: id 0 | task 2787108 | total time = 46374.64 ms / 40830 tokens
llama-server | 11012.57.165.809 I slot print_timing: id 0 | task 2787108 | graphs reused = 2699517
llama-server | 11012.57.165.812 I slot print_timing: id 0 | task 2787108 | draft acceptance = 0.36250 ( 87 accepted / 240 generated), mean len = 2.81
llama-server | 11012.57.166.923 I slot release: id 0 | task 2787108 | stop processing: n_tokens = 40829, truncated = 0
llama-server | 11012.58.294.271 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 660743356633
llama-server | 11012.58.294.996 I slot launch_slot_: id 1 | task 2787179 | processing task, is_child = 0
llama-server | 11012.58.296.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1943.795 MiB)
llama-server | 11013.05.164.117 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1280.22 tokens per second
llama-server | 11013.07.015.826 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.65 s / 1231.59 tokens per second
llama-server | 11013.08.905.994 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.53 s / 1199.92 tokens per second
llama-server | 11013.10.826.654 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.45 s / 1176.40 tokens per second
llama-server | 11013.12.790.118 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 14336, progress = 0.36, t = 12.40 s / 1156.57 tokens per second
llama-server | 11013.14.789.390 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 16384, progress = 0.41, t = 14.39 s / 1138.90 tokens per second
llama-server | 11013.16.826.571 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 18432, progress = 0.46, t = 16.42 s / 1122.79 tokens per second
llama-server | 11013.18.908.599 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 20480, progress = 0.51, t = 18.48 s / 1108.11 tokens per second
llama-server | 11013.21.026.113 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 22528, progress = 0.56, t = 20.59 s / 1093.94 tokens per second
llama-server | 11013.23.194.472 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 24576, progress = 0.61, t = 22.74 s / 1080.69 tokens per second
llama-server | 11013.25.388.387 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 26624, progress = 0.66, t = 24.94 s / 1067.67 tokens per second
llama-server | 11013.27.619.803 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 28672, progress = 0.71, t = 27.16 s / 1055.77 tokens per second
llama-server | 11013.29.885.442 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 30720, progress = 0.77, t = 29.41 s / 1044.40 tokens per second
llama-server | 11013.32.220.460 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 32768, progress = 0.82, t = 31.71 s / 1033.50 tokens per second
llama-server | 11013.34.556.028 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 34816, progress = 0.87, t = 34.07 s / 1021.95 tokens per second
llama-server | 11013.36.929.578 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 36864, progress = 0.92, t = 36.43 s / 1011.91 tokens per second
llama-server | 11013.39.336.432 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 38912, progress = 0.97, t = 38.83 s / 1002.11 tokens per second
llama-server | 11013.40.270.360 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 39638, progress = 0.99, t = 40.12 s / 988.09 tokens per second
llama-server | 11013.41.003.501 I slot print_timing: id 1 | task 2787179 | prompt processing, n_tokens = 40150, progress = 1.00, t = 40.60 s / 988.97 tokens per second
llama-server | 11013.44.147.832 I slot print_timing: id 1 | task 2787179 | prompt eval time = 41386.80 ms / 40154 tokens ( 1.03 ms per token, 970.21 tokens per second)
llama-server | 11013.44.147.835 I slot print_timing: id 1 | task 2787179 | eval time = 2951.98 ms / 120 tokens ( 24.81 ms per token, 40.31 tokens per second)
llama-server | 11013.44.147.836 I slot print_timing: id 1 | task 2787179 | total time = 44338.78 ms / 40274 tokens
llama-server | 11013.44.147.837 I slot print_timing: id 1 | task 2787179 | graphs reused = 2699548
llama-server | 11013.44.147.839 I slot print_timing: id 1 | task 2787179 | draft acceptance = 0.52727 ( 87 accepted / 165 generated), mean len = 3.64
llama-server | 11013.44.149.052 I slot release: id 1 | task 2787179 | stop processing: n_tokens = 40274, truncated = 0
llama-server | 11013.45.308.510 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 660793006975
llama-server | 11013.45.309.306 I slot launch_slot_: id 0 | task 2787235 | processing task, is_child = 0
llama-server | 11013.45.311.174 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1889.932 MiB)
llama-server | 11013.51.788.193 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1279.68 tokens per second
llama-server | 11013.53.636.159 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.64 s / 1233.98 tokens per second
llama-server | 11013.55.518.896 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.51 s / 1202.75 tokens per second
llama-server | 11013.57.453.831 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 12288, progress = 0.30, t = 10.43 s / 1177.98 tokens per second
llama-server | 11013.59.418.488 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 14336, progress = 0.35, t = 12.39 s / 1157.03 tokens per second
llama-server | 11014.01.418.725 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 16384, progress = 0.40, t = 14.38 s / 1139.29 tokens per second
llama-server | 11014.03.453.907 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 18432, progress = 0.45, t = 16.41 s / 1123.20 tokens per second
llama-server | 11014.05.529.180 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 20480, progress = 0.51, t = 18.47 s / 1108.55 tokens per second
llama-server | 11014.07.651.857 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 22528, progress = 0.56, t = 20.58 s / 1094.74 tokens per second
llama-server | 11014.09.823.693 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 24576, progress = 0.61, t = 22.73 s / 1080.98 tokens per second
llama-server | 11014.12.017.552 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 26624, progress = 0.66, t = 24.93 s / 1067.90 tokens per second
llama-server | 11014.14.249.773 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 28672, progress = 0.71, t = 27.15 s / 1055.94 tokens per second
llama-server | 11014.16.515.816 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 30720, progress = 0.76, t = 29.41 s / 1044.48 tokens per second
llama-server | 11014.18.851.013 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 32768, progress = 0.81, t = 31.70 s / 1033.57 tokens per second
llama-server | 11014.21.186.204 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 34816, progress = 0.86, t = 34.07 s / 1022.05 tokens per second
llama-server | 11014.23.562.017 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 36864, progress = 0.91, t = 36.43 s / 1011.97 tokens per second
llama-server | 11014.25.969.207 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 38912, progress = 0.96, t = 38.83 s / 1002.13 tokens per second
llama-server | 11014.27.357.020 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 40016, progress = 0.99, t = 40.69 s / 983.53 tokens per second
llama-server | 11014.28.076.713 I slot print_timing: id 0 | task 2787235 | prompt processing, n_tokens = 40528, progress = 1.00, t = 41.04 s / 987.63 tokens per second
llama-server | 11014.32.466.551 I slot print_timing: id 0 | task 2787235 | n_gen = 105, tg = 24.91 t/s, tg_3s = 25.15 t/s
llama-server | 11014.35.492.845 I slot print_timing: id 0 | task 2787235 | n_gen = 221, tg = 30.55 t/s, tg_3s = 38.33 t/s
llama-server | 11014.38.506.423 I slot print_timing: id 0 | task 2787235 | n_gen = 344, tg = 33.58 t/s, tg_3s = 40.82 t/s
llama-server | 11014.41.538.671 I slot print_timing: id 0 | task 2787235 | n_gen = 452, tg = 34.05 t/s, tg_3s = 35.62 t/s
llama-server | 11014.44.553.456 I slot print_timing: id 0 | task 2787235 | n_gen = 540, tg = 33.15 t/s, tg_3s = 29.19 t/s
llama-server | 11014.47.563.977 I slot print_timing: id 0 | task 2787235 | n_gen = 613, tg = 31.76 t/s, tg_3s = 24.25 t/s
llama-server | 11014.50.583.352 I slot print_timing: id 0 | task 2787235 | n_gen = 682, tg = 30.55 t/s, tg_3s = 22.85 t/s
llama-server | 11014.53.621.093 I slot print_timing: id 0 | task 2787235 | n_gen = 762, tg = 30.04 t/s, tg_3s = 26.34 t/s
llama-server | 11014.56.650.814 I slot print_timing: id 0 | task 2787235 | n_gen = 843, tg = 29.69 t/s, tg_3s = 26.74 t/s
llama-server | 11014.59.677.459 I slot print_timing: id 0 | task 2787235 | n_gen = 923, tg = 29.38 t/s, tg_3s = 26.43 t/s
llama-server | 11015.02.729.889 I slot print_timing: id 0 | task 2787235 | n_gen = 1007, tg = 29.21 t/s, tg_3s = 27.52 t/s
llama-server | 11015.05.764.533 I slot print_timing: id 0 | task 2787235 | n_gen = 1124, tg = 29.97 t/s, tg_3s = 38.55 t/s
llama-server | 11015.08.826.727 I slot print_timing: id 0 | task 2787235 | n_gen = 1292, tg = 31.85 t/s, tg_3s = 54.86 t/s
llama-server | 11015.11.869.113 I slot print_timing: id 0 | task 2787235 | n_gen = 1392, tg = 31.92 t/s, tg_3s = 32.87 t/s
llama-server | 11015.14.920.440 I slot print_timing: id 0 | task 2787235 | n_gen = 1478, tg = 31.68 t/s, tg_3s = 28.18 t/s
llama-server | 11015.17.960.402 I slot print_timing: id 0 | task 2787235 | n_gen = 1578, tg = 31.75 t/s, tg_3s = 32.90 t/s
llama-server | 11015.21.002.039 I slot print_timing: id 0 | task 2787235 | n_gen = 1645, tg = 31.19 t/s, tg_3s = 22.03 t/s
llama-server | 11015.24.058.182 I slot print_timing: id 0 | task 2787235 | n_gen = 1744, tg = 31.26 t/s, tg_3s = 32.39 t/s
llama-server | 11015.27.108.892 I slot print_timing: id 0 | task 2787235 | n_gen = 1852, tg = 31.47 t/s, tg_3s = 35.40 t/s
llama-server | 11015.30.181.804 I slot print_timing: id 0 | task 2787235 | n_gen = 1999, tg = 32.28 t/s, tg_3s = 47.84 t/s
llama-server | 11015.33.064.957 I slot print_timing: id 0 | task 2787235 | prompt eval time = 41849.05 ms / 40532 tokens ( 1.03 ms per token, 968.53 tokens per second)
llama-server | 11015.33.064.960 I slot print_timing: id 0 | task 2787235 | eval time = 64773.25 ms / 2135 tokens ( 30.35 ms per token, 32.95 tokens per second)
llama-server | 11015.33.064.960 I slot print_timing: id 0 | task 2787235 | total time = 106622.30 ms / 42667 tokens
llama-server | 11015.33.064.961 I slot print_timing: id 0 | task 2787235 | graphs reused = 2700264
llama-server | 11015.33.064.964 I slot print_timing: id 0 | task 2787235 | draft acceptance = 0.38869 ( 1409 accepted / 3625 generated), mean len = 2.94
llama-server | 11015.33.066.150 I slot release: id 0 | task 2787235 | stop processing: n_tokens = 42666, truncated = 0
llama-server | 11015.50.315.243 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 660839989104
llama-server | 11015.50.315.782 I slot launch_slot_: id 1 | task 2787983 | processing task, is_child = 0
llama-server | 11015.50.318.660 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1902.500 MiB)
llama-server | 11015.56.857.069 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.75 s / 1293.44 tokens per second
llama-server | 11015.58.685.413 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.57 s / 1247.03 tokens per second
llama-server | 11016.00.549.187 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.42 s / 1215.46 tokens per second
llama-server | 11016.02.454.129 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 12288, progress = 0.30, t = 10.32 s / 1191.05 tokens per second
llama-server | 11016.04.396.484 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 14336, progress = 0.35, t = 12.25 s / 1170.06 tokens per second
llama-server | 11016.06.380.227 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 16384, progress = 0.40, t = 14.22 s / 1151.89 tokens per second
llama-server | 11016.08.401.014 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 18432, progress = 0.46, t = 16.24 s / 1135.16 tokens per second
llama-server | 11016.10.461.791 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 20480, progress = 0.51, t = 18.29 s / 1119.87 tokens per second
llama-server | 11016.12.573.305 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 22528, progress = 0.56, t = 20.38 s / 1105.49 tokens per second
llama-server | 11016.14.731.825 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 24576, progress = 0.61, t = 22.52 s / 1091.12 tokens per second
llama-server | 11016.16.915.295 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 26624, progress = 0.66, t = 24.71 s / 1077.52 tokens per second
llama-server | 11016.19.137.365 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 28672, progress = 0.71, t = 26.92 s / 1065.10 tokens per second
llama-server | 11016.21.392.455 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 30720, progress = 0.76, t = 29.17 s / 1053.21 tokens per second
llama-server | 11016.23.720.499 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 32768, progress = 0.81, t = 31.45 s / 1041.86 tokens per second
llama-server | 11016.26.049.020 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 34816, progress = 0.86, t = 33.81 s / 1029.87 tokens per second
llama-server | 11016.28.414.972 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 36864, progress = 0.91, t = 36.16 s / 1019.44 tokens per second
llama-server | 11016.30.816.956 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 38912, progress = 0.96, t = 38.56 s / 1009.26 tokens per second
llama-server | 11016.32.116.746 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 39965, progress = 0.99, t = 40.41 s / 989.06 tokens per second
llama-server | 11016.32.842.874 I slot print_timing: id 1 | task 2787983 | prompt processing, n_tokens = 40477, progress = 1.00, t = 40.68 s / 995.02 tokens per second
llama-server | 11016.36.677.940 I slot print_timing: id 1 | task 2787983 | n_gen = 104, tg = 28.29 t/s, tg_3s = 28.56 t/s
llama-server | 11016.39.680.588 I slot print_timing: id 1 | task 2787983 | n_gen = 205, tg = 30.71 t/s, tg_3s = 33.64 t/s
llama-server | 11016.42.700.607 I slot print_timing: id 1 | task 2787983 | n_gen = 275, tg = 28.35 t/s, tg_3s = 23.18 t/s
llama-server | 11016.45.706.916 I slot print_timing: id 1 | task 2787983 | n_gen = 350, tg = 27.55 t/s, tg_3s = 24.95 t/s
llama-server | 11016.48.713.452 I slot print_timing: id 1 | task 2787983 | n_gen = 434, tg = 27.62 t/s, tg_3s = 27.94 t/s
llama-server | 11016.51.738.410 I slot print_timing: id 1 | task 2787983 | n_gen = 504, tg = 26.90 t/s, tg_3s = 23.14 t/s
llama-server | 11016.54.754.654 I slot print_timing: id 1 | task 2787983 | n_gen = 599, tg = 27.54 t/s, tg_3s = 31.50 t/s
llama-server | 11016.57.775.104 I slot print_timing: id 1 | task 2787983 | n_gen = 710, tg = 28.66 t/s, tg_3s = 36.75 t/s
llama-server | 11017.00.811.882 I slot print_timing: id 1 | task 2787983 | n_gen = 813, tg = 29.24 t/s, tg_3s = 33.92 t/s
llama-server | 11017.03.830.989 I slot print_timing: id 1 | task 2787983 | n_gen = 899, tg = 29.16 t/s, tg_3s = 28.49 t/s
llama-server | 11017.06.855.049 I slot print_timing: id 1 | task 2787983 | n_gen = 982, tg = 29.01 t/s, tg_3s = 27.45 t/s
llama-server | 11017.09.891.940 I slot print_timing: id 1 | task 2787983 | n_gen = 1045, tg = 28.33 t/s, tg_3s = 20.74 t/s
llama-server | 11017.12.921.358 I slot print_timing: id 1 | task 2787983 | n_gen = 1139, tg = 28.53 t/s, tg_3s = 31.03 t/s
llama-server | 11017.15.950.341 I slot print_timing: id 1 | task 2787983 | n_gen = 1209, tg = 28.15 t/s, tg_3s = 23.11 t/s
llama-server | 11017.18.995.354 I slot print_timing: id 1 | task 2787983 | n_gen = 1269, tg = 27.59 t/s, tg_3s = 19.70 t/s
llama-server | 11017.22.027.680 I slot print_timing: id 1 | task 2787983 | n_gen = 1344, tg = 27.41 t/s, tg_3s = 24.73 t/s
llama-server | 11017.25.061.910 I slot print_timing: id 1 | task 2787983 | n_gen = 1432, tg = 27.51 t/s, tg_3s = 29.00 t/s
llama-server | 11017.28.111.763 I slot print_timing: id 1 | task 2787983 | n_gen = 1525, tg = 27.67 t/s, tg_3s = 30.49 t/s
llama-server | 11017.31.146.360 I slot print_timing: id 1 | task 2787983 | n_gen = 1599, tg = 27.50 t/s, tg_3s = 24.39 t/s
llama-server | 11017.34.190.496 I slot print_timing: id 1 | task 2787983 | n_gen = 1687, tg = 27.57 t/s, tg_3s = 28.91 t/s
llama-server | 11017.37.248.721 I slot print_timing: id 1 | task 2787983 | n_gen = 1772, tg = 27.58 t/s, tg_3s = 27.79 t/s
llama-server | 11017.40.290.970 I slot print_timing: id 1 | task 2787983 | n_gen = 1866, tg = 27.73 t/s, tg_3s = 30.90 t/s
llama-server | 11017.41.099.731 I slot print_timing: id 1 | task 2787983 | prompt eval time = 41471.08 ms / 40481 tokens ( 1.02 ms per token, 976.13 tokens per second)
llama-server | 11017.41.099.735 I slot print_timing: id 1 | task 2787983 | eval time = 68062.69 ms / 1905 tokens ( 35.75 ms per token, 27.97 tokens per second)
llama-server | 11017.41.099.735 I slot print_timing: id 1 | task 2787983 | total time = 109533.77 ms / 42386 tokens
llama-server | 11017.41.099.736 I slot print_timing: id 1 | task 2787983 | graphs reused = 2701020
llama-server | 11017.41.099.739 I slot print_timing: id 1 | task 2787983 | draft acceptance = 0.29843 ( 1140 accepted / 3820 generated), mean len = 2.49
llama-server | 11017.41.100.866 I slot release: id 1 | task 2787983 | stop processing: n_tokens = 42385, truncated = 0
llama-server | 11017.42.979.362 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 660948906202
llama-server | 11017.42.980.032 I slot launch_slot_: id 0 | task 2788770 | processing task, is_child = 0
llama-server | 11017.42.982.170 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1964.809 MiB)
llama-server | 11017.48.097.501 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.01 s / 1359.65 tokens per second
llama-server | 11017.49.916.579 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.82 s / 1274.11 tokens per second
llama-server | 11017.51.777.112 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.67 s / 1228.51 tokens per second
llama-server | 11017.53.669.892 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.56 s / 1196.87 tokens per second
llama-server | 11017.55.607.820 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 12288, progress = 0.30, t = 10.49 s / 1171.78 tokens per second
llama-server | 11017.57.577.027 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 14336, progress = 0.35, t = 12.44 s / 1152.07 tokens per second
llama-server | 11017.59.584.591 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 16384, progress = 0.40, t = 14.44 s / 1134.62 tokens per second
llama-server | 11018.01.628.350 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 18432, progress = 0.45, t = 16.48 s / 1118.64 tokens per second
llama-server | 11018.03.712.018 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 20480, progress = 0.50, t = 18.55 s / 1104.09 tokens per second
llama-server | 11018.05.835.576 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 22528, progress = 0.55, t = 20.66 s / 1090.32 tokens per second
llama-server | 11018.08.010.620 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 24576, progress = 0.60, t = 22.82 s / 1077.05 tokens per second
llama-server | 11018.10.209.141 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 26624, progress = 0.65, t = 25.02 s / 1064.25 tokens per second
llama-server | 11018.12.447.073 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 28672, progress = 0.70, t = 27.24 s / 1052.45 tokens per second
llama-server | 11018.14.718.819 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 30720, progress = 0.75, t = 29.51 s / 1041.09 tokens per second
llama-server | 11018.17.059.000 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 32768, progress = 0.80, t = 31.80 s / 1030.31 tokens per second
llama-server | 11018.19.399.983 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 34816, progress = 0.85, t = 34.17 s / 1018.84 tokens per second
llama-server | 11018.21.777.842 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 36864, progress = 0.90, t = 36.54 s / 1008.89 tokens per second
llama-server | 11018.24.187.140 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 38912, progress = 0.95, t = 38.94 s / 999.25 tokens per second
llama-server | 11018.26.010.007 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 40436, progress = 0.99, t = 40.80 s / 990.99 tokens per second
llama-server | 11018.26.788.508 I slot print_timing: id 0 | task 2788770 | prompt processing, n_tokens = 40948, progress = 1.00, t = 41.61 s / 984.19 tokens per second
llama-server | 11018.30.081.424 I slot print_timing: id 0 | task 2788770 | n_gen = 163, tg = 53.09 t/s, tg_3s = 53.42 t/s
llama-server | 11018.33.092.819 I slot print_timing: id 0 | task 2788770 | n_gen = 252, tg = 41.40 t/s, tg_3s = 29.55 t/s
llama-server | 11018.36.127.246 I slot print_timing: id 0 | task 2788770 | n_gen = 354, tg = 38.80 t/s, tg_3s = 33.61 t/s
llama-server | 11018.39.148.621 I slot print_timing: id 0 | task 2788770 | n_gen = 477, tg = 39.28 t/s, tg_3s = 40.71 t/s
llama-server | 11018.42.189.329 I slot print_timing: id 0 | task 2788770 | n_gen = 611, tg = 40.24 t/s, tg_3s = 44.07 t/s
llama-server | 11018.45.206.282 I slot print_timing: id 0 | task 2788770 | n_gen = 686, tg = 37.69 t/s, tg_3s = 24.86 t/s
llama-server | 11018.48.248.013 I slot print_timing: id 0 | task 2788770 | n_gen = 791, tg = 37.23 t/s, tg_3s = 34.52 t/s
llama-server | 11018.51.273.841 I slot print_timing: id 0 | task 2788770 | n_gen = 872, tg = 35.93 t/s, tg_3s = 26.77 t/s
llama-server | 11018.54.304.682 I slot print_timing: id 0 | task 2788770 | n_gen = 994, tg = 36.41 t/s, tg_3s = 40.25 t/s
llama-server | 11018.55.845.169 I slot print_timing: id 0 | task 2788770 | prompt eval time = 42481.85 ms / 40952 tokens ( 1.04 ms per token, 963.99 tokens per second)
llama-server | 11018.55.845.172 I slot print_timing: id 0 | task 2788770 | eval time = 28815.04 ms / 1073 tokens ( 26.88 ms per token, 37.20 tokens per second)
llama-server | 11018.55.845.173 I slot print_timing: id 0 | task 2788770 | total time = 71296.89 ms / 42025 tokens
llama-server | 11018.55.845.174 I slot print_timing: id 0 | task 2788770 | graphs reused = 2701337
llama-server | 11018.55.845.176 I slot print_timing: id 0 | task 2788770 | draft acceptance = 0.46378 ( 749 accepted / 1615 generated), mean len = 3.32
llama-server | 11018.55.846.428 I slot release: id 0 | task 2788770 | stop processing: n_tokens = 42024, truncated = 0
llama-server | 11019.02.916.220 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 661076940918
llama-server | 11019.02.916.754 I slot launch_slot_: id 1 | task 2789116 | processing task, is_child = 0
llama-server | 11019.02.918.712 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1926.539 MiB)
llama-server | 11019.10.131.571 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.77 s / 1287.98 tokens per second
llama-server | 11019.11.981.992 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.61 s / 1238.54 tokens per second
llama-server | 11019.13.856.445 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.48 s / 1207.57 tokens per second
llama-server | 11019.15.768.107 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 12288, progress = 0.30, t = 10.38 s / 1183.53 tokens per second
llama-server | 11019.17.716.585 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 14336, progress = 0.35, t = 12.32 s / 1163.44 tokens per second
llama-server | 11019.19.710.974 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 16384, progress = 0.40, t = 14.30 s / 1145.52 tokens per second
llama-server | 11019.21.740.375 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 18432, progress = 0.45, t = 16.33 s / 1128.98 tokens per second
llama-server | 11019.23.811.436 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 20480, progress = 0.50, t = 18.38 s / 1114.00 tokens per second
llama-server | 11019.25.923.555 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 22528, progress = 0.55, t = 20.49 s / 1099.73 tokens per second
llama-server | 11019.28.088.800 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 24576, progress = 0.60, t = 22.63 s / 1085.99 tokens per second
llama-server | 11019.30.282.681 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 26624, progress = 0.65, t = 24.82 s / 1072.72 tokens per second
llama-server | 11019.32.510.698 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 28672, progress = 0.70, t = 27.04 s / 1060.25 tokens per second
llama-server | 11019.34.771.082 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 30720, progress = 0.75, t = 29.30 s / 1048.61 tokens per second
llama-server | 11019.37.104.386 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 32768, progress = 0.80, t = 31.58 s / 1037.50 tokens per second
llama-server | 11019.39.436.972 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 34816, progress = 0.85, t = 33.94 s / 1025.72 tokens per second
llama-server | 11019.41.807.616 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 36864, progress = 0.90, t = 36.30 s / 1015.45 tokens per second
llama-server | 11019.44.213.343 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 38912, progress = 0.95, t = 38.70 s / 1005.45 tokens per second
llama-server | 11019.46.020.648 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 40404, progress = 0.99, t = 40.56 s / 996.18 tokens per second
llama-server | 11019.46.771.071 I slot print_timing: id 1 | task 2789116 | prompt processing, n_tokens = 40916, progress = 1.00, t = 41.32 s / 990.13 tokens per second
llama-server | 11019.50.056.677 I slot print_timing: id 1 | task 2789116 | n_gen = 102, tg = 33.17 t/s, tg_3s = 33.50 t/s
llama-server | 11019.53.077.594 I slot print_timing: id 1 | task 2789116 | n_gen = 223, tg = 36.60 t/s, tg_3s = 40.05 t/s
llama-server | 11019.56.104.027 I slot print_timing: id 1 | task 2789116 | n_gen = 325, tg = 35.64 t/s, tg_3s = 33.70 t/s
llama-server | 11019.59.118.866 I slot print_timing: id 1 | task 2789116 | n_gen = 418, tg = 34.44 t/s, tg_3s = 30.85 t/s
llama-server | 11020.02.138.815 I slot print_timing: id 1 | task 2789116 | n_gen = 522, tg = 34.44 t/s, tg_3s = 34.44 t/s
llama-server | 11020.05.173.054 I slot print_timing: id 1 | task 2789116 | n_gen = 620, tg = 34.08 t/s, tg_3s = 32.30 t/s
llama-server | 11020.08.196.354 I slot print_timing: id 1 | task 2789116 | n_gen = 718, tg = 33.85 t/s, tg_3s = 32.41 t/s
llama-server | 11020.11.243.862 I slot print_timing: id 1 | task 2789116 | n_gen = 829, tg = 34.17 t/s, tg_3s = 36.42 t/s
llama-server | 11020.14.274.076 I slot print_timing: id 1 | task 2789116 | n_gen = 913, tg = 33.45 t/s, tg_3s = 27.72 t/s
llama-server | 11020.17.307.936 I slot print_timing: id 1 | task 2789116 | n_gen = 1025, tg = 33.80 t/s, tg_3s = 36.92 t/s
llama-server | 11020.20.369.922 I slot print_timing: id 1 | task 2789116 | n_gen = 1161, tg = 34.77 t/s, tg_3s = 44.42 t/s
llama-server | 11020.23.420.266 I slot print_timing: id 1 | task 2789116 | n_gen = 1306, tg = 35.84 t/s, tg_3s = 47.54 t/s
llama-server | 11020.25.050.798 I slot print_timing: id 1 | task 2789116 | prompt eval time = 42197.16 ms / 40920 tokens ( 1.03 ms per token, 969.73 tokens per second)
llama-server | 11020.25.050.801 I slot print_timing: id 1 | task 2789116 | eval time = 38038.69 ms / 1387 tokens ( 27.44 ms per token, 36.44 tokens per second)
llama-server | 11020.25.050.802 I slot print_timing: id 1 | task 2789116 | total time = 80235.84 ms / 42307 tokens
llama-server | 11020.25.050.803 I slot print_timing: id 1 | task 2789116 | graphs reused = 2701756
llama-server | 11020.25.050.806 I slot print_timing: id 1 | task 2789116 | draft acceptance = 0.45117 ( 961 accepted / 2130 generated), mean len = 3.26
llama-server | 11020.25.051.936 I slot release: id 1 | task 2789116 | stop processing: n_tokens = 42307, truncated = 0
llama-server | 11020.42.294.795 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 661151686480
llama-server | 11020.42.295.596 I slot launch_slot_: id 0 | task 2789565 | processing task, is_child = 0
llama-server | 11020.42.299.758 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1908.086 MiB)
llama-server | 11020.48.773.606 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.75 s / 1294.43 tokens per second
llama-server | 11020.50.601.272 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.56 s / 1248.17 tokens per second
llama-server | 11020.52.462.936 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.42 s / 1216.41 tokens per second
llama-server | 11020.54.363.182 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.31 s / 1191.90 tokens per second
llama-server | 11020.56.302.586 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 14336, progress = 0.34, t = 12.24 s / 1171.42 tokens per second
llama-server | 11020.58.283.531 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 16384, progress = 0.39, t = 14.21 s / 1153.37 tokens per second
llama-server | 11021.00.301.873 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 18432, progress = 0.44, t = 16.22 s / 1136.56 tokens per second
llama-server | 11021.02.362.465 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 20480, progress = 0.49, t = 18.27 s / 1121.22 tokens per second
llama-server | 11021.04.465.703 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 22528, progress = 0.54, t = 20.36 s / 1106.66 tokens per second
llama-server | 11021.06.624.499 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 24576, progress = 0.59, t = 22.49 s / 1092.51 tokens per second
llama-server | 11021.08.807.682 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 26624, progress = 0.64, t = 24.68 s / 1078.79 tokens per second
llama-server | 11021.11.027.670 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 28672, progress = 0.69, t = 26.89 s / 1066.33 tokens per second
llama-server | 11021.13.284.128 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 30720, progress = 0.74, t = 29.14 s / 1054.30 tokens per second
llama-server | 11021.15.611.805 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 32768, progress = 0.79, t = 31.42 s / 1042.85 tokens per second
llama-server | 11021.17.940.405 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 34816, progress = 0.83, t = 33.78 s / 1030.80 tokens per second
llama-server | 11021.20.306.822 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 36864, progress = 0.88, t = 36.13 s / 1020.29 tokens per second
llama-server | 11021.22.708.013 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 38912, progress = 0.93, t = 38.53 s / 1010.03 tokens per second
llama-server | 11021.25.163.651 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 40960, progress = 0.98, t = 40.95 s / 1000.18 tokens per second
llama-server | 11021.25.554.264 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 41219, progress = 0.99, t = 41.69 s / 988.72 tokens per second
llama-server | 11021.26.283.776 I slot print_timing: id 0 | task 2789565 | prompt processing, n_tokens = 41731, progress = 1.00, t = 42.19 s / 989.15 tokens per second
llama-server | 11021.29.521.070 I slot print_timing: id 0 | task 2789565 | n_gen = 127, tg = 41.41 t/s, tg_3s = 41.73 t/s
llama-server | 11021.32.535.934 I slot print_timing: id 0 | task 2789565 | n_gen = 210, tg = 34.50 t/s, tg_3s = 27.53 t/s
llama-server | 11021.35.571.945 I slot print_timing: id 0 | task 2789565 | n_gen = 313, tg = 34.31 t/s, tg_3s = 33.93 t/s
llama-server | 11021.38.595.584 I slot print_timing: id 0 | task 2789565 | n_gen = 400, tg = 32.93 t/s, tg_3s = 28.77 t/s
llama-server | 11021.41.620.608 I slot print_timing: id 0 | task 2789565 | n_gen = 483, tg = 31.83 t/s, tg_3s = 27.44 t/s
llama-server | 11021.44.665.864 I slot print_timing: id 0 | task 2789565 | n_gen = 581, tg = 31.89 t/s, tg_3s = 32.18 t/s
llama-server | 11021.47.704.004 I slot print_timing: id 0 | task 2789565 | n_gen = 707, tg = 33.26 t/s, tg_3s = 41.47 t/s
llama-server | 11021.50.749.864 I slot print_timing: id 0 | task 2789565 | n_gen = 787, tg = 32.38 t/s, tg_3s = 26.27 t/s
llama-server | 11021.53.792.352 I slot print_timing: id 0 | task 2789565 | n_gen = 897, tg = 32.80 t/s, tg_3s = 36.15 t/s
llama-server | 11021.56.834.890 I slot print_timing: id 0 | task 2789565 | n_gen = 997, tg = 32.81 t/s, tg_3s = 32.87 t/s
llama-server | 11021.59.898.723 I slot print_timing: id 0 | task 2789565 | n_gen = 1093, tg = 32.67 t/s, tg_3s = 31.33 t/s
llama-server | 11022.02.949.064 I slot print_timing: id 0 | task 2789565 | n_gen = 1191, tg = 32.63 t/s, tg_3s = 32.13 t/s
llama-server | 11022.06.010.913 I slot print_timing: id 0 | task 2789565 | n_gen = 1273, tg = 32.18 t/s, tg_3s = 26.78 t/s
llama-server | 11022.09.065.388 I slot print_timing: id 0 | task 2789565 | n_gen = 1355, tg = 31.79 t/s, tg_3s = 26.85 t/s
llama-server | 11022.12.120.468 I slot print_timing: id 0 | task 2789565 | n_gen = 1442, tg = 31.57 t/s, tg_3s = 28.48 t/s
llama-server | 11022.15.197.797 I slot print_timing: id 0 | task 2789565 | n_gen = 1542, tg = 31.63 t/s, tg_3s = 32.50 t/s
llama-server | 11022.18.256.217 I slot print_timing: id 0 | task 2789565 | n_gen = 1623, tg = 31.33 t/s, tg_3s = 26.48 t/s
llama-server | 11022.21.321.537 I slot print_timing: id 0 | task 2789565 | n_gen = 1737, tg = 31.65 t/s, tg_3s = 37.19 t/s
llama-server | 11022.23.591.737 I slot print_timing: id 0 | task 2789565 | prompt eval time = 42990.39 ms / 41735 tokens ( 1.03 ms per token, 970.80 tokens per second)
llama-server | 11022.23.591.740 I slot print_timing: id 0 | task 2789565 | eval time = 57113.68 ms / 1827 tokens ( 31.28 ms per token, 31.97 tokens per second)
llama-server | 11022.23.591.740 I slot print_timing: id 0 | task 2789565 | total time = 100104.07 ms / 43562 tokens
llama-server | 11022.23.591.741 I slot print_timing: id 0 | task 2789565 | graphs reused = 2702385
llama-server | 11022.23.591.744 I slot print_timing: id 0 | task 2789565 | draft acceptance = 0.37363 ( 1190 accepted / 3185 generated), mean len = 2.87
llama-server | 11022.23.592.916 I slot release: id 0 | task 2789565 | stop processing: n_tokens = 43562, truncated = 0
llama-server | 11022.24.876.649 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 661240891988
llama-server | 11022.24.877.274 I slot launch_slot_: id 1 | task 2790226 | processing task, is_child = 0
llama-server | 11022.24.879.420 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1987.617 MiB)
llama-server | 11022.30.040.409 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.01 s / 1363.03 tokens per second
llama-server | 11022.31.860.514 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.82 s / 1275.73 tokens per second
llama-server | 11022.33.719.838 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.66 s / 1229.58 tokens per second
llama-server | 11022.35.607.636 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.55 s / 1198.08 tokens per second
llama-server | 11022.37.539.435 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.47 s / 1173.57 tokens per second
llama-server | 11022.39.502.202 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 14336, progress = 0.34, t = 12.42 s / 1154.03 tokens per second
llama-server | 11022.41.508.672 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 16384, progress = 0.39, t = 14.41 s / 1136.70 tokens per second
llama-server | 11022.43.548.060 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 18432, progress = 0.44, t = 16.45 s / 1120.54 tokens per second
llama-server | 11022.45.626.219 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 20480, progress = 0.49, t = 18.52 s / 1106.00 tokens per second
llama-server | 11022.47.743.336 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 22528, progress = 0.54, t = 20.62 s / 1092.41 tokens per second
llama-server | 11022.49.913.374 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 24576, progress = 0.59, t = 22.77 s / 1079.26 tokens per second
llama-server | 11022.52.106.390 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 26624, progress = 0.64, t = 24.97 s / 1066.36 tokens per second
llama-server | 11022.54.338.242 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 28672, progress = 0.68, t = 27.19 s / 1054.59 tokens per second
llama-server | 11022.56.600.967 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 30720, progress = 0.73, t = 29.44 s / 1043.33 tokens per second
llama-server | 11022.58.938.862 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 32768, progress = 0.78, t = 31.73 s / 1032.59 tokens per second
llama-server | 11023.01.273.277 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 34816, progress = 0.83, t = 34.10 s / 1021.09 tokens per second
llama-server | 11023.03.645.158 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 36864, progress = 0.88, t = 36.46 s / 1011.10 tokens per second
llama-server | 11023.06.051.484 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 38912, progress = 0.93, t = 38.86 s / 1001.39 tokens per second
llama-server | 11023.08.509.058 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 40960, progress = 0.98, t = 41.29 s / 992.01 tokens per second
llama-server | 11023.09.088.223 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 41407, progress = 0.99, t = 42.03 s / 985.22 tokens per second
llama-server | 11023.09.852.401 I slot print_timing: id 1 | task 2790226 | prompt processing, n_tokens = 41919, progress = 1.00, t = 42.75 s / 980.64 tokens per second
llama-server | 11023.13.096.462 I slot print_timing: id 1 | task 2790226 | n_gen = 102, tg = 32.96 t/s, tg_3s = 33.28 t/s
llama-server | 11023.16.120.871 I slot print_timing: id 1 | task 2790226 | n_gen = 192, tg = 31.37 t/s, tg_3s = 29.76 t/s
llama-server | 11023.18.977.592 I slot print_timing: id 1 | task 2790226 | prompt eval time = 43534.99 ms / 41923 tokens ( 1.04 ms per token, 962.97 tokens per second)
llama-server | 11023.18.977.596 I slot print_timing: id 1 | task 2790226 | eval time = 8945.74 ms / 312 tokens ( 28.76 ms per token, 34.77 tokens per second)
llama-server | 11023.18.977.596 I slot print_timing: id 1 | task 2790226 | total time = 52480.72 ms / 42235 tokens
llama-server | 11023.18.977.597 I slot print_timing: id 1 | task 2790226 | graphs reused = 2702483
llama-server | 11023.18.977.600 I slot print_timing: id 1 | task 2790226 | draft acceptance = 0.42200 ( 211 accepted / 500 generated), mean len = 3.11
llama-server | 11023.18.978.752 I slot release: id 1 | task 2790226 | stop processing: n_tokens = 42234, truncated = 0
llama-server | 11023.20.229.807 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 661359432967
llama-server | 11023.20.230.670 I slot launch_slot_: id 0 | task 2790350 | processing task, is_child = 0
llama-server | 11023.20.232.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1978.275 MiB)
llama-server | 11023.27.493.453 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1281.23 tokens per second
llama-server | 11023.29.346.020 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.63 s / 1235.01 tokens per second
llama-server | 11023.31.228.936 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.51 s / 1202.86 tokens per second
llama-server | 11023.33.149.596 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.42 s / 1178.82 tokens per second
llama-server | 11023.35.115.995 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 14336, progress = 0.34, t = 12.38 s / 1157.90 tokens per second
llama-server | 11023.37.116.567 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 16384, progress = 0.39, t = 14.37 s / 1140.31 tokens per second
llama-server | 11023.39.153.499 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 18432, progress = 0.44, t = 16.40 s / 1123.97 tokens per second
llama-server | 11023.41.230.800 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 20480, progress = 0.48, t = 18.46 s / 1109.13 tokens per second
llama-server | 11023.43.347.728 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 22528, progress = 0.53, t = 20.57 s / 1095.25 tokens per second
llama-server | 11023.45.517.483 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 24576, progress = 0.58, t = 22.72 s / 1081.71 tokens per second
llama-server | 11023.47.710.816 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 26624, progress = 0.63, t = 24.91 s / 1068.61 tokens per second
llama-server | 11023.49.941.938 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 28672, progress = 0.68, t = 27.13 s / 1056.65 tokens per second
llama-server | 11023.52.207.815 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 30720, progress = 0.73, t = 29.39 s / 1045.13 tokens per second
llama-server | 11023.54.543.075 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 32768, progress = 0.78, t = 31.68 s / 1034.21 tokens per second
llama-server | 11023.56.878.547 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 34816, progress = 0.82, t = 34.05 s / 1022.59 tokens per second
llama-server | 11023.59.250.115 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 36864, progress = 0.87, t = 36.41 s / 1012.55 tokens per second
llama-server | 11024.01.657.934 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 38912, progress = 0.92, t = 38.81 s / 1002.70 tokens per second
llama-server | 11024.04.116.310 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 40960, progress = 0.97, t = 41.24 s / 993.19 tokens per second
llama-server | 11024.05.089.102 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 41727, progress = 0.99, t = 42.56 s / 980.43 tokens per second
llama-server | 11024.05.811.002 I slot print_timing: id 0 | task 2790350 | prompt processing, n_tokens = 42239, progress = 1.00, t = 43.05 s / 981.11 tokens per second
llama-server | 11024.09.114.509 I slot print_timing: id 0 | task 2790350 | n_gen = 113, tg = 36.59 t/s, tg_3s = 36.92 t/s
llama-server | 11024.10.009.287 I slot print_timing: id 0 | task 2790350 | prompt eval time = 43900.61 ms / 42243 tokens ( 1.04 ms per token, 962.24 tokens per second)
llama-server | 11024.10.009.289 I slot print_timing: id 0 | task 2790350 | eval time = 3955.61 ms / 155 tokens ( 25.69 ms per token, 38.93 tokens per second)
llama-server | 11024.10.009.290 I slot print_timing: id 0 | task 2790350 | total time = 47856.22 ms / 42398 tokens
llama-server | 11024.10.009.291 I slot print_timing: id 0 | task 2790350 | graphs reused = 2702526
llama-server | 11024.10.009.294 I slot print_timing: id 0 | task 2790350 | draft acceptance = 0.50455 ( 111 accepted / 220 generated), mean len = 3.52
llama-server | 11024.10.010.576 I slot release: id 0 | task 2790350 | stop processing: n_tokens = 42398, truncated = 0
llama-server | 11024.11.226.843 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 661414818804
llama-server | 11024.11.227.506 I slot launch_slot_: id 1 | task 2790418 | processing task, is_child = 0
llama-server | 11024.11.229.571 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1966.272 MiB)
llama-server | 11024.18.242.392 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1280.70 tokens per second
llama-server | 11024.20.092.834 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.63 s / 1234.68 tokens per second
llama-server | 11024.21.982.922 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.51 s / 1203.22 tokens per second
llama-server | 11024.23.911.993 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 12288, progress = 0.30, t = 10.44 s / 1176.78 tokens per second
llama-server | 11024.25.869.353 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 14336, progress = 0.34, t = 12.39 s / 1157.27 tokens per second
llama-server | 11024.27.868.624 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 16384, progress = 0.39, t = 14.38 s / 1139.75 tokens per second
llama-server | 11024.29.903.639 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 18432, progress = 0.44, t = 16.40 s / 1123.77 tokens per second
llama-server | 11024.31.981.570 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 20480, progress = 0.49, t = 18.47 s / 1108.99 tokens per second
llama-server | 11024.34.096.184 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 22528, progress = 0.54, t = 20.57 s / 1095.00 tokens per second
llama-server | 11024.36.262.762 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 24576, progress = 0.59, t = 22.72 s / 1081.70 tokens per second
llama-server | 11024.38.454.606 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 26624, progress = 0.64, t = 24.91 s / 1068.68 tokens per second
llama-server | 11024.40.683.189 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 28672, progress = 0.69, t = 27.13 s / 1056.79 tokens per second
llama-server | 11024.42.948.959 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 30720, progress = 0.74, t = 29.39 s / 1045.32 tokens per second
llama-server | 11024.45.283.257 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 32768, progress = 0.79, t = 31.68 s / 1034.37 tokens per second
llama-server | 11024.47.616.279 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 34816, progress = 0.84, t = 34.04 s / 1022.83 tokens per second
llama-server | 11024.49.988.929 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 36864, progress = 0.89, t = 36.40 s / 1012.77 tokens per second
llama-server | 11024.52.394.757 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 38912, progress = 0.93, t = 38.80 s / 1002.94 tokens per second
llama-server | 11024.54.854.175 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 40960, progress = 0.98, t = 41.23 s / 993.41 tokens per second
llama-server | 11024.55.163.196 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 41138, progress = 0.99, t = 41.97 s / 980.24 tokens per second
llama-server | 11024.55.884.109 I slot print_timing: id 1 | task 2790418 | prompt processing, n_tokens = 41650, progress = 1.00, t = 42.38 s / 982.83 tokens per second
llama-server | 11024.58.432.418 I slot print_timing: id 1 | task 2790418 | prompt eval time = 43179.59 ms / 41654 tokens ( 1.04 ms per token, 964.67 tokens per second)
llama-server | 11024.58.432.421 I slot print_timing: id 1 | task 2790418 | eval time = 2353.76 ms / 108 tokens ( 22.00 ms per token, 45.46 tokens per second)
llama-server | 11024.58.432.422 I slot print_timing: id 1 | task 2790418 | total time = 45533.35 ms / 41762 tokens
llama-server | 11024.58.432.422 I slot print_timing: id 1 | task 2790418 | graphs reused = 2702550
llama-server | 11024.58.432.426 I slot print_timing: id 1 | task 2790418 | draft acceptance = 0.63077 ( 82 accepted / 130 generated), mean len = 4.15
llama-server | 11024.58.433.571 I slot release: id 1 | task 2790418 | stop processing: n_tokens = 41762, truncated = 0
llama-server | 11024.59.617.086 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 661465850628
llama-server | 11024.59.617.818 I slot launch_slot_: id 0 | task 2790468 | processing task, is_child = 0
llama-server | 11024.59.619.833 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1975.681 MiB)
llama-server | 11025.06.131.175 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1280.48 tokens per second
llama-server | 11025.07.979.414 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.64 s / 1234.42 tokens per second
llama-server | 11025.09.861.716 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.51 s / 1203.20 tokens per second
llama-server | 11025.11.788.670 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.43 s / 1178.14 tokens per second
llama-server | 11025.13.752.332 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 14336, progress = 0.34, t = 12.38 s / 1158.23 tokens per second
llama-server | 11025.15.751.992 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 16384, progress = 0.39, t = 14.37 s / 1140.15 tokens per second
llama-server | 11025.17.786.302 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 18432, progress = 0.44, t = 16.40 s / 1124.08 tokens per second
llama-server | 11025.19.861.847 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 20480, progress = 0.49, t = 18.46 s / 1109.32 tokens per second
llama-server | 11025.21.977.431 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 22528, progress = 0.54, t = 20.56 s / 1095.46 tokens per second
llama-server | 11025.24.146.360 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 24576, progress = 0.59, t = 22.71 s / 1081.96 tokens per second
llama-server | 11025.26.339.528 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 26624, progress = 0.64, t = 24.91 s / 1068.84 tokens per second
llama-server | 11025.28.569.289 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 28672, progress = 0.69, t = 27.13 s / 1056.91 tokens per second
llama-server | 11025.30.833.703 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 30720, progress = 0.74, t = 29.39 s / 1045.42 tokens per second
llama-server | 11025.33.167.914 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 32768, progress = 0.78, t = 31.68 s / 1034.50 tokens per second
llama-server | 11025.35.501.715 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 34816, progress = 0.83, t = 34.04 s / 1022.88 tokens per second
llama-server | 11025.37.872.705 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 36864, progress = 0.88, t = 36.40 s / 1012.88 tokens per second
llama-server | 11025.40.277.283 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 38912, progress = 0.93, t = 38.79 s / 1003.08 tokens per second
llama-server | 11025.42.734.608 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 40960, progress = 0.98, t = 41.22 s / 993.59 tokens per second
llama-server | 11025.43.159.725 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 41263, progress = 0.99, t = 41.96 s / 983.37 tokens per second
llama-server | 11025.43.878.431 I slot print_timing: id 0 | task 2790468 | prompt processing, n_tokens = 41775, progress = 1.00, t = 42.48 s / 983.34 tokens per second
llama-server | 11025.47.123.380 I slot print_timing: id 0 | task 2790468 | n_gen = 104, tg = 33.78 t/s, tg_3s = 34.11 t/s
llama-server | 11025.50.145.319 I slot print_timing: id 0 | task 2790468 | n_gen = 189, tg = 30.97 t/s, tg_3s = 28.13 t/s
llama-server | 11025.53.187.519 I slot print_timing: id 0 | task 2790468 | n_gen = 267, tg = 29.19 t/s, tg_3s = 25.64 t/s
llama-server | 11025.56.214.298 I slot print_timing: id 0 | task 2790468 | n_gen = 334, tg = 27.43 t/s, tg_3s = 22.14 t/s
llama-server | 11025.59.247.747 I slot print_timing: id 0 | task 2790468 | n_gen = 451, tg = 29.66 t/s, tg_3s = 38.57 t/s
llama-server | 11026.02.298.597 I slot print_timing: id 0 | task 2790468 | n_gen = 542, tg = 29.69 t/s, tg_3s = 29.83 t/s
llama-server | 11026.03.645.450 I slot print_timing: id 0 | task 2790468 | prompt eval time = 43286.73 ms / 41779 tokens ( 1.04 ms per token, 965.17 tokens per second)
llama-server | 11026.03.645.454 I slot print_timing: id 0 | task 2790468 | eval time = 19571.10 ms / 612 tokens ( 32.03 ms per token, 31.22 tokens per second)
llama-server | 11026.03.645.454 I slot print_timing: id 0 | task 2790468 | total time = 62857.83 ms / 42391 tokens
llama-server | 11026.03.645.455 I slot print_timing: id 0 | task 2790468 | graphs reused = 2702766
llama-server | 11026.03.645.458 I slot print_timing: id 0 | task 2790468 | draft acceptance = 0.35890 ( 393 accepted / 1095 generated), mean len = 2.79
llama-server | 11026.03.646.600 I slot release: id 0 | task 2790468 | stop processing: n_tokens = 42391, truncated = 0
llama-server | 11026.04.839.931 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 661514273623
llama-server | 11026.04.840.523 I slot launch_slot_: id 1 | task 2790711 | processing task, is_child = 0
llama-server | 11026.04.842.819 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2017.408 MiB)
llama-server | 11026.11.723.476 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.80 s / 1279.60 tokens per second
llama-server | 11026.13.574.864 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.64 s / 1233.55 tokens per second
llama-server | 11026.15.459.671 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.52 s / 1201.96 tokens per second
llama-server | 11026.17.381.772 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.43 s / 1177.81 tokens per second
llama-server | 11026.19.358.592 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 14336, progress = 0.34, t = 12.39 s / 1156.61 tokens per second
llama-server | 11026.21.359.161 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 16384, progress = 0.39, t = 14.39 s / 1138.61 tokens per second
llama-server | 11026.23.397.402 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 18432, progress = 0.44, t = 16.42 s / 1122.52 tokens per second
llama-server | 11026.25.475.890 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 20480, progress = 0.48, t = 18.49 s / 1107.83 tokens per second
llama-server | 11026.27.594.898 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 22528, progress = 0.53, t = 20.59 s / 1093.87 tokens per second
llama-server | 11026.29.766.417 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 24576, progress = 0.58, t = 22.75 s / 1080.50 tokens per second
llama-server | 11026.31.962.070 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 26624, progress = 0.63, t = 24.94 s / 1067.42 tokens per second
llama-server | 11026.34.193.900 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 28672, progress = 0.68, t = 27.16 s / 1055.50 tokens per second
llama-server | 11026.36.457.176 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 30720, progress = 0.73, t = 29.42 s / 1044.16 tokens per second
llama-server | 11026.38.792.172 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 32768, progress = 0.77, t = 31.71 s / 1033.34 tokens per second
llama-server | 11026.41.130.468 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 34816, progress = 0.82, t = 34.07 s / 1021.81 tokens per second
llama-server | 11026.43.501.961 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 36864, progress = 0.87, t = 36.44 s / 1011.70 tokens per second
llama-server | 11026.45.906.656 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 38912, progress = 0.92, t = 38.83 s / 1002.01 tokens per second
llama-server | 11026.48.366.334 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 40960, progress = 0.97, t = 41.27 s / 992.55 tokens per second
llama-server | 11026.49.403.964 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 41767, progress = 0.99, t = 42.59 s / 980.74 tokens per second
llama-server | 11026.50.141.657 I slot print_timing: id 1 | task 2790711 | prompt processing, n_tokens = 42279, progress = 1.00, t = 43.16 s / 979.68 tokens per second
llama-server | 11026.53.388.456 I slot print_timing: id 1 | task 2790711 | n_gen = 104, tg = 33.74 t/s, tg_3s = 34.07 t/s
llama-server | 11026.54.015.498 I slot print_timing: id 1 | task 2790711 | prompt eval time = 43959.98 ms / 42283 tokens ( 1.04 ms per token, 961.85 tokens per second)
llama-server | 11026.54.015.501 I slot print_timing: id 1 | task 2790711 | eval time = 3679.68 ms / 141 tokens ( 26.28 ms per token, 38.05 tokens per second)
llama-server | 11026.54.015.501 I slot print_timing: id 1 | task 2790711 | total time = 47639.65 ms / 42424 tokens
llama-server | 11026.54.015.502 I slot print_timing: id 1 | task 2790711 | graphs reused = 2702806
llama-server | 11026.54.015.505 I slot print_timing: id 1 | task 2790711 | draft acceptance = 0.48780 ( 100 accepted / 205 generated), mean len = 3.44
llama-server | 11026.54.016.660 I slot release: id 1 | task 2790711 | stop processing: n_tokens = 42424, truncated = 0
llama-server | 11026.55.201.725 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 661579486652
llama-server | 11026.55.202.354 I slot launch_slot_: id 0 | task 2790776 | processing task, is_child = 0
llama-server | 11026.55.204.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1973.254 MiB)
llama-server | 11027.02.277.374 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.79 s / 1282.42 tokens per second
llama-server | 11027.04.127.560 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.63 s / 1235.97 tokens per second
llama-server | 11027.06.007.184 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.50 s / 1204.03 tokens per second
llama-server | 11027.07.937.230 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.43 s / 1178.65 tokens per second
llama-server | 11027.09.894.502 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.37 s / 1158.67 tokens per second
llama-server | 11027.11.892.798 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.36 s / 1141.11 tokens per second
llama-server | 11027.13.928.401 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 18432, progress = 0.43, t = 16.39 s / 1124.76 tokens per second
llama-server | 11027.16.002.340 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 20480, progress = 0.48, t = 18.45 s / 1110.06 tokens per second
llama-server | 11027.18.116.398 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.55 s / 1096.11 tokens per second
llama-server | 11027.20.285.104 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 24576, progress = 0.57, t = 22.70 s / 1082.66 tokens per second
llama-server | 11027.22.475.517 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 26624, progress = 0.62, t = 24.89 s / 1069.54 tokens per second
llama-server | 11027.24.705.444 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 28672, progress = 0.67, t = 27.11 s / 1057.57 tokens per second
llama-server | 11027.26.972.322 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 30720, progress = 0.71, t = 29.37 s / 1046.00 tokens per second
llama-server | 11027.29.315.363 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 32768, progress = 0.76, t = 31.66 s / 1034.99 tokens per second
llama-server | 11027.31.649.468 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 34816, progress = 0.81, t = 34.03 s / 1023.06 tokens per second
llama-server | 11027.34.020.860 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 36864, progress = 0.86, t = 36.39 s / 1012.98 tokens per second
llama-server | 11027.36.425.081 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 38912, progress = 0.91, t = 38.79 s / 1003.17 tokens per second
llama-server | 11027.38.883.047 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 40960, progress = 0.95, t = 41.22 s / 993.68 tokens per second
llama-server | 11027.40.727.150 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 42479, progress = 0.99, t = 43.12 s / 985.10 tokens per second
llama-server | 11027.41.464.049 I slot print_timing: id 0 | task 2790776 | prompt processing, n_tokens = 42991, progress = 1.00, t = 43.90 s / 979.26 tokens per second
llama-server | 11027.45.234.231 I slot print_timing: id 0 | task 2790776 | n_gen = 100, tg = 28.06 t/s, tg_3s = 28.34 t/s
llama-server | 11027.48.275.849 I slot print_timing: id 0 | task 2790776 | n_gen = 184, tg = 27.86 t/s, tg_3s = 27.62 t/s
llama-server | 11027.51.336.660 I slot print_timing: id 0 | task 2790776 | n_gen = 284, tg = 29.39 t/s, tg_3s = 32.67 t/s
llama-server | 11027.54.382.149 I slot print_timing: id 0 | task 2790776 | n_gen = 379, tg = 29.82 t/s, tg_3s = 31.19 t/s
llama-server | 11027.57.428.602 I slot print_timing: id 0 | task 2790776 | n_gen = 470, tg = 29.83 t/s, tg_3s = 29.87 t/s
llama-server | 11028.00.495.651 I slot print_timing: id 0 | task 2790776 | n_gen = 551, tg = 29.27 t/s, tg_3s = 26.41 t/s
llama-server | 11028.03.550.470 I slot print_timing: id 0 | task 2790776 | n_gen = 620, tg = 28.34 t/s, tg_3s = 22.59 t/s
llama-server | 11028.06.607.071 I slot print_timing: id 0 | task 2790776 | n_gen = 716, tg = 28.71 t/s, tg_3s = 31.41 t/s
llama-server | 11028.09.689.445 I slot print_timing: id 0 | task 2790776 | n_gen = 845, tg = 30.16 t/s, tg_3s = 41.85 t/s
llama-server | 11028.12.761.497 I slot print_timing: id 0 | task 2790776 | n_gen = 963, tg = 30.98 t/s, tg_3s = 38.41 t/s
llama-server | 11028.15.848.383 I slot print_timing: id 0 | task 2790776 | n_gen = 1094, tg = 32.01 t/s, tg_3s = 42.44 t/s
llama-server | 11028.18.929.189 I slot print_timing: id 0 | task 2790776 | n_gen = 1250, tg = 33.55 t/s, tg_3s = 50.64 t/s
llama-server | 11028.20.486.335 I slot print_timing: id 0 | task 2790776 | prompt eval time = 44766.08 ms / 42995 tokens ( 1.04 ms per token, 960.44 tokens per second)
llama-server | 11028.20.486.338 I slot print_timing: id 0 | task 2790776 | eval time = 38780.06 ms / 1332 tokens ( 29.14 ms per token, 34.32 tokens per second)
llama-server | 11028.20.486.339 I slot print_timing: id 0 | task 2790776 | total time = 83546.14 ms / 44327 tokens
llama-server | 11028.20.486.339 I slot print_timing: id 0 | task 2790776 | graphs reused = 2703229
llama-server | 11028.20.486.342 I slot print_timing: id 0 | task 2790776 | draft acceptance = 0.41953 ( 902 accepted / 2150 generated), mean len = 3.10
llama-server | 11028.20.487.541 I slot release: id 0 | task 2790776 | stop processing: n_tokens = 44327, truncated = 0
llama-server | 11028.37.817.048 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 661629856712
llama-server | 11028.37.817.592 I slot launch_slot_: id 1 | task 2791230 | processing task, is_child = 0
llama-server | 11028.37.820.739 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1978.707 MiB)
llama-server | 11028.45.114.197 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.75 s / 1294.55 tokens per second
llama-server | 11028.46.940.477 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.56 s / 1248.38 tokens per second
llama-server | 11028.48.802.926 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.42 s / 1216.49 tokens per second
llama-server | 11028.50.703.240 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.31 s / 1192.12 tokens per second
llama-server | 11028.52.652.642 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 14336, progress = 0.34, t = 12.24 s / 1171.37 tokens per second
llama-server | 11028.54.635.422 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 16384, progress = 0.39, t = 14.22 s / 1152.40 tokens per second
llama-server | 11028.56.654.766 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 18432, progress = 0.43, t = 16.23 s / 1135.71 tokens per second
llama-server | 11028.58.715.439 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 20480, progress = 0.48, t = 18.28 s / 1120.39 tokens per second
llama-server | 11029.00.817.714 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 22528, progress = 0.53, t = 20.37 s / 1105.97 tokens per second
llama-server | 11029.02.983.510 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 24576, progress = 0.58, t = 22.51 s / 1092.01 tokens per second
llama-server | 11029.05.166.967 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 26624, progress = 0.63, t = 24.70 s / 1077.97 tokens per second
llama-server | 11029.07.389.247 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 28672, progress = 0.68, t = 26.91 s / 1065.49 tokens per second
llama-server | 11029.09.646.598 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 30720, progress = 0.72, t = 29.16 s / 1053.53 tokens per second
llama-server | 11029.11.975.249 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 32768, progress = 0.77, t = 31.44 s / 1042.15 tokens per second
llama-server | 11029.14.304.097 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 34816, progress = 0.82, t = 33.80 s / 1030.07 tokens per second
llama-server | 11029.16.671.179 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 36864, progress = 0.87, t = 36.16 s / 1019.61 tokens per second
llama-server | 11029.19.080.396 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 38912, progress = 0.92, t = 38.55 s / 1009.42 tokens per second
llama-server | 11029.21.534.395 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 40960, progress = 0.96, t = 40.99 s / 999.37 tokens per second
llama-server | 11029.22.761.336 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 41961, progress = 0.99, t = 42.30 s / 991.90 tokens per second
llama-server | 11029.23.495.140 I slot print_timing: id 1 | task 2791230 | prompt processing, n_tokens = 42473, progress = 1.00, t = 43.06 s / 986.40 tokens per second
llama-server | 11029.26.761.415 I slot print_timing: id 1 | task 2791230 | n_gen = 103, tg = 33.21 t/s, tg_3s = 33.53 t/s
llama-server | 11029.29.794.470 I slot print_timing: id 1 | task 2791230 | n_gen = 202, tg = 32.93 t/s, tg_3s = 32.64 t/s
llama-server | 11029.32.839.101 I slot print_timing: id 1 | task 2791230 | n_gen = 273, tg = 29.73 t/s, tg_3s = 23.32 t/s
llama-server | 11029.35.878.503 I slot print_timing: id 1 | task 2791230 | n_gen = 363, tg = 29.70 t/s, tg_3s = 29.61 t/s
llama-server | 11029.38.922.323 I slot print_timing: id 1 | task 2791230 | n_gen = 488, tg = 31.97 t/s, tg_3s = 41.07 t/s
llama-server | 11029.39.012.343 I slot print_timing: id 1 | task 2791230 | prompt eval time = 43862.14 ms / 42477 tokens ( 1.03 ms per token, 968.42 tokens per second)
llama-server | 11029.39.012.346 I slot print_timing: id 1 | task 2791230 | eval time = 15322.44 ms / 493 tokens ( 31.14 ms per token, 32.11 tokens per second)
llama-server | 11029.39.012.346 I slot print_timing: id 1 | task 2791230 | total time = 59184.58 ms / 42970 tokens
llama-server | 11029.39.012.347 I slot print_timing: id 1 | task 2791230 | graphs reused = 2703397
llama-server | 11029.39.012.350 I slot print_timing: id 1 | task 2791230 | draft acceptance = 0.37661 ( 322 accepted / 855 generated), mean len = 2.88
llama-server | 11029.39.013.522 I slot release: id 1 | task 2791230 | stop processing: n_tokens = 42970, truncated = 0
llama-server | 11029.40.327.291 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 661716327593
llama-server | 11029.40.327.918 I slot launch_slot_: id 0 | task 2791425 | processing task, is_child = 0
llama-server | 11029.40.330.018 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1957.560 MiB)
llama-server | 11029.45.043.485 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.00 s / 1363.90 tokens per second
llama-server | 11029.46.857.709 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1277.78 tokens per second
llama-server | 11029.48.708.426 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.65 s / 1232.04 tokens per second
llama-server | 11029.50.597.368 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.53 s / 1201.04 tokens per second
llama-server | 11029.52.520.262 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 12288, progress = 0.29, t = 10.44 s / 1176.57 tokens per second
llama-server | 11029.54.489.968 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.40 s / 1155.76 tokens per second
llama-server | 11029.56.496.564 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.40 s / 1138.16 tokens per second
llama-server | 11029.58.534.118 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 18432, progress = 0.43, t = 16.43 s / 1121.82 tokens per second
llama-server | 11030.00.610.650 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 20480, progress = 0.48, t = 18.49 s / 1107.38 tokens per second
llama-server | 11030.02.727.009 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.60 s / 1093.57 tokens per second
llama-server | 11030.04.898.571 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 24576, progress = 0.57, t = 22.75 s / 1080.27 tokens per second
llama-server | 11030.07.092.557 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 26624, progress = 0.62, t = 24.95 s / 1067.25 tokens per second
llama-server | 11030.09.322.585 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 28672, progress = 0.67, t = 27.17 s / 1055.44 tokens per second
llama-server | 11030.11.588.314 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 30720, progress = 0.72, t = 29.42 s / 1044.10 tokens per second
llama-server | 11030.13.922.245 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 32768, progress = 0.76, t = 31.71 s / 1033.22 tokens per second
llama-server | 11030.16.257.627 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 34816, progress = 0.81, t = 34.08 s / 1021.74 tokens per second
llama-server | 11030.18.630.840 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 36864, progress = 0.86, t = 36.44 s / 1011.70 tokens per second
llama-server | 11030.21.038.761 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 38912, progress = 0.91, t = 38.84 s / 1001.91 tokens per second
llama-server | 11030.23.498.268 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 40960, progress = 0.95, t = 41.27 s / 992.44 tokens per second
llama-server | 11030.25.296.484 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 42414, progress = 0.99, t = 43.17 s / 982.40 tokens per second
llama-server | 11030.26.072.132 I slot print_timing: id 0 | task 2791425 | prompt processing, n_tokens = 42926, progress = 1.00, t = 43.94 s / 976.86 tokens per second
llama-server | 11030.29.109.760 I slot print_timing: id 0 | task 2791425 | prompt eval time = 44781.32 ms / 42930 tokens ( 1.04 ms per token, 958.66 tokens per second)
llama-server | 11030.29.109.764 I slot print_timing: id 0 | task 2791425 | eval time = 2825.39 ms / 126 tokens ( 22.60 ms per token, 44.24 tokens per second)
llama-server | 11030.29.109.764 I slot print_timing: id 0 | task 2791425 | total time = 47606.71 ms / 43056 tokens
llama-server | 11030.29.109.765 I slot print_timing: id 0 | task 2791425 | graphs reused = 2703426
llama-server | 11030.29.109.768 I slot print_timing: id 0 | task 2791425 | draft acceptance = 0.61290 ( 95 accepted / 155 generated), mean len = 4.06
llama-server | 11030.29.110.958 I slot release: id 0 | task 2791425 | stop processing: n_tokens = 43056, truncated = 0
llama-server | 11030.30.292.790 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 661794853574
llama-server | 11030.30.293.575 I slot launch_slot_: id 1 | task 2791480 | processing task, is_child = 0
llama-server | 11030.30.295.552 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1978.474 MiB)
llama-server | 11030.37.345.753 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.80 s / 1281.19 tokens per second
llama-server | 11030.39.198.329 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.63 s / 1235.24 tokens per second
llama-server | 11030.41.082.250 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.51 s / 1203.17 tokens per second
llama-server | 11030.43.007.524 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.43 s / 1178.09 tokens per second
llama-server | 11030.44.964.268 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.38 s / 1158.25 tokens per second
llama-server | 11030.46.970.779 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.36 s / 1140.72 tokens per second
llama-server | 11030.49.005.138 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 18432, progress = 0.43, t = 16.40 s / 1123.98 tokens per second
llama-server | 11030.51.080.214 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.46 s / 1109.29 tokens per second
llama-server | 11030.53.194.485 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.56 s / 1095.49 tokens per second
llama-server | 11030.55.364.090 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 24576, progress = 0.57, t = 22.71 s / 1082.04 tokens per second
llama-server | 11030.57.567.126 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 26624, progress = 0.62, t = 24.91 s / 1068.86 tokens per second
llama-server | 11030.59.801.043 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.14 s / 1056.47 tokens per second
llama-server | 11031.02.066.991 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 30720, progress = 0.71, t = 29.40 s / 1044.91 tokens per second
llama-server | 11031.04.399.736 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 32768, progress = 0.76, t = 31.69 s / 1034.03 tokens per second
llama-server | 11031.06.734.489 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 34816, progress = 0.81, t = 34.05 s / 1022.51 tokens per second
llama-server | 11031.09.107.319 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 36864, progress = 0.85, t = 36.41 s / 1012.41 tokens per second
llama-server | 11031.11.512.224 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 38912, progress = 0.90, t = 38.81 s / 1002.63 tokens per second
llama-server | 11031.13.970.001 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 40960, progress = 0.95, t = 41.24 s / 993.18 tokens per second
llama-server | 11031.16.142.339 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 42689, progress = 0.99, t = 43.72 s / 976.33 tokens per second
llama-server | 11031.16.872.239 I slot print_timing: id 1 | task 2791480 | prompt processing, n_tokens = 43201, progress = 1.00, t = 44.26 s / 976.16 tokens per second
llama-server | 11031.20.117.409 I slot print_timing: id 1 | task 2791480 | n_gen = 117, tg = 38.63 t/s, tg_3s = 38.96 t/s
llama-server | 11031.23.166.674 I slot print_timing: id 1 | task 2791480 | n_gen = 213, tg = 35.03 t/s, tg_3s = 31.48 t/s
llama-server | 11031.26.235.910 I slot print_timing: id 1 | task 2791480 | n_gen = 330, tg = 36.07 t/s, tg_3s = 38.12 t/s
llama-server | 11031.29.290.916 I slot print_timing: id 1 | task 2791480 | n_gen = 427, tg = 34.99 t/s, tg_3s = 31.75 t/s
llama-server | 11031.32.341.125 I slot print_timing: id 1 | task 2791480 | n_gen = 520, tg = 34.09 t/s, tg_3s = 30.49 t/s
llama-server | 11031.35.409.438 I slot print_timing: id 1 | task 2791480 | n_gen = 608, tg = 33.18 t/s, tg_3s = 28.68 t/s
llama-server | 11031.38.471.605 I slot print_timing: id 1 | task 2791480 | n_gen = 696, tg = 32.54 t/s, tg_3s = 28.74 t/s
llama-server | 11031.41.537.984 I slot print_timing: id 1 | task 2791480 | n_gen = 803, tg = 32.84 t/s, tg_3s = 34.89 t/s
llama-server | 11031.44.619.388 I slot print_timing: id 1 | task 2791480 | n_gen = 890, tg = 32.32 t/s, tg_3s = 28.23 t/s
llama-server | 11031.47.688.195 I slot print_timing: id 1 | task 2791480 | n_gen = 986, tg = 32.22 t/s, tg_3s = 31.28 t/s
llama-server | 11031.50.764.234 I slot print_timing: id 1 | task 2791480 | n_gen = 1081, tg = 32.10 t/s, tg_3s = 30.88 t/s
llama-server | 11031.53.842.127 I slot print_timing: id 1 | task 2791480 | n_gen = 1163, tg = 31.64 t/s, tg_3s = 26.64 t/s
llama-server | 11031.56.910.045 I slot print_timing: id 1 | task 2791480 | n_gen = 1248, tg = 31.34 t/s, tg_3s = 27.71 t/s
llama-server | 11031.59.987.451 I slot print_timing: id 1 | task 2791480 | n_gen = 1336, tg = 31.14 t/s, tg_3s = 28.60 t/s
llama-server | 11032.02.990.710 I slot print_timing: id 1 | task 2791480 | n_gen = 1424, tg = 31.02 t/s, tg_3s = 29.30 t/s
llama-server | 11032.06.068.902 I slot print_timing: id 1 | task 2791480 | n_gen = 1519, tg = 31.01 t/s, tg_3s = 30.86 t/s
llama-server | 11032.09.072.693 I slot print_timing: id 1 | task 2791480 | n_gen = 1609, tg = 30.95 t/s, tg_3s = 29.96 t/s
llama-server | 11032.12.157.327 I slot print_timing: id 1 | task 2791480 | n_gen = 1693, tg = 30.74 t/s, tg_3s = 27.23 t/s
llama-server | 11032.15.240.129 I slot print_timing: id 1 | task 2791480 | n_gen = 1759, tg = 30.24 t/s, tg_3s = 21.41 t/s
llama-server | 11032.18.324.629 I slot print_timing: id 1 | task 2791480 | n_gen = 1843, tg = 30.09 t/s, tg_3s = 27.23 t/s
llama-server | 11032.21.337.482 I slot print_timing: id 1 | task 2791480 | n_gen = 1918, tg = 29.85 t/s, tg_3s = 24.89 t/s
llama-server | 11032.24.427.168 I slot print_timing: id 1 | task 2791480 | n_gen = 2019, tg = 29.98 t/s, tg_3s = 32.69 t/s
llama-server | 11032.27.515.741 I slot print_timing: id 1 | task 2791480 | n_gen = 2103, tg = 29.86 t/s, tg_3s = 27.20 t/s
llama-server | 11032.30.536.234 I slot print_timing: id 1 | task 2791480 | n_gen = 2203, tg = 29.99 t/s, tg_3s = 33.11 t/s
llama-server | 11032.33.539.933 I slot print_timing: id 1 | task 2791480 | n_gen = 2295, tg = 30.02 t/s, tg_3s = 30.63 t/s
llama-server | 11032.36.561.719 I slot print_timing: id 1 | task 2791480 | n_gen = 2395, tg = 30.13 t/s, tg_3s = 33.09 t/s
llama-server | 11032.38.664.555 I slot print_timing: id 1 | task 2791480 | prompt eval time = 45108.85 ms / 43205 tokens ( 1.04 ms per token, 957.79 tokens per second)
llama-server | 11032.38.664.558 I slot print_timing: id 1 | task 2791480 | eval time = 81549.81 ms / 2485 tokens ( 32.83 ms per token, 30.46 tokens per second)
llama-server | 11032.38.664.559 I slot print_timing: id 1 | task 2791480 | total time = 126658.67 ms / 45690 tokens
llama-server | 11032.38.664.559 I slot print_timing: id 1 | task 2791480 | graphs reused = 2704315
llama-server | 11032.38.664.562 I slot print_timing: id 1 | task 2791480 | draft acceptance = 0.35200 ( 1584 accepted / 4500 generated), mean len = 2.76
llama-server | 11032.38.665.755 I slot release: id 1 | task 2791480 | stop processing: n_tokens = 45689, truncated = 0
llama-server | 11032.40.020.734 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 661844951010
llama-server | 11032.40.021.227 I slot launch_slot_: id 0 | task 2792404 | processing task, is_child = 0
llama-server | 11032.40.023.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1979.571 MiB)
llama-server | 11032.45.208.886 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1361.57 tokens per second
llama-server | 11032.47.024.973 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.82 s / 1275.86 tokens per second
llama-server | 11032.48.882.771 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.66 s / 1230.52 tokens per second
llama-server | 11032.50.769.984 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.54 s / 1198.83 tokens per second
llama-server | 11032.52.707.112 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.47 s / 1173.54 tokens per second
llama-server | 11032.54.674.275 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.42 s / 1153.88 tokens per second
llama-server | 11032.56.678.742 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.42 s / 1136.23 tokens per second
llama-server | 11032.58.718.815 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 18432, progress = 0.43, t = 16.45 s / 1120.21 tokens per second
llama-server | 11033.00.798.715 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.52 s / 1105.72 tokens per second
llama-server | 11033.02.919.819 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.63 s / 1091.96 tokens per second
llama-server | 11033.05.091.645 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 24576, progress = 0.57, t = 22.78 s / 1078.66 tokens per second
llama-server | 11033.07.287.994 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 26624, progress = 0.61, t = 24.98 s / 1065.76 tokens per second
llama-server | 11033.09.522.819 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.20 s / 1053.95 tokens per second
llama-server | 11033.11.790.994 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 30720, progress = 0.71, t = 29.47 s / 1042.57 tokens per second
llama-server | 11033.14.129.670 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 32768, progress = 0.76, t = 31.76 s / 1031.75 tokens per second
llama-server | 11033.16.467.547 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 34816, progress = 0.80, t = 34.12 s / 1020.29 tokens per second
llama-server | 11033.18.843.673 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 36864, progress = 0.85, t = 36.49 s / 1010.27 tokens per second
llama-server | 11033.21.252.543 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 38912, progress = 0.90, t = 38.89 s / 1000.52 tokens per second
llama-server | 11033.23.712.812 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 40960, progress = 0.94, t = 41.33 s / 991.16 tokens per second
llama-server | 11033.26.069.726 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 42845, progress = 0.99, t = 43.81 s / 977.95 tokens per second
llama-server | 11033.26.841.449 I slot print_timing: id 0 | task 2792404 | prompt processing, n_tokens = 43357, progress = 1.00, t = 44.56 s / 972.93 tokens per second
llama-server | 11033.29.934.553 I slot print_timing: id 0 | task 2792404 | prompt eval time = 45372.91 ms / 43361 tokens ( 1.05 ms per token, 955.66 tokens per second)
llama-server | 11033.29.934.556 I slot print_timing: id 0 | task 2792404 | eval time = 2898.17 ms / 112 tokens ( 26.11 ms per token, 38.30 tokens per second)
llama-server | 11033.29.934.557 I slot print_timing: id 0 | task 2792404 | total time = 48271.07 ms / 43473 tokens
llama-server | 11033.29.934.558 I slot print_timing: id 0 | task 2792404 | graphs reused = 2704346
llama-server | 11033.29.934.561 I slot print_timing: id 0 | task 2792404 | draft acceptance = 0.49375 ( 79 accepted / 160 generated), mean len = 3.47
llama-server | 11033.29.935.849 I slot release: id 0 | task 2792404 | stop processing: n_tokens = 43472, truncated = 0
llama-server | 11033.31.181.760 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 661974505807
llama-server | 11033.31.182.391 I slot launch_slot_: id 1 | task 2792460 | processing task, is_child = 0
llama-server | 11033.31.184.533 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2042.844 MiB)
llama-server | 11033.38.527.506 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.79 s / 1282.09 tokens per second
llama-server | 11033.40.379.170 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.63 s / 1235.73 tokens per second
llama-server | 11033.42.259.659 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.51 s / 1203.83 tokens per second
llama-server | 11033.44.198.996 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.43 s / 1178.31 tokens per second
llama-server | 11033.46.158.694 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.39 s / 1157.34 tokens per second
llama-server | 11033.48.157.268 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.37 s / 1139.98 tokens per second
llama-server | 11033.50.193.361 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 18432, progress = 0.36, t = 16.40 s / 1123.84 tokens per second
llama-server | 11033.52.268.858 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 20480, progress = 0.40, t = 18.47 s / 1109.07 tokens per second
llama-server | 11033.54.388.322 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 22528, progress = 0.44, t = 20.57 s / 1095.17 tokens per second
llama-server | 11033.56.557.747 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 24576, progress = 0.48, t = 22.72 s / 1081.55 tokens per second
llama-server | 11033.58.748.376 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 26624, progress = 0.52, t = 24.92 s / 1068.52 tokens per second
llama-server | 11034.00.977.210 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 28672, progress = 0.56, t = 27.13 s / 1056.68 tokens per second
llama-server | 11034.03.241.739 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 30720, progress = 0.60, t = 29.39 s / 1045.24 tokens per second
llama-server | 11034.05.577.496 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 32768, progress = 0.64, t = 31.68 s / 1034.26 tokens per second
llama-server | 11034.07.912.103 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 34816, progress = 0.68, t = 34.04 s / 1022.71 tokens per second
llama-server | 11034.10.285.358 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 36864, progress = 0.72, t = 36.40 s / 1012.63 tokens per second
llama-server | 11034.12.690.934 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 38912, progress = 0.75, t = 38.80 s / 1002.78 tokens per second
llama-server | 11034.15.150.768 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 40960, progress = 0.79, t = 41.24 s / 993.29 tokens per second
llama-server | 11034.17.628.052 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 43008, progress = 0.83, t = 43.72 s / 983.66 tokens per second
llama-server | 11034.20.142.977 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 45056, progress = 0.87, t = 46.23 s / 974.66 tokens per second
llama-server | 11034.22.692.091 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 47104, progress = 0.91, t = 48.77 s / 965.88 tokens per second
llama-server | 11034.25.298.281 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 49152, progress = 0.95, t = 51.34 s / 957.30 tokens per second
llama-server | 11034.27.790.356 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 51028, progress = 0.99, t = 53.98 s / 945.39 tokens per second
llama-server | 11034.28.583.786 I slot print_timing: id 1 | task 2792460 | prompt processing, n_tokens = 51540, progress = 1.00, t = 54.74 s / 941.48 tokens per second
llama-server | 11034.32.358.396 I slot print_timing: id 1 | task 2792460 | n_gen = 100, tg = 27.65 t/s, tg_3s = 27.93 t/s
llama-server | 11034.35.369.504 I slot print_timing: id 1 | task 2792460 | n_gen = 173, tg = 26.10 t/s, tg_3s = 24.24 t/s
llama-server | 11034.38.373.755 I slot print_timing: id 1 | task 2792460 | n_gen = 263, tg = 27.30 t/s, tg_3s = 29.96 t/s
llama-server | 11034.41.378.914 I slot print_timing: id 1 | task 2792460 | prompt eval time = 55587.87 ms / 51544 tokens ( 1.08 ms per token, 927.25 tokens per second)
llama-server | 11034.41.378.918 I slot print_timing: id 1 | task 2792460 | eval time = 12600.62 ms / 379 tokens ( 33.33 ms per token, 30.00 tokens per second)
llama-server | 11034.41.378.918 I slot print_timing: id 1 | task 2792460 | total time = 68188.49 ms / 51923 tokens
llama-server | 11034.41.378.919 I slot print_timing: id 1 | task 2792460 | graphs reused = 2704478
llama-server | 11034.41.378.922 I slot print_timing: id 1 | task 2792460 | draft acceptance = 0.36567 ( 245 accepted / 670 generated), mean len = 2.83
llama-server | 11034.41.380.449 I slot release: id 1 | task 2792460 | stop processing: n_tokens = 51923, truncated = 0
llama-server | 11034.42.677.941 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 662025775901
llama-server | 11034.42.678.593 I slot launch_slot_: id 0 | task 2792622 | processing task, is_child = 0
llama-server | 11034.42.681.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1997.725 MiB)
llama-server | 11034.42.843.953 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2000.585 MiB)
llama-server | 11034.49.593.398 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 6144, progress = 0.12, t = 4.80 s / 1280.32 tokens per second
llama-server | 11034.51.447.567 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 8192, progress = 0.16, t = 6.64 s / 1233.99 tokens per second
llama-server | 11034.53.331.445 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 10240, progress = 0.20, t = 8.52 s / 1201.92 tokens per second
llama-server | 11034.55.254.151 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 12288, progress = 0.24, t = 10.43 s / 1177.89 tokens per second
llama-server | 11034.57.225.890 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 14336, progress = 0.28, t = 12.39 s / 1157.20 tokens per second
llama-server | 11034.59.228.235 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 16384, progress = 0.32, t = 14.38 s / 1139.07 tokens per second
llama-server | 11035.01.265.370 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 18432, progress = 0.36, t = 16.41 s / 1122.89 tokens per second
llama-server | 11035.03.341.185 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 20480, progress = 0.40, t = 18.48 s / 1108.18 tokens per second
llama-server | 11035.05.457.043 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 22528, progress = 0.44, t = 20.58 s / 1094.43 tokens per second
llama-server | 11035.07.629.795 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 24576, progress = 0.47, t = 22.73 s / 1081.05 tokens per second
llama-server | 11035.09.823.229 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 26624, progress = 0.51, t = 24.93 s / 1067.90 tokens per second
llama-server | 11035.12.054.640 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 28672, progress = 0.55, t = 27.15 s / 1055.97 tokens per second
llama-server | 11035.14.319.062 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 30720, progress = 0.59, t = 29.41 s / 1044.56 tokens per second
llama-server | 11035.16.653.568 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 32768, progress = 0.63, t = 31.70 s / 1033.73 tokens per second
llama-server | 11035.18.993.956 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 34816, progress = 0.67, t = 34.06 s / 1022.11 tokens per second
llama-server | 11035.21.367.317 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 36864, progress = 0.71, t = 36.43 s / 1011.96 tokens per second
llama-server | 11035.23.775.101 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 38912, progress = 0.75, t = 38.83 s / 1002.16 tokens per second
llama-server | 11035.26.232.829 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 40960, progress = 0.79, t = 41.26 s / 992.71 tokens per second
llama-server | 11035.28.711.389 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 43008, progress = 0.83, t = 43.75 s / 983.11 tokens per second
llama-server | 11035.31.225.104 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 45056, progress = 0.87, t = 46.25 s / 974.17 tokens per second
llama-server | 11035.33.774.118 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 47104, progress = 0.91, t = 48.79 s / 965.41 tokens per second
llama-server | 11035.36.378.531 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 49152, progress = 0.95, t = 51.37 s / 956.89 tokens per second
llama-server | 11035.38.998.019 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 51200, progress = 0.99, t = 54.00 s / 948.19 tokens per second
llama-server | 11035.39.143.059 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 51236, progress = 0.99, t = 54.76 s / 935.66 tokens per second
llama-server | 11035.39.913.899 I slot print_timing: id 0 | task 2792622 | prompt processing, n_tokens = 51748, progress = 1.00, t = 55.02 s / 940.61 tokens per second
llama-server | 11035.43.140.913 I slot print_timing: id 0 | task 2792622 | n_gen = 124, tg = 40.62 t/s, tg_3s = 40.95 t/s
llama-server | 11035.46.156.782 I slot print_timing: id 0 | task 2792622 | n_gen = 217, tg = 35.74 t/s, tg_3s = 30.84 t/s
llama-server | 11035.49.160.639 I slot print_timing: id 0 | task 2792622 | n_gen = 302, tg = 33.27 t/s, tg_3s = 28.30 t/s
llama-server | 11035.52.167.670 I slot print_timing: id 0 | task 2792622 | n_gen = 390, tg = 32.27 t/s, tg_3s = 29.26 t/s
llama-server | 11035.55.197.041 I slot print_timing: id 0 | task 2792622 | n_gen = 501, tg = 33.15 t/s, tg_3s = 36.64 t/s
llama-server | 11035.58.215.189 I slot print_timing: id 0 | task 2792622 | n_gen = 614, tg = 33.86 t/s, tg_3s = 37.44 t/s
llama-server | 11036.01.227.408 I slot print_timing: id 0 | task 2792622 | n_gen = 693, tg = 32.77 t/s, tg_3s = 26.23 t/s
llama-server | 11036.04.257.269 I slot print_timing: id 0 | task 2792622 | n_gen = 784, tg = 32.43 t/s, tg_3s = 30.03 t/s
llama-server | 11036.07.275.488 I slot print_timing: id 0 | task 2792622 | n_gen = 887, tg = 32.62 t/s, tg_3s = 34.13 t/s
llama-server | 11036.10.314.830 I slot print_timing: id 0 | task 2792622 | n_gen = 994, tg = 32.88 t/s, tg_3s = 35.20 t/s
llama-server | 11036.13.341.992 I slot print_timing: id 0 | task 2792622 | n_gen = 1094, tg = 32.89 t/s, tg_3s = 33.03 t/s
llama-server | 11036.16.368.801 I slot print_timing: id 0 | task 2792622 | n_gen = 1201, tg = 33.10 t/s, tg_3s = 35.35 t/s
llama-server | 11036.19.411.076 I slot print_timing: id 0 | task 2792622 | n_gen = 1283, tg = 32.62 t/s, tg_3s = 26.95 t/s
llama-server | 11036.22.446.228 I slot print_timing: id 0 | task 2792622 | n_gen = 1382, tg = 32.62 t/s, tg_3s = 32.62 t/s
llama-server | 11036.25.474.217 I slot print_timing: id 0 | task 2792622 | n_gen = 1440, tg = 31.72 t/s, tg_3s = 19.15 t/s
llama-server | 11036.28.517.633 I slot print_timing: id 0 | task 2792622 | n_gen = 1516, tg = 31.30 t/s, tg_3s = 24.97 t/s
llama-server | 11036.31.548.909 I slot print_timing: id 0 | task 2792622 | n_gen = 1585, tg = 30.80 t/s, tg_3s = 22.76 t/s
llama-server | 11036.34.577.278 I slot print_timing: id 0 | task 2792622 | n_gen = 1660, tg = 30.46 t/s, tg_3s = 24.77 t/s
llama-server | 11036.37.607.350 I slot print_timing: id 0 | task 2792622 | n_gen = 1730, tg = 30.07 t/s, tg_3s = 23.10 t/s
llama-server | 11036.40.662.972 I slot print_timing: id 0 | task 2792622 | n_gen = 1822, tg = 30.07 t/s, tg_3s = 30.11 t/s
llama-server | 11036.43.706.964 I slot print_timing: id 0 | task 2792622 | n_gen = 1917, tg = 30.13 t/s, tg_3s = 31.21 t/s
llama-server | 11036.46.743.458 I slot print_timing: id 0 | task 2792622 | n_gen = 2003, tg = 30.05 t/s, tg_3s = 28.32 t/s
llama-server | 11036.49.799.820 I slot print_timing: id 0 | task 2792622 | n_gen = 2082, tg = 29.86 t/s, tg_3s = 25.85 t/s
llama-server | 11036.52.843.175 I slot print_timing: id 0 | task 2792622 | n_gen = 2164, tg = 29.74 t/s, tg_3s = 26.94 t/s
llama-server | 11036.55.884.119 I slot print_timing: id 0 | task 2792622 | n_gen = 2247, tg = 29.64 t/s, tg_3s = 27.29 t/s
llama-server | 11036.58.950.897 I slot print_timing: id 0 | task 2792622 | n_gen = 2355, tg = 29.86 t/s, tg_3s = 35.22 t/s
llama-server | 11037.01.998.330 I slot print_timing: id 0 | task 2792622 | n_gen = 2436, tg = 29.74 t/s, tg_3s = 26.58 t/s
llama-server | 11037.05.064.672 I slot print_timing: id 0 | task 2792622 | n_gen = 2524, tg = 29.70 t/s, tg_3s = 28.70 t/s
llama-server | 11037.08.112.914 I slot print_timing: id 0 | task 2792622 | n_gen = 2602, tg = 29.56 t/s, tg_3s = 25.59 t/s
llama-server | 11037.11.166.897 I slot print_timing: id 0 | task 2792622 | n_gen = 2691, tg = 29.54 t/s, tg_3s = 29.14 t/s
llama-server | 11037.14.220.250 I slot print_timing: id 0 | task 2792622 | n_gen = 2770, tg = 29.42 t/s, tg_3s = 25.87 t/s
llama-server | 11037.17.291.968 I slot print_timing: id 0 | task 2792622 | n_gen = 2858, tg = 29.40 t/s, tg_3s = 28.65 t/s
llama-server | 11037.20.349.223 I slot print_timing: id 0 | task 2792622 | n_gen = 2949, tg = 29.41 t/s, tg_3s = 29.77 t/s
llama-server | 11037.23.406.044 I slot print_timing: id 0 | task 2792622 | n_gen = 3017, tg = 29.20 t/s, tg_3s = 22.25 t/s
llama-server | 11037.26.475.767 I slot print_timing: id 0 | task 2792622 | n_gen = 3073, tg = 28.88 t/s, tg_3s = 18.24 t/s
llama-server | 11037.29.538.092 I slot print_timing: id 0 | task 2792622 | n_gen = 3168, tg = 28.94 t/s, tg_3s = 31.02 t/s
llama-server | 11037.32.605.190 I slot print_timing: id 0 | task 2792622 | n_gen = 3287, tg = 29.21 t/s, tg_3s = 38.80 t/s
llama-server | 11037.35.685.732 I slot print_timing: id 0 | task 2792622 | n_gen = 3358, tg = 29.05 t/s, tg_3s = 23.05 t/s
llama-server | 11037.38.754.767 I slot print_timing: id 0 | task 2792622 | n_gen = 3462, tg = 29.17 t/s, tg_3s = 33.89 t/s
llama-server | 11037.41.837.105 I slot print_timing: id 0 | task 2792622 | n_gen = 3559, tg = 29.23 t/s, tg_3s = 31.47 t/s
llama-server | 11037.44.908.660 I slot print_timing: id 0 | task 2792622 | n_gen = 3648, tg = 29.22 t/s, tg_3s = 28.98 t/s
llama-server | 11037.47.976.100 I slot print_timing: id 0 | task 2792622 | n_gen = 3726, tg = 29.13 t/s, tg_3s = 25.43 t/s
llama-server | 11037.51.062.409 I slot print_timing: id 0 | task 2792622 | n_gen = 3818, tg = 29.15 t/s, tg_3s = 29.81 t/s
llama-server | 11037.54.138.653 I slot print_timing: id 0 | task 2792622 | n_gen = 3924, tg = 29.27 t/s, tg_3s = 34.46 t/s
llama-server | 11037.57.210.219 I slot print_timing: id 0 | task 2792622 | n_gen = 3996, tg = 29.14 t/s, tg_3s = 23.44 t/s
llama-server | 11038.00.303.165 I slot print_timing: id 0 | task 2792622 | n_gen = 4076, tg = 29.07 t/s, tg_3s = 25.87 t/s
llama-server | 11038.03.388.883 I slot print_timing: id 0 | task 2792622 | n_gen = 4188, tg = 29.22 t/s, tg_3s = 36.30 t/s
llama-server | 11038.06.470.581 I slot print_timing: id 0 | task 2792622 | n_gen = 4277, tg = 29.22 t/s, tg_3s = 28.88 t/s
llama-server | 11038.09.475.143 I slot print_timing: id 0 | task 2792622 | n_gen = 4364, tg = 29.21 t/s, tg_3s = 28.96 t/s
llama-server | 11038.12.556.013 I slot print_timing: id 0 | task 2792622 | n_gen = 4433, tg = 29.07 t/s, tg_3s = 22.40 t/s
llama-server | 11038.15.645.540 I slot print_timing: id 0 | task 2792622 | n_gen = 4529, tg = 29.11 t/s, tg_3s = 31.07 t/s
llama-server | 11038.18.646.422 I slot print_timing: id 0 | task 2792622 | n_gen = 4611, tg = 29.08 t/s, tg_3s = 27.33 t/s
llama-server | 11038.21.731.401 I slot print_timing: id 0 | task 2792622 | n_gen = 4691, tg = 29.02 t/s, tg_3s = 25.93 t/s
llama-server | 11038.24.820.760 I slot print_timing: id 0 | task 2792622 | n_gen = 4802, tg = 29.15 t/s, tg_3s = 35.93 t/s
llama-server | 11038.27.828.900 I slot print_timing: id 0 | task 2792622 | n_gen = 4883, tg = 29.11 t/s, tg_3s = 26.93 t/s
llama-server | 11038.30.915.206 I slot print_timing: id 0 | task 2792622 | n_gen = 4971, tg = 29.10 t/s, tg_3s = 28.51 t/s
llama-server | 11038.33.811.161 I slot print_timing: id 0 | task 2792622 | prompt eval time = 55864.25 ms / 51752 tokens ( 1.08 ms per token, 926.39 tokens per second)
llama-server | 11038.33.811.165 I slot print_timing: id 0 | task 2792622 | eval time = 173698.16 ms / 5068 tokens ( 34.28 ms per token, 29.17 tokens per second)
llama-server | 11038.33.811.165 I slot print_timing: id 0 | task 2792622 | total time = 229562.41 ms / 56820 tokens
llama-server | 11038.33.811.166 I slot print_timing: id 0 | task 2792622 | graphs reused = 2706277
llama-server | 11038.33.811.169 I slot print_timing: id 0 | task 2792622 | draft acceptance = 0.35712 ( 3248 accepted / 9095 generated), mean len = 2.79
llama-server | 11038.33.812.685 I slot release: id 0 | task 2792622 | stop processing: n_tokens = 56819, truncated = 0
llama-server | 11038.35.245.692 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 662097220501
llama-server | 11038.35.246.224 I slot launch_slot_: id 1 | task 2794470 | processing task, is_child = 0
llama-server | 11038.35.248.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2088.129 MiB)
llama-server | 11038.41.049.262 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.00 s / 1364.29 tokens per second
llama-server | 11038.42.864.240 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1277.59 tokens per second
llama-server | 11038.44.719.992 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.65 s / 1231.61 tokens per second
llama-server | 11038.46.607.251 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 10240, progress = 0.24, t = 8.53 s / 1199.77 tokens per second
llama-server | 11038.48.540.649 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.46 s / 1174.82 tokens per second
llama-server | 11038.50.502.776 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.41 s / 1155.12 tokens per second
llama-server | 11038.52.507.045 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.40 s / 1137.56 tokens per second
llama-server | 11038.54.546.394 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 18432, progress = 0.42, t = 16.44 s / 1121.48 tokens per second
llama-server | 11038.56.633.151 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.50 s / 1106.81 tokens per second
llama-server | 11038.58.752.556 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.62 s / 1092.59 tokens per second
llama-server | 11039.00.925.064 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 24576, progress = 0.56, t = 22.77 s / 1079.30 tokens per second
llama-server | 11039.03.119.196 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 26624, progress = 0.61, t = 24.97 s / 1066.36 tokens per second
llama-server | 11039.05.355.332 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.19 s / 1054.53 tokens per second
llama-server | 11039.07.620.862 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 30720, progress = 0.71, t = 29.45 s / 1043.03 tokens per second
llama-server | 11039.09.957.600 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 32768, progress = 0.75, t = 31.74 s / 1032.29 tokens per second
llama-server | 11039.12.292.022 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 34816, progress = 0.80, t = 34.10 s / 1020.87 tokens per second
llama-server | 11039.14.665.262 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 36864, progress = 0.85, t = 36.47 s / 1010.90 tokens per second
llama-server | 11039.17.072.826 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 38912, progress = 0.89, t = 38.87 s / 1001.14 tokens per second
llama-server | 11039.19.533.415 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 40960, progress = 0.94, t = 41.30 s / 991.75 tokens per second
llama-server | 11039.22.011.548 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 43008, progress = 0.99, t = 43.79 s / 982.20 tokens per second
llama-server | 11039.22.145.453 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 43043, progress = 0.99, t = 44.51 s / 966.99 tokens per second
llama-server | 11039.22.915.465 I slot print_timing: id 1 | task 2794470 | prompt processing, n_tokens = 43555, progress = 1.00, t = 44.79 s / 972.36 tokens per second
llama-server | 11039.26.237.626 I slot print_timing: id 1 | task 2794470 | n_gen = 115, tg = 37.00 t/s, tg_3s = 37.32 t/s
llama-server | 11039.29.313.463 I slot print_timing: id 1 | task 2794470 | n_gen = 231, tg = 37.36 t/s, tg_3s = 37.71 t/s
llama-server | 11039.32.373.054 I slot print_timing: id 1 | task 2794470 | n_gen = 340, tg = 36.78 t/s, tg_3s = 35.63 t/s
llama-server | 11039.34.081.567 I slot print_timing: id 1 | task 2794470 | prompt eval time = 45647.69 ms / 43559 tokens ( 1.05 ms per token, 954.24 tokens per second)
llama-server | 11039.34.081.570 I slot print_timing: id 1 | task 2794470 | eval time = 10924.76 ms / 393 tokens ( 27.87 ms per token, 35.88 tokens per second)
llama-server | 11039.34.081.571 I slot print_timing: id 1 | task 2794470 | total time = 56572.45 ms / 43952 tokens
llama-server | 11039.34.081.571 I slot print_timing: id 1 | task 2794470 | graphs reused = 2706396
llama-server | 11039.34.081.574 I slot print_timing: id 1 | task 2794470 | draft acceptance = 0.44793 ( 271 accepted / 605 generated), mean len = 3.24
llama-server | 11039.34.082.776 I slot release: id 1 | task 2794470 | stop processing: n_tokens = 43951, truncated = 0
llama-server | 11039.35.311.297 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 662329652737
llama-server | 11039.35.311.987 I slot launch_slot_: id 0 | task 2794616 | processing task, is_child = 0
llama-server | 11039.35.314.141 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2014.416 MiB)
llama-server | 11039.42.313.106 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.80 s / 1279.46 tokens per second
llama-server | 11039.44.168.668 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.64 s / 1233.53 tokens per second
llama-server | 11039.46.063.453 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.53 s / 1200.06 tokens per second
llama-server | 11039.47.984.815 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.45 s / 1176.37 tokens per second
llama-server | 11039.49.944.988 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.40 s / 1156.45 tokens per second
llama-server | 11039.51.946.682 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.39 s / 1138.95 tokens per second
llama-server | 11039.53.984.608 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 18432, progress = 0.42, t = 16.42 s / 1122.78 tokens per second
llama-server | 11039.56.063.413 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.48 s / 1108.01 tokens per second
llama-server | 11039.58.181.068 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.59 s / 1094.13 tokens per second
llama-server | 11040.00.352.744 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 24576, progress = 0.56, t = 22.74 s / 1080.73 tokens per second
llama-server | 11040.02.546.123 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 26624, progress = 0.61, t = 24.94 s / 1067.68 tokens per second
llama-server | 11040.04.777.539 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.16 s / 1055.78 tokens per second
llama-server | 11040.07.043.190 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 30720, progress = 0.70, t = 29.42 s / 1044.34 tokens per second
llama-server | 11040.09.382.527 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 32768, progress = 0.75, t = 31.71 s / 1033.49 tokens per second
llama-server | 11040.11.716.985 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 34816, progress = 0.80, t = 34.07 s / 1021.83 tokens per second
llama-server | 11040.14.090.848 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 36864, progress = 0.84, t = 36.43 s / 1011.81 tokens per second
llama-server | 11040.16.497.759 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 38912, progress = 0.89, t = 38.83 s / 1002.00 tokens per second
llama-server | 11040.18.956.889 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 40960, progress = 0.94, t = 41.27 s / 992.56 tokens per second
llama-server | 11040.21.435.676 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 43008, progress = 0.98, t = 43.75 s / 982.94 tokens per second
llama-server | 11040.21.679.214 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 43160, progress = 0.99, t = 44.48 s / 970.30 tokens per second
llama-server | 11040.22.422.226 I slot print_timing: id 0 | task 2794616 | prompt processing, n_tokens = 43672, progress = 1.00, t = 44.84 s / 973.88 tokens per second
llama-server | 11040.25.760.226 I slot print_timing: id 0 | task 2794616 | n_gen = 112, tg = 35.87 t/s, tg_3s = 36.19 t/s
llama-server | 11040.28.815.717 I slot print_timing: id 0 | task 2794616 | n_gen = 191, tg = 30.89 t/s, tg_3s = 25.86 t/s
llama-server | 11040.31.873.647 I slot print_timing: id 0 | task 2794616 | n_gen = 253, tg = 27.37 t/s, tg_3s = 20.28 t/s
llama-server | 11040.34.936.064 I slot print_timing: id 0 | task 2794616 | n_gen = 346, tg = 28.12 t/s, tg_3s = 30.37 t/s
llama-server | 11040.38.023.724 I slot print_timing: id 0 | task 2794616 | n_gen = 450, tg = 29.24 t/s, tg_3s = 33.68 t/s
llama-server | 11040.41.103.303 I slot print_timing: id 0 | task 2794616 | n_gen = 564, tg = 30.54 t/s, tg_3s = 37.02 t/s
llama-server | 11040.41.285.264 I slot print_timing: id 0 | task 2794616 | prompt eval time = 45698.94 ms / 43676 tokens ( 1.05 ms per token, 955.73 tokens per second)
llama-server | 11040.41.285.268 I slot print_timing: id 0 | task 2794616 | eval time = 18619.63 ms / 575 tokens ( 32.44 ms per token, 30.83 tokens per second)
llama-server | 11040.41.285.268 I slot print_timing: id 0 | task 2794616 | total time = 64318.58 ms / 44251 tokens
llama-server | 11040.41.285.269 I slot print_timing: id 0 | task 2794616 | graphs reused = 2706599
llama-server | 11040.41.285.272 I slot print_timing: id 0 | task 2794616 | draft acceptance = 0.35825 ( 369 accepted / 1030 generated), mean len = 2.79
llama-server | 11040.41.286.447 I slot release: id 0 | task 2794616 | stop processing: n_tokens = 44251, truncated = 0
llama-server | 11040.42.655.424 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 662389922828
llama-server | 11040.42.655.836 I slot launch_slot_: id 1 | task 2794847 | processing task, is_child = 0
llama-server | 11040.42.657.873 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2295.403 MiB)
llama-server | 11040.49.236.634 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.80 s / 1280.43 tokens per second
llama-server | 11040.51.090.126 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.64 s / 1233.31 tokens per second
llama-server | 11040.52.975.465 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.52 s / 1201.48 tokens per second
llama-server | 11040.54.898.273 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.44 s / 1177.56 tokens per second
llama-server | 11040.56.873.891 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.40 s / 1156.28 tokens per second
llama-server | 11040.58.876.938 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 16384, progress = 0.37, t = 14.39 s / 1138.41 tokens per second
llama-server | 11041.00.915.770 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 18432, progress = 0.42, t = 16.42 s / 1122.23 tokens per second
llama-server | 11041.02.994.187 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.49 s / 1107.48 tokens per second
llama-server | 11041.05.111.424 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.60 s / 1093.70 tokens per second
llama-server | 11041.07.284.038 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 24576, progress = 0.56, t = 22.75 s / 1080.30 tokens per second
llama-server | 11041.09.477.739 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 26624, progress = 0.61, t = 24.94 s / 1067.31 tokens per second
llama-server | 11041.11.713.612 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.17 s / 1055.45 tokens per second
llama-server | 11041.13.979.181 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 30720, progress = 0.70, t = 29.43 s / 1043.85 tokens per second
llama-server | 11041.16.314.877 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 32768, progress = 0.75, t = 31.72 s / 1033.07 tokens per second
llama-server | 11041.18.649.318 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 34816, progress = 0.80, t = 34.08 s / 1021.56 tokens per second
llama-server | 11041.21.022.148 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 36864, progress = 0.84, t = 36.44 s / 1011.56 tokens per second
llama-server | 11041.23.429.316 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 38912, progress = 0.89, t = 38.84 s / 1001.77 tokens per second
llama-server | 11041.25.887.702 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 40960, progress = 0.94, t = 41.27 s / 992.37 tokens per second
llama-server | 11041.28.366.099 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 43008, progress = 0.98, t = 43.76 s / 982.79 tokens per second
llama-server | 11041.28.703.774 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 43209, progress = 0.99, t = 44.49 s / 971.24 tokens per second
llama-server | 11041.29.440.152 I slot print_timing: id 1 | task 2794847 | prompt processing, n_tokens = 43721, progress = 1.00, t = 44.94 s / 972.93 tokens per second
llama-server | 11041.32.703.380 I slot print_timing: id 1 | task 2794847 | n_gen = 113, tg = 37.05 t/s, tg_3s = 37.37 t/s
llama-server | 11041.33.156.759 I slot print_timing: id 1 | task 2794847 | prompt eval time = 45790.19 ms / 43725 tokens ( 1.05 ms per token, 954.90 tokens per second)
llama-server | 11041.33.156.762 I slot print_timing: id 1 | task 2794847 | eval time = 3476.65 ms / 138 tokens ( 25.38 ms per token, 39.41 tokens per second)
llama-server | 11041.33.156.762 I slot print_timing: id 1 | task 2794847 | total time = 49266.84 ms / 43863 tokens
llama-server | 11041.33.156.763 I slot print_timing: id 1 | task 2794847 | graphs reused = 2706635
llama-server | 11041.33.156.766 I slot print_timing: id 1 | task 2794847 | draft acceptance = 0.52105 ( 99 accepted / 190 generated), mean len = 3.61
llama-server | 11041.33.157.938 I slot release: id 1 | task 2794847 | stop processing: n_tokens = 43862, truncated = 0
llama-server | 11041.34.347.797 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 662457126499
llama-server | 11041.34.348.569 I slot launch_slot_: id 0 | task 2794910 | processing task, is_child = 0
llama-server | 11041.34.350.527 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2458.189 MiB)
llama-server | 11041.41.202.059 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.80 s / 1279.58 tokens per second
llama-server | 11041.43.059.127 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.64 s / 1233.75 tokens per second
llama-server | 11041.44.941.836 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.52 s / 1201.31 tokens per second
llama-server | 11041.46.860.839 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.43 s / 1177.65 tokens per second
llama-server | 11041.48.828.782 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.39 s / 1157.18 tokens per second
llama-server | 11041.50.828.797 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 16384, progress = 0.38, t = 14.38 s / 1139.46 tokens per second
llama-server | 11041.52.865.227 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 18432, progress = 0.42, t = 16.41 s / 1123.38 tokens per second
llama-server | 11041.54.943.356 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.47 s / 1108.57 tokens per second
llama-server | 11041.57.059.475 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 22528, progress = 0.52, t = 20.58 s / 1094.66 tokens per second
llama-server | 11041.59.228.732 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 24576, progress = 0.56, t = 22.73 s / 1081.30 tokens per second
llama-server | 11042.01.421.835 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 26624, progress = 0.61, t = 24.92 s / 1068.25 tokens per second
llama-server | 11042.03.652.909 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 28672, progress = 0.66, t = 27.14 s / 1056.29 tokens per second
llama-server | 11042.05.917.518 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 30720, progress = 0.70, t = 29.40 s / 1044.87 tokens per second
llama-server | 11042.08.253.042 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 32768, progress = 0.75, t = 31.69 s / 1033.97 tokens per second
llama-server | 11042.10.589.822 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 34816, progress = 0.80, t = 34.05 s / 1022.35 tokens per second
llama-server | 11042.12.964.232 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 36864, progress = 0.85, t = 36.42 s / 1012.24 tokens per second
llama-server | 11042.15.372.305 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 38912, progress = 0.89, t = 38.82 s / 1002.38 tokens per second
llama-server | 11042.17.830.112 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 40960, progress = 0.94, t = 41.25 s / 992.92 tokens per second
llama-server | 11042.20.308.133 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 43008, progress = 0.99, t = 43.74 s / 983.31 tokens per second
llama-server | 11042.20.504.429 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 43099, progress = 0.99, t = 44.46 s / 969.31 tokens per second
llama-server | 11042.21.302.977 I slot print_timing: id 0 | task 2794910 | prompt processing, n_tokens = 43611, progress = 1.00, t = 44.83 s / 972.75 tokens per second
llama-server | 11042.23.720.560 I slot print_timing: id 0 | task 2794910 | prompt eval time = 45682.56 ms / 43615 tokens ( 1.05 ms per token, 954.74 tokens per second)
llama-server | 11042.23.720.563 I slot print_timing: id 0 | task 2794910 | eval time = 2182.56 ms / 101 tokens ( 21.83 ms per token, 45.82 tokens per second)
llama-server | 11042.23.720.564 I slot print_timing: id 0 | task 2794910 | total time = 47865.12 ms / 43716 tokens
llama-server | 11042.23.720.564 I slot print_timing: id 0 | task 2794910 | graphs reused = 2706658
llama-server | 11042.23.720.575 I slot print_timing: id 0 | task 2794910 | draft acceptance = 0.63333 ( 76 accepted / 120 generated), mean len = 4.17
llama-server | 11042.23.721.880 I slot release: id 0 | task 2794910 | stop processing: n_tokens = 43715, truncated = 0
llama-server | 11042.24.958.196 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 662508997991
llama-server | 11042.24.958.774 I slot launch_slot_: id 1 | task 2794959 | processing task, is_child = 0
llama-server | 11042.31.808.416 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.80 s / 1280.92 tokens per second
llama-server | 11042.33.655.227 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 8192, progress = 0.19, t = 6.63 s / 1234.92 tokens per second
llama-server | 11042.35.534.039 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.51 s / 1203.94 tokens per second
llama-server | 11042.37.462.680 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 12288, progress = 0.28, t = 10.43 s / 1178.64 tokens per second
llama-server | 11042.39.423.619 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 14336, progress = 0.33, t = 12.37 s / 1158.83 tokens per second
llama-server | 11042.41.422.270 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 16384, progress = 0.37, t = 14.36 s / 1140.82 tokens per second
llama-server | 11042.43.456.801 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 18432, progress = 0.42, t = 16.39 s / 1124.66 tokens per second
llama-server | 11042.45.537.860 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 20480, progress = 0.47, t = 18.45 s / 1109.84 tokens per second
llama-server | 11042.47.653.161 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 22528, progress = 0.51, t = 20.56 s / 1095.55 tokens per second
llama-server | 11042.49.819.452 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 24576, progress = 0.56, t = 22.71 s / 1082.21 tokens per second
llama-server | 11042.52.009.667 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 26624, progress = 0.61, t = 24.90 s / 1069.20 tokens per second
llama-server | 11042.54.237.761 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 28672, progress = 0.65, t = 27.12 s / 1057.25 tokens per second
llama-server | 11042.56.501.392 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 30720, progress = 0.70, t = 29.37 s / 1045.82 tokens per second
llama-server | 11042.58.837.477 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 32768, progress = 0.75, t = 31.66 s / 1034.92 tokens per second
llama-server | 11043.01.169.703 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 34816, progress = 0.79, t = 34.03 s / 1023.24 tokens per second
llama-server | 11043.03.540.434 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 36864, progress = 0.84, t = 36.38 s / 1013.17 tokens per second
llama-server | 11043.05.944.942 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 38912, progress = 0.89, t = 38.78 s / 1003.35 tokens per second
llama-server | 11043.08.402.225 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 40960, progress = 0.93, t = 41.21 s / 993.85 tokens per second
llama-server | 11043.10.880.767 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 43008, progress = 0.98, t = 43.70 s / 984.19 tokens per second
llama-server | 11043.11.400.118 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 43370, progress = 0.99, t = 44.43 s / 976.17 tokens per second
llama-server | 11043.12.170.012 I slot print_timing: id 1 | task 2794959 | prompt processing, n_tokens = 43882, progress = 1.00, t = 45.09 s / 973.27 tokens per second
llama-server | 11043.15.501.714 I slot print_timing: id 1 | task 2794959 | n_gen = 143, tg = 45.92 t/s, tg_3s = 46.24 t/s
llama-server | 11043.18.591.903 I slot print_timing: id 1 | task 2794959 | n_gen = 244, tg = 39.31 t/s, tg_3s = 32.68 t/s
llama-server | 11043.21.664.833 I slot print_timing: id 1 | task 2794959 | n_gen = 343, tg = 36.95 t/s, tg_3s = 32.22 t/s
llama-server | 11043.24.664.926 I slot print_timing: id 1 | task 2794959 | n_gen = 449, tg = 36.56 t/s, tg_3s = 35.33 t/s
llama-server | 11043.27.745.862 I slot print_timing: id 1 | task 2794959 | n_gen = 552, tg = 35.93 t/s, tg_3s = 33.43 t/s
llama-server | 11043.30.816.139 I slot print_timing: id 1 | task 2794959 | n_gen = 645, tg = 34.99 t/s, tg_3s = 30.29 t/s
llama-server | 11043.33.904.365 I slot print_timing: id 1 | task 2794959 | n_gen = 733, tg = 34.05 t/s, tg_3s = 28.50 t/s
llama-server | 11043.36.978.719 I slot print_timing: id 1 | task 2794959 | n_gen = 822, tg = 33.42 t/s, tg_3s = 28.95 t/s
llama-server | 11043.40.062.045 I slot print_timing: id 1 | task 2794959 | n_gen = 909, tg = 32.84 t/s, tg_3s = 28.22 t/s
llama-server | 11043.43.068.724 I slot print_timing: id 1 | task 2794959 | n_gen = 1004, tg = 32.71 t/s, tg_3s = 31.60 t/s
llama-server | 11043.46.159.917 I slot print_timing: id 1 | task 2794959 | n_gen = 1117, tg = 33.07 t/s, tg_3s = 36.56 t/s
llama-server | 11043.49.179.997 I slot print_timing: id 1 | task 2794959 | n_gen = 1232, tg = 33.48 t/s, tg_3s = 38.08 t/s
llama-server | 11043.52.271.276 I slot print_timing: id 1 | task 2794959 | n_gen = 1340, tg = 33.59 t/s, tg_3s = 34.94 t/s
llama-server | 11043.55.363.106 I slot print_timing: id 1 | task 2794959 | n_gen = 1427, tg = 33.20 t/s, tg_3s = 28.14 t/s
llama-server | 11043.58.376.906 I slot print_timing: id 1 | task 2794959 | n_gen = 1500, tg = 32.61 t/s, tg_3s = 24.22 t/s
llama-server | 11044.01.382.337 I slot print_timing: id 1 | task 2794959 | n_gen = 1597, tg = 32.59 t/s, tg_3s = 32.27 t/s
llama-server | 11044.04.469.130 I slot print_timing: id 1 | task 2794959 | n_gen = 1678, tg = 32.21 t/s, tg_3s = 26.24 t/s
llama-server | 11044.07.490.650 I slot print_timing: id 1 | task 2794959 | n_gen = 1764, tg = 32.01 t/s, tg_3s = 28.46 t/s
llama-server | 11044.10.498.269 I slot print_timing: id 1 | task 2794959 | n_gen = 1840, tg = 31.66 t/s, tg_3s = 25.27 t/s
llama-server | 11044.13.508.326 I slot print_timing: id 1 | task 2794959 | n_gen = 1930, tg = 31.57 t/s, tg_3s = 29.90 t/s
llama-server | 11044.16.535.105 I slot print_timing: id 1 | task 2794959 | n_gen = 2018, tg = 31.45 t/s, tg_3s = 29.07 t/s
llama-server | 11044.19.546.739 I slot print_timing: id 1 | task 2794959 | n_gen = 2085, tg = 31.04 t/s, tg_3s = 22.25 t/s
llama-server | 11044.22.560.245 I slot print_timing: id 1 | task 2794959 | n_gen = 2167, tg = 30.88 t/s, tg_3s = 27.21 t/s
llama-server | 11044.25.591.514 I slot print_timing: id 1 | task 2794959 | n_gen = 2252, tg = 30.76 t/s, tg_3s = 28.04 t/s
llama-server | 11044.28.612.409 I slot print_timing: id 1 | task 2794959 | n_gen = 2343, tg = 30.73 t/s, tg_3s = 30.12 t/s
llama-server | 11044.31.629.833 I slot print_timing: id 1 | task 2794959 | n_gen = 2432, tg = 30.69 t/s, tg_3s = 29.50 t/s
llama-server | 11044.34.666.277 I slot print_timing: id 1 | task 2794959 | n_gen = 2510, tg = 30.50 t/s, tg_3s = 25.69 t/s
llama-server | 11044.37.692.185 I slot print_timing: id 1 | task 2794959 | n_gen = 2611, tg = 30.60 t/s, tg_3s = 33.38 t/s
llama-server | 11044.40.716.236 I slot print_timing: id 1 | task 2794959 | n_gen = 2690, tg = 30.45 t/s, tg_3s = 26.12 t/s
llama-server | 11044.43.755.583 I slot print_timing: id 1 | task 2794959 | n_gen = 2766, tg = 30.27 t/s, tg_3s = 25.01 t/s
llama-server | 11044.46.778.127 I slot print_timing: id 1 | task 2794959 | n_gen = 2848, tg = 30.17 t/s, tg_3s = 27.13 t/s
llama-server | 11044.49.808.695 I slot print_timing: id 1 | task 2794959 | n_gen = 2967, tg = 30.45 t/s, tg_3s = 39.27 t/s
llama-server | 11044.52.854.236 I slot print_timing: id 1 | task 2794959 | n_gen = 3051, tg = 30.36 t/s, tg_3s = 27.58 t/s
llama-server | 11044.55.882.440 I slot print_timing: id 1 | task 2794959 | n_gen = 3123, tg = 30.17 t/s, tg_3s = 23.78 t/s
llama-server | 11044.58.918.794 I slot print_timing: id 1 | task 2794959 | n_gen = 3214, tg = 30.17 t/s, tg_3s = 29.97 t/s
llama-server | 11045.01.974.389 I slot print_timing: id 1 | task 2794959 | n_gen = 3313, tg = 30.23 t/s, tg_3s = 32.40 t/s
llama-server | 11045.05.008.215 I slot print_timing: id 1 | task 2794959 | n_gen = 3416, tg = 30.33 t/s, tg_3s = 33.95 t/s
llama-server | 11045.08.056.441 I slot print_timing: id 1 | task 2794959 | n_gen = 3499, tg = 30.25 t/s, tg_3s = 27.23 t/s
llama-server | 11045.11.102.503 I slot print_timing: id 1 | task 2794959 | n_gen = 3602, tg = 30.34 t/s, tg_3s = 33.81 t/s
llama-server | 11045.14.148.728 I slot print_timing: id 1 | task 2794959 | n_gen = 3705, tg = 30.43 t/s, tg_3s = 33.81 t/s
llama-server | 11045.17.209.017 I slot print_timing: id 1 | task 2794959 | n_gen = 3795, tg = 30.40 t/s, tg_3s = 29.41 t/s
llama-server | 11045.20.261.932 I slot print_timing: id 1 | task 2794959 | n_gen = 3899, tg = 30.49 t/s, tg_3s = 34.07 t/s
llama-server | 11045.23.324.605 I slot print_timing: id 1 | task 2794959 | n_gen = 3992, tg = 30.49 t/s, tg_3s = 30.37 t/s
llama-server | 11045.26.372.214 I slot print_timing: id 1 | task 2794959 | n_gen = 4067, tg = 30.35 t/s, tg_3s = 24.61 t/s
llama-server | 11045.29.419.724 I slot print_timing: id 1 | task 2794959 | n_gen = 4158, tg = 30.34 t/s, tg_3s = 29.86 t/s
llama-server | 11045.32.467.945 I slot print_timing: id 1 | task 2794959 | n_gen = 4234, tg = 30.22 t/s, tg_3s = 24.93 t/s
llama-server | 11045.35.534.874 I slot print_timing: id 1 | task 2794959 | n_gen = 4339, tg = 30.31 t/s, tg_3s = 34.24 t/s
llama-server | 11045.38.589.335 I slot print_timing: id 1 | task 2794959 | n_gen = 4448, tg = 30.42 t/s, tg_3s = 35.69 t/s
llama-server | 11045.41.656.437 I slot print_timing: id 1 | task 2794959 | n_gen = 4539, tg = 30.41 t/s, tg_3s = 29.67 t/s
llama-server | 11045.44.711.633 I slot print_timing: id 1 | task 2794959 | n_gen = 4627, tg = 30.37 t/s, tg_3s = 28.80 t/s
llama-server | 11045.47.767.409 I slot print_timing: id 1 | task 2794959 | n_gen = 4727, tg = 30.42 t/s, tg_3s = 32.72 t/s
llama-server | 11045.50.839.102 I slot print_timing: id 1 | task 2794959 | n_gen = 4820, tg = 30.42 t/s, tg_3s = 30.28 t/s
llama-server | 11045.53.903.259 I slot print_timing: id 1 | task 2794959 | n_gen = 4932, tg = 30.53 t/s, tg_3s = 36.55 t/s
llama-server | 11045.56.980.709 I slot print_timing: id 1 | task 2794959 | n_gen = 5009, tg = 30.43 t/s, tg_3s = 25.02 t/s
llama-server | 11046.00.052.653 I slot print_timing: id 1 | task 2794959 | n_gen = 5108, tg = 30.46 t/s, tg_3s = 32.23 t/s
llama-server | 11046.03.120.337 I slot print_timing: id 1 | task 2794959 | n_gen = 5220, tg = 30.57 t/s, tg_3s = 36.51 t/s
llama-server | 11046.06.209.501 I slot print_timing: id 1 | task 2794959 | n_gen = 5313, tg = 30.56 t/s, tg_3s = 30.11 t/s
llama-server | 11046.09.283.807 I slot print_timing: id 1 | task 2794959 | n_gen = 5407, tg = 30.56 t/s, tg_3s = 30.58 t/s
llama-server | 11046.12.353.461 I slot print_timing: id 1 | task 2794959 | n_gen = 5476, tg = 30.43 t/s, tg_3s = 22.48 t/s
llama-server | 11046.15.441.435 I slot print_timing: id 1 | task 2794959 | n_gen = 5562, tg = 30.38 t/s, tg_3s = 27.85 t/s
llama-server | 11046.18.515.036 I slot print_timing: id 1 | task 2794959 | n_gen = 5641, tg = 30.31 t/s, tg_3s = 25.70 t/s
llama-server | 11046.21.588.468 I slot print_timing: id 1 | task 2794959 | n_gen = 5727, tg = 30.27 t/s, tg_3s = 27.98 t/s
llama-server | 11046.24.592.128 I slot print_timing: id 1 | task 2794959 | n_gen = 5817, tg = 30.26 t/s, tg_3s = 29.96 t/s
llama-server | 11046.27.674.446 I slot print_timing: id 1 | task 2794959 | n_gen = 5913, tg = 30.28 t/s, tg_3s = 31.15 t/s
llama-server | 11046.30.683.395 I slot print_timing: id 1 | task 2794959 | n_gen = 6044, tg = 30.48 t/s, tg_3s = 43.54 t/s
llama-server | 11046.31.809.813 I slot print_timing: id 1 | task 2794959 | prompt eval time = 45942.60 ms / 43886 tokens ( 1.05 ms per token, 955.24 tokens per second)
llama-server | 11046.31.809.816 I slot print_timing: id 1 | task 2794959 | eval time = 199400.33 ms / 6100 tokens ( 32.69 ms per token, 30.59 tokens per second)
llama-server | 11046.31.809.817 I slot print_timing: id 1 | task 2794959 | total time = 245342.93 ms / 49986 tokens
llama-server | 11046.31.809.818 I slot print_timing: id 1 | task 2794959 | graphs reused = 2708800
llama-server | 11046.31.809.821 I slot print_timing: id 1 | task 2794959 | draft acceptance = 0.36299 ( 3933 accepted / 10835 generated), mean len = 2.81
llama-server | 11046.31.811.023 I slot release: id 1 | task 2794959 | stop processing: n_tokens = 49986, truncated = 0
llama-server | 11046.33.254.172 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 662559561932
llama-server | 11046.33.254.672 I slot launch_slot_: id 0 | task 2797151 | processing task, is_child = 0
llama-server | 11046.33.257.014 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2030.342 MiB)
llama-server | 11046.33.403.158 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2040.317 MiB)
llama-server | 11046.38.259.873 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.00 s / 1364.52 tokens per second
llama-server | 11046.40.077.166 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1277.27 tokens per second
llama-server | 11046.41.935.446 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.65 s / 1231.19 tokens per second
llama-server | 11046.43.823.166 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.54 s / 1199.24 tokens per second
llama-server | 11046.45.764.392 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.47 s / 1173.18 tokens per second
llama-server | 11046.47.728.130 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.42 s / 1153.81 tokens per second
llama-server | 11046.49.733.158 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 16384, progress = 0.37, t = 14.42 s / 1136.38 tokens per second
llama-server | 11046.51.774.734 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 18432, progress = 0.41, t = 16.45 s / 1120.38 tokens per second
llama-server | 11046.53.853.692 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 20480, progress = 0.46, t = 18.52 s / 1105.82 tokens per second
llama-server | 11046.55.974.040 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 22528, progress = 0.50, t = 20.63 s / 1092.05 tokens per second
llama-server | 11046.58.145.992 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 24576, progress = 0.55, t = 22.78 s / 1078.81 tokens per second
llama-server | 11047.00.342.657 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 26624, progress = 0.60, t = 24.98 s / 1065.87 tokens per second
llama-server | 11047.02.574.978 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 28672, progress = 0.64, t = 27.20 s / 1054.08 tokens per second
llama-server | 11047.04.841.815 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 30720, progress = 0.69, t = 29.46 s / 1042.77 tokens per second
llama-server | 11047.07.180.991 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 32768, progress = 0.73, t = 31.75 s / 1031.93 tokens per second
llama-server | 11047.09.517.393 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 34816, progress = 0.78, t = 34.12 s / 1020.47 tokens per second
llama-server | 11047.11.892.605 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 36864, progress = 0.82, t = 36.48 s / 1010.47 tokens per second
llama-server | 11047.14.301.585 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 38912, progress = 0.87, t = 38.88 s / 1000.71 tokens per second
llama-server | 11047.16.761.273 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 40960, progress = 0.92, t = 41.32 s / 991.36 tokens per second
llama-server | 11047.19.239.426 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 43008, progress = 0.96, t = 43.80 s / 981.83 tokens per second
llama-server | 11047.20.722.618 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 44171, progress = 0.99, t = 45.71 s / 966.25 tokens per second
llama-server | 11047.21.473.708 I slot print_timing: id 0 | task 2797151 | prompt processing, n_tokens = 44683, progress = 1.00, t = 46.14 s / 968.49 tokens per second
llama-server | 11047.24.855.930 I slot print_timing: id 0 | task 2797151 | n_gen = 100, tg = 31.05 t/s, tg_3s = 31.36 t/s
llama-server | 11047.27.862.264 I slot print_timing: id 0 | task 2797151 | n_gen = 203, tg = 32.61 t/s, tg_3s = 34.26 t/s
llama-server | 11047.30.946.619 I slot print_timing: id 0 | task 2797151 | n_gen = 292, tg = 31.36 t/s, tg_3s = 28.86 t/s
llama-server | 11047.33.958.553 I slot print_timing: id 0 | task 2797151 | n_gen = 409, tg = 33.20 t/s, tg_3s = 38.85 t/s
llama-server | 11047.36.959.244 I slot print_timing: id 0 | task 2797151 | n_gen = 508, tg = 33.16 t/s, tg_3s = 32.99 t/s
llama-server | 11047.40.049.014 I slot print_timing: id 0 | task 2797151 | n_gen = 609, tg = 33.08 t/s, tg_3s = 32.69 t/s
llama-server | 11047.43.064.101 I slot print_timing: id 0 | task 2797151 | n_gen = 688, tg = 32.11 t/s, tg_3s = 26.20 t/s
llama-server | 11047.46.064.165 I slot print_timing: id 0 | task 2797151 | n_gen = 765, tg = 31.32 t/s, tg_3s = 25.67 t/s
llama-server | 11047.49.069.180 I slot print_timing: id 0 | task 2797151 | n_gen = 859, tg = 31.31 t/s, tg_3s = 31.28 t/s
llama-server | 11047.52.087.490 I slot print_timing: id 0 | task 2797151 | n_gen = 940, tg = 30.87 t/s, tg_3s = 26.84 t/s
llama-server | 11047.55.093.359 I slot print_timing: id 0 | task 2797151 | n_gen = 1024, tg = 30.61 t/s, tg_3s = 27.95 t/s
llama-server | 11047.58.099.803 I slot print_timing: id 0 | task 2797151 | n_gen = 1113, tg = 30.52 t/s, tg_3s = 29.60 t/s
llama-server | 11048.01.125.659 I slot print_timing: id 0 | task 2797151 | n_gen = 1195, tg = 30.26 t/s, tg_3s = 27.10 t/s
llama-server | 11048.04.139.995 I slot print_timing: id 0 | task 2797151 | n_gen = 1301, tg = 30.61 t/s, tg_3s = 35.17 t/s
llama-server | 11048.07.151.210 I slot print_timing: id 0 | task 2797151 | n_gen = 1373, tg = 30.16 t/s, tg_3s = 23.91 t/s
llama-server | 11048.10.191.567 I slot print_timing: id 0 | task 2797151 | n_gen = 1496, tg = 30.81 t/s, tg_3s = 40.46 t/s
llama-server | 11048.13.216.719 I slot print_timing: id 0 | task 2797151 | n_gen = 1594, tg = 30.90 t/s, tg_3s = 32.40 t/s
llama-server | 11048.16.254.465 I slot print_timing: id 0 | task 2797151 | n_gen = 1687, tg = 30.89 t/s, tg_3s = 30.61 t/s
llama-server | 11048.19.291.198 I slot print_timing: id 0 | task 2797151 | n_gen = 1794, tg = 31.12 t/s, tg_3s = 35.24 t/s
llama-server | 11048.22.313.858 I slot print_timing: id 0 | task 2797151 | n_gen = 1887, tg = 31.10 t/s, tg_3s = 30.77 t/s
llama-server | 11048.25.354.232 I slot print_timing: id 0 | task 2797151 | n_gen = 1975, tg = 31.00 t/s, tg_3s = 28.94 t/s
llama-server | 11048.28.382.383 I slot print_timing: id 0 | task 2797151 | n_gen = 2065, tg = 30.94 t/s, tg_3s = 29.72 t/s
llama-server | 11048.31.418.019 I slot print_timing: id 0 | task 2797151 | n_gen = 2157, tg = 30.91 t/s, tg_3s = 30.31 t/s
llama-server | 11048.34.465.246 I slot print_timing: id 0 | task 2797151 | n_gen = 2228, tg = 30.59 t/s, tg_3s = 23.30 t/s
llama-server | 11048.37.500.524 I slot print_timing: id 0 | task 2797151 | n_gen = 2307, tg = 30.41 t/s, tg_3s = 26.03 t/s
llama-server | 11048.40.539.061 I slot print_timing: id 0 | task 2797151 | n_gen = 2380, tg = 30.16 t/s, tg_3s = 24.02 t/s
llama-server | 11048.43.595.149 I slot print_timing: id 0 | task 2797151 | n_gen = 2468, tg = 30.11 t/s, tg_3s = 28.79 t/s
llama-server | 11048.44.702.591 I slot print_timing: id 0 | task 2797151 | prompt eval time = 46947.34 ms / 44687 tokens ( 1.05 ms per token, 951.85 tokens per second)
llama-server | 11048.44.702.597 I slot print_timing: id 0 | task 2797151 | eval time = 83034.88 ms / 2507 tokens ( 33.13 ms per token, 30.18 tokens per second)
llama-server | 11048.44.702.598 I slot print_timing: id 0 | task 2797151 | total time = 129982.22 ms / 47194 tokens
llama-server | 11048.44.702.599 I slot print_timing: id 0 | task 2797151 | graphs reused = 2709696
llama-server | 11048.44.702.603 I slot print_timing: id 0 | task 2797151 | draft acceptance = 0.35259 ( 1599 accepted / 4535 generated), mean len = 2.76
llama-server | 11048.44.704.078 I slot release: id 0 | task 2797151 | stop processing: n_tokens = 47193, truncated = 0
llama-server | 11048.46.090.305 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 662807651076
llama-server | 11048.46.090.885 I slot launch_slot_: id 1 | task 2798083 | processing task, is_child = 0
llama-server | 11048.46.093.151 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2027.383 MiB)
llama-server | 11048.51.304.042 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.84 tokens per second
llama-server | 11048.53.121.289 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1276.80 tokens per second
llama-server | 11048.54.980.762 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.66 s / 1230.73 tokens per second
llama-server | 11048.56.868.641 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.54 s / 1198.76 tokens per second
llama-server | 11048.58.806.820 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.47 s / 1173.36 tokens per second
llama-server | 11049.00.771.295 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.43 s / 1153.72 tokens per second
llama-server | 11049.02.774.488 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.42 s / 1136.44 tokens per second
llama-server | 11049.04.814.569 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 18432, progress = 0.41, t = 16.45 s / 1120.42 tokens per second
llama-server | 11049.06.894.609 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.52 s / 1105.88 tokens per second
llama-server | 11049.09.014.304 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 22528, progress = 0.50, t = 20.63 s / 1092.13 tokens per second
llama-server | 11049.11.187.490 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.78 s / 1078.86 tokens per second
llama-server | 11049.13.383.977 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 26624, progress = 0.59, t = 24.98 s / 1065.90 tokens per second
llama-server | 11049.15.616.738 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 28672, progress = 0.63, t = 27.20 s / 1054.09 tokens per second
llama-server | 11049.17.884.587 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 30720, progress = 0.68, t = 29.46 s / 1042.79 tokens per second
llama-server | 11049.20.222.143 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 32768, progress = 0.72, t = 31.75 s / 1031.93 tokens per second
llama-server | 11049.22.559.671 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 34816, progress = 0.77, t = 34.12 s / 1020.47 tokens per second
llama-server | 11049.24.935.066 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 36864, progress = 0.81, t = 36.48 s / 1010.46 tokens per second
llama-server | 11049.27.344.014 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 38912, progress = 0.86, t = 38.88 s / 1000.74 tokens per second
llama-server | 11049.29.805.921 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 40960, progress = 0.90, t = 41.32 s / 991.31 tokens per second
llama-server | 11049.32.286.241 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 43008, progress = 0.95, t = 43.81 s / 981.73 tokens per second
llama-server | 11049.34.690.728 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 44926, progress = 0.99, t = 46.31 s / 970.07 tokens per second
llama-server | 11049.35.441.737 I slot print_timing: id 1 | task 2798083 | prompt processing, n_tokens = 45438, progress = 1.00, t = 47.05 s / 965.65 tokens per second
llama-server | 11049.39.738.428 I slot print_timing: id 1 | task 2798083 | n_gen = 103, tg = 24.87 t/s, tg_3s = 25.11 t/s
llama-server | 11049.42.757.144 I slot print_timing: id 1 | task 2798083 | n_gen = 195, tg = 27.24 t/s, tg_3s = 30.48 t/s
llama-server | 11049.45.757.444 I slot print_timing: id 1 | task 2798083 | n_gen = 273, tg = 26.87 t/s, tg_3s = 26.00 t/s
llama-server | 11049.48.848.365 I slot print_timing: id 1 | task 2798083 | n_gen = 375, tg = 28.31 t/s, tg_3s = 33.00 t/s
llama-server | 11049.51.868.961 I slot print_timing: id 1 | task 2798083 | n_gen = 448, tg = 27.54 t/s, tg_3s = 24.17 t/s
llama-server | 11049.54.878.391 I slot print_timing: id 1 | task 2798083 | n_gen = 550, tg = 28.53 t/s, tg_3s = 33.89 t/s
llama-server | 11049.57.883.064 I slot print_timing: id 1 | task 2798083 | n_gen = 627, tg = 28.14 t/s, tg_3s = 25.63 t/s
llama-server | 11050.00.916.643 I slot print_timing: id 1 | task 2798083 | n_gen = 724, tg = 28.60 t/s, tg_3s = 31.98 t/s
llama-server | 11050.03.937.858 I slot print_timing: id 1 | task 2798083 | n_gen = 814, tg = 28.73 t/s, tg_3s = 29.79 t/s
llama-server | 11050.06.973.189 I slot print_timing: id 1 | task 2798083 | n_gen = 920, tg = 29.33 t/s, tg_3s = 34.92 t/s
llama-server | 11050.09.992.423 I slot print_timing: id 1 | task 2798083 | n_gen = 1012, tg = 29.43 t/s, tg_3s = 30.47 t/s
llama-server | 11050.13.010.211 I slot print_timing: id 1 | task 2798083 | n_gen = 1092, tg = 29.19 t/s, tg_3s = 26.51 t/s
llama-server | 11050.16.055.340 I slot print_timing: id 1 | task 2798083 | n_gen = 1188, tg = 29.37 t/s, tg_3s = 31.53 t/s
llama-server | 11050.19.084.585 I slot print_timing: id 1 | task 2798083 | n_gen = 1287, tg = 29.60 t/s, tg_3s = 32.68 t/s
llama-server | 11050.22.114.140 I slot print_timing: id 1 | task 2798083 | n_gen = 1392, tg = 29.93 t/s, tg_3s = 34.66 t/s
llama-server | 11050.25.161.527 I slot print_timing: id 1 | task 2798083 | n_gen = 1476, tg = 29.78 t/s, tg_3s = 27.56 t/s
llama-server | 11050.28.195.002 I slot print_timing: id 1 | task 2798083 | n_gen = 1558, tg = 29.62 t/s, tg_3s = 27.03 t/s
llama-server | 11050.31.230.299 I slot print_timing: id 1 | task 2798083 | n_gen = 1641, tg = 29.50 t/s, tg_3s = 27.34 t/s
llama-server | 11050.34.291.388 I slot print_timing: id 1 | task 2798083 | n_gen = 1742, tg = 29.68 t/s, tg_3s = 32.99 t/s
llama-server | 11050.37.337.988 I slot print_timing: id 1 | task 2798083 | n_gen = 1846, tg = 29.90 t/s, tg_3s = 34.14 t/s
llama-server | 11050.40.404.213 I slot print_timing: id 1 | task 2798083 | n_gen = 1938, tg = 29.91 t/s, tg_3s = 30.00 t/s
llama-server | 11050.43.455.867 I slot print_timing: id 1 | task 2798083 | n_gen = 2020, tg = 29.77 t/s, tg_3s = 26.87 t/s
llama-server | 11050.46.503.524 I slot print_timing: id 1 | task 2798083 | n_gen = 2119, tg = 29.89 t/s, tg_3s = 32.48 t/s
llama-server | 11050.49.567.465 I slot print_timing: id 1 | task 2798083 | n_gen = 2195, tg = 29.68 t/s, tg_3s = 24.80 t/s
llama-server | 11050.52.617.682 I slot print_timing: id 1 | task 2798083 | n_gen = 2292, tg = 29.76 t/s, tg_3s = 31.80 t/s
llama-server | 11050.55.667.246 I slot print_timing: id 1 | task 2798083 | n_gen = 2392, tg = 29.88 t/s, tg_3s = 32.79 t/s
llama-server | 11050.58.732.544 I slot print_timing: id 1 | task 2798083 | n_gen = 2476, tg = 29.78 t/s, tg_3s = 27.40 t/s
llama-server | 11051.01.792.256 I slot print_timing: id 1 | task 2798083 | n_gen = 2592, tg = 30.07 t/s, tg_3s = 37.91 t/s
llama-server | 11051.04.843.708 I slot print_timing: id 1 | task 2798083 | n_gen = 2683, tg = 30.06 t/s, tg_3s = 29.82 t/s
llama-server | 11051.07.911.956 I slot print_timing: id 1 | task 2798083 | n_gen = 2768, tg = 29.99 t/s, tg_3s = 27.70 t/s
llama-server | 11051.10.970.339 I slot print_timing: id 1 | task 2798083 | n_gen = 2890, tg = 30.30 t/s, tg_3s = 39.89 t/s
llama-server | 11051.14.039.582 I slot print_timing: id 1 | task 2798083 | n_gen = 2976, tg = 30.23 t/s, tg_3s = 28.02 t/s
llama-server | 11051.17.097.738 I slot print_timing: id 1 | task 2798083 | n_gen = 3058, tg = 30.13 t/s, tg_3s = 26.81 t/s
llama-server | 11051.20.152.846 I slot print_timing: id 1 | task 2798083 | n_gen = 3137, tg = 30.00 t/s, tg_3s = 25.86 t/s
llama-server | 11051.23.221.398 I slot print_timing: id 1 | task 2798083 | n_gen = 3222, tg = 29.94 t/s, tg_3s = 27.70 t/s
llama-server | 11051.26.280.247 I slot print_timing: id 1 | task 2798083 | n_gen = 3311, tg = 29.92 t/s, tg_3s = 29.10 t/s
llama-server | 11051.29.342.940 I slot print_timing: id 1 | task 2798083 | n_gen = 3403, tg = 29.92 t/s, tg_3s = 30.04 t/s
llama-server | 11051.32.422.265 I slot print_timing: id 1 | task 2798083 | n_gen = 3487, tg = 29.85 t/s, tg_3s = 27.28 t/s
llama-server | 11051.35.485.142 I slot print_timing: id 1 | task 2798083 | n_gen = 3565, tg = 29.74 t/s, tg_3s = 25.47 t/s
llama-server | 11051.38.548.013 I slot print_timing: id 1 | task 2798083 | n_gen = 3651, tg = 29.70 t/s, tg_3s = 28.08 t/s
llama-server | 11051.41.626.640 I slot print_timing: id 1 | task 2798083 | n_gen = 3738, tg = 29.66 t/s, tg_3s = 28.26 t/s
llama-server | 11051.44.692.003 I slot print_timing: id 1 | task 2798083 | n_gen = 3829, tg = 29.66 t/s, tg_3s = 29.69 t/s
llama-server | 11051.47.760.050 I slot print_timing: id 1 | task 2798083 | n_gen = 3911, tg = 29.59 t/s, tg_3s = 26.73 t/s
llama-server | 11051.50.846.305 I slot print_timing: id 1 | task 2798083 | n_gen = 3980, tg = 29.43 t/s, tg_3s = 22.36 t/s
llama-server | 11051.53.912.373 I slot print_timing: id 1 | task 2798083 | n_gen = 4063, tg = 29.38 t/s, tg_3s = 27.07 t/s
llama-server | 11051.56.984.061 I slot print_timing: id 1 | task 2798083 | n_gen = 4164, tg = 29.45 t/s, tg_3s = 32.88 t/s
llama-server | 11052.00.068.232 I slot print_timing: id 1 | task 2798083 | n_gen = 4223, tg = 29.23 t/s, tg_3s = 19.13 t/s
llama-server | 11052.03.145.960 I slot print_timing: id 1 | task 2798083 | n_gen = 4321, tg = 29.29 t/s, tg_3s = 31.84 t/s
llama-server | 11052.06.222.674 I slot print_timing: id 1 | task 2798083 | n_gen = 4408, tg = 29.27 t/s, tg_3s = 28.28 t/s
llama-server | 11052.09.313.476 I slot print_timing: id 1 | task 2798083 | n_gen = 4484, tg = 29.17 t/s, tg_3s = 24.59 t/s
llama-server | 11052.12.398.909 I slot print_timing: id 1 | task 2798083 | n_gen = 4579, tg = 29.20 t/s, tg_3s = 30.79 t/s
llama-server | 11052.15.476.374 I slot print_timing: id 1 | task 2798083 | n_gen = 4674, tg = 29.24 t/s, tg_3s = 30.87 t/s
llama-server | 11052.18.480.786 I slot print_timing: id 1 | task 2798083 | n_gen = 4760, tg = 29.22 t/s, tg_3s = 28.62 t/s
llama-server | 11052.21.556.233 I slot print_timing: id 1 | task 2798083 | n_gen = 4822, tg = 29.06 t/s, tg_3s = 20.16 t/s
llama-server | 11052.24.641.931 I slot print_timing: id 1 | task 2798083 | n_gen = 4937, tg = 29.21 t/s, tg_3s = 37.27 t/s
llama-server | 11052.27.644.754 I slot print_timing: id 1 | task 2798083 | n_gen = 5021, tg = 29.18 t/s, tg_3s = 27.97 t/s
llama-server | 11052.30.733.734 I slot print_timing: id 1 | task 2798083 | n_gen = 5119, tg = 29.23 t/s, tg_3s = 31.73 t/s
llama-server | 11052.33.817.501 I slot print_timing: id 1 | task 2798083 | n_gen = 5190, tg = 29.12 t/s, tg_3s = 23.02 t/s
llama-server | 11052.36.822.748 I slot print_timing: id 1 | task 2798083 | n_gen = 5265, tg = 29.05 t/s, tg_3s = 24.96 t/s
llama-server | 11052.39.913.543 I slot print_timing: id 1 | task 2798083 | n_gen = 5348, tg = 29.02 t/s, tg_3s = 26.85 t/s
llama-server | 11052.42.916.384 I slot print_timing: id 1 | task 2798083 | prompt eval time = 47873.92 ms / 45442 tokens ( 1.05 ms per token, 949.20 tokens per second)
llama-server | 11052.42.916.388 I slot print_timing: id 1 | task 2798083 | eval time = 187280.10 ms / 5448 tokens ( 34.38 ms per token, 29.08 tokens per second)
llama-server | 11052.42.916.388 I slot print_timing: id 1 | task 2798083 | total time = 235154.02 ms / 50890 tokens
llama-server | 11052.42.916.389 I slot print_timing: id 1 | task 2798083 | graphs reused = 2711696
llama-server | 11052.42.916.392 I slot print_timing: id 1 | task 2798083 | draft acceptance = 0.33877 ( 3425 accepted / 10110 generated), mean len = 2.69
llama-server | 11052.42.917.608 I slot release: id 1 | task 2798083 | stop processing: n_tokens = 50889, truncated = 0
llama-server | 11052.44.349.557 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 662940544132
llama-server | 11052.44.350.055 I slot launch_slot_: id 0 | task 2800130 | processing task, is_child = 0
llama-server | 11052.44.352.360 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2022.496 MiB)
llama-server | 11052.49.824.611 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.18 tokens per second
llama-server | 11052.51.641.433 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 6144, progress = 0.14, t = 4.81 s / 1276.18 tokens per second
llama-server | 11052.53.501.580 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.66 s / 1230.39 tokens per second
llama-server | 11052.55.389.774 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 10240, progress = 0.23, t = 8.55 s / 1198.35 tokens per second
llama-server | 11052.57.327.648 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.47 s / 1173.10 tokens per second
llama-server | 11052.59.291.625 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 14336, progress = 0.32, t = 12.43 s / 1153.47 tokens per second
llama-server | 11053.01.299.552 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.42 s / 1136.03 tokens per second
llama-server | 11053.03.339.871 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 18432, progress = 0.41, t = 16.46 s / 1120.01 tokens per second
llama-server | 11053.05.420.610 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.53 s / 1105.44 tokens per second
llama-server | 11053.07.541.404 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 22528, progress = 0.50, t = 20.63 s / 1091.74 tokens per second
llama-server | 11053.09.715.999 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.79 s / 1078.38 tokens per second
llama-server | 11053.11.913.882 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 26624, progress = 0.59, t = 24.99 s / 1065.44 tokens per second
llama-server | 11053.14.147.594 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 28672, progress = 0.63, t = 27.21 s / 1053.63 tokens per second
llama-server | 11053.16.415.533 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 30720, progress = 0.68, t = 29.47 s / 1042.29 tokens per second
llama-server | 11053.18.761.432 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 32768, progress = 0.72, t = 31.77 s / 1031.51 tokens per second
llama-server | 11053.21.099.577 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 34816, progress = 0.77, t = 34.14 s / 1019.82 tokens per second
llama-server | 11053.23.473.769 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 36864, progress = 0.81, t = 36.50 s / 1009.90 tokens per second
llama-server | 11053.25.881.973 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 38912, progress = 0.86, t = 38.90 s / 1000.21 tokens per second
llama-server | 11053.28.342.376 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 40960, progress = 0.90, t = 41.34 s / 990.86 tokens per second
llama-server | 11053.30.823.559 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 43008, progress = 0.95, t = 43.83 s / 981.31 tokens per second
llama-server | 11053.33.277.835 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 44957, progress = 0.99, t = 46.33 s / 970.30 tokens per second
llama-server | 11053.34.059.179 I slot print_timing: id 0 | task 2800130 | prompt processing, n_tokens = 45469, progress = 1.00, t = 47.15 s / 964.33 tokens per second
llama-server | 11053.38.958.265 I slot print_timing: id 0 | task 2800130 | n_gen = 100, tg = 21.26 t/s, tg_3s = 21.48 t/s
llama-server | 11053.42.046.897 I slot print_timing: id 0 | task 2800130 | n_gen = 180, tg = 23.11 t/s, tg_3s = 25.90 t/s
llama-server | 11053.45.135.240 I slot print_timing: id 0 | task 2800130 | n_gen = 269, tg = 24.74 t/s, tg_3s = 28.82 t/s
llama-server | 11053.48.221.854 I slot print_timing: id 0 | task 2800130 | n_gen = 351, tg = 25.14 t/s, tg_3s = 26.57 t/s
llama-server | 11053.51.242.344 I slot print_timing: id 0 | task 2800130 | n_gen = 448, tg = 26.39 t/s, tg_3s = 32.11 t/s
llama-server | 11053.54.256.747 I slot print_timing: id 0 | task 2800130 | n_gen = 574, tg = 28.72 t/s, tg_3s = 41.80 t/s
llama-server | 11053.54.985.658 I slot print_timing: id 0 | task 2800130 | prompt eval time = 48021.60 ms / 45473 tokens ( 1.06 ms per token, 946.93 tokens per second)
llama-server | 11053.54.985.661 I slot print_timing: id 0 | task 2800130 | eval time = 20683.48 ms / 603 tokens ( 34.36 ms per token, 29.11 tokens per second)
llama-server | 11053.54.985.661 I slot print_timing: id 0 | task 2800130 | total time = 68705.08 ms / 46076 tokens
llama-server | 11053.54.985.662 I slot print_timing: id 0 | task 2800130 | graphs reused = 2711920
llama-server | 11053.54.985.665 I slot print_timing: id 0 | task 2800130 | draft acceptance = 0.33128 ( 376 accepted / 1135 generated), mean len = 2.66
llama-server | 11053.54.986.910 I slot release: id 0 | task 2800130 | stop processing: n_tokens = 46076, truncated = 0
llama-server | 11053.56.338.833 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 663178757663
llama-server | 11053.56.339.394 I slot launch_slot_: id 1 | task 2800382 | processing task, is_child = 0
llama-server | 11053.56.341.649 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2230.999 MiB)
llama-server | 11054.01.149.501 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.00 s / 1364.48 tokens per second
llama-server | 11054.02.967.624 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.81 s / 1276.92 tokens per second
llama-server | 11054.04.820.656 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.65 s / 1231.41 tokens per second
llama-server | 11054.06.706.933 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.53 s / 1200.22 tokens per second
llama-server | 11054.08.630.795 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.45 s / 1176.41 tokens per second
llama-server | 11054.10.614.120 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.41 s / 1154.96 tokens per second
llama-server | 11054.12.623.056 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.41 s / 1136.98 tokens per second
llama-server | 11054.14.665.039 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.45 s / 1120.49 tokens per second
llama-server | 11054.16.743.582 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.52 s / 1105.87 tokens per second
llama-server | 11054.18.865.375 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.63 s / 1092.18 tokens per second
llama-server | 11054.21.038.200 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.78 s / 1078.75 tokens per second
llama-server | 11054.23.237.060 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.98 s / 1065.86 tokens per second
llama-server | 11054.25.470.180 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 28672, progress = 0.63, t = 27.21 s / 1053.91 tokens per second
llama-server | 11054.27.736.568 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.46 s / 1042.63 tokens per second
llama-server | 11054.30.071.802 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 32768, progress = 0.72, t = 31.76 s / 1031.86 tokens per second
llama-server | 11054.32.405.802 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 34816, progress = 0.76, t = 34.12 s / 1020.51 tokens per second
llama-server | 11054.34.779.013 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 36864, progress = 0.81, t = 36.48 s / 1010.56 tokens per second
llama-server | 11054.37.184.939 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 38912, progress = 0.85, t = 38.88 s / 1000.88 tokens per second
llama-server | 11054.39.644.116 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 40960, progress = 0.90, t = 41.31 s / 991.52 tokens per second
llama-server | 11054.42.121.448 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 43008, progress = 0.94, t = 43.80 s / 982.01 tokens per second
llama-server | 11054.44.635.942 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 45056, progress = 0.98, t = 46.30 s / 973.13 tokens per second
llama-server | 11054.44.954.744 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 45232, progress = 0.99, t = 47.04 s / 961.63 tokens per second
llama-server | 11054.45.737.747 I slot print_timing: id 1 | task 2800382 | prompt processing, n_tokens = 45744, progress = 1.00, t = 47.51 s / 962.91 tokens per second
llama-server | 11054.48.968.656 I slot print_timing: id 1 | task 2800382 | n_gen = 105, tg = 34.27 t/s, tg_3s = 34.60 t/s
llama-server | 11054.50.610.668 I slot print_timing: id 1 | task 2800382 | prompt eval time = 48322.78 ms / 45748 tokens ( 1.06 ms per token, 946.72 tokens per second)
llama-server | 11054.50.610.671 I slot print_timing: id 1 | task 2800382 | eval time = 4676.55 ms / 191 tokens ( 24.61 ms per token, 40.63 tokens per second)
llama-server | 11054.50.610.672 I slot print_timing: id 1 | task 2800382 | total time = 52999.33 ms / 45939 tokens
llama-server | 11054.50.610.672 I slot print_timing: id 1 | task 2800382 | graphs reused = 2711969
llama-server | 11054.50.610.675 I slot print_timing: id 1 | task 2800382 | draft acceptance = 0.54510 ( 139 accepted / 255 generated), mean len = 3.73
llama-server | 11054.50.611.914 I slot release: id 1 | task 2800382 | stop processing: n_tokens = 45938, truncated = 0
llama-server | 11054.51.825.109 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 663250826962
llama-server | 11054.51.825.905 I slot launch_slot_: id 0 | task 2800459 | processing task, is_child = 0
llama-server | 11054.51.828.004 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2138.135 MiB)
llama-server | 11054.59.318.857 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.79 s / 1282.11 tokens per second
llama-server | 11055.01.170.339 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.63 s / 1235.63 tokens per second
llama-server | 11055.03.051.084 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.51 s / 1203.66 tokens per second
llama-server | 11055.04.981.797 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.42 s / 1178.95 tokens per second
llama-server | 11055.06.939.349 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.38 s / 1158.34 tokens per second
llama-server | 11055.08.937.967 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.36 s / 1140.83 tokens per second
llama-server | 11055.10.974.031 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.39 s / 1124.59 tokens per second
llama-server | 11055.13.048.669 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.46 s / 1109.71 tokens per second
llama-server | 11055.15.171.698 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.56 s / 1095.82 tokens per second
llama-server | 11055.17.341.196 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.72 s / 1081.92 tokens per second
llama-server | 11055.19.533.394 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.91 s / 1068.86 tokens per second
llama-server | 11055.21.764.485 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 28672, progress = 0.63, t = 27.13 s / 1056.87 tokens per second
llama-server | 11055.24.028.833 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.39 s / 1045.37 tokens per second
llama-server | 11055.26.361.960 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 32768, progress = 0.72, t = 31.68 s / 1034.46 tokens per second
llama-server | 11055.28.696.307 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 34816, progress = 0.76, t = 34.04 s / 1022.93 tokens per second
llama-server | 11055.31.069.877 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 36864, progress = 0.81, t = 36.40 s / 1012.77 tokens per second
llama-server | 11055.33.476.120 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 38912, progress = 0.85, t = 38.80 s / 1002.96 tokens per second
llama-server | 11055.35.936.299 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 40960, progress = 0.90, t = 41.23 s / 993.47 tokens per second
llama-server | 11055.38.413.976 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 43008, progress = 0.94, t = 43.72 s / 983.78 tokens per second
llama-server | 11055.40.929.625 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 45056, progress = 0.99, t = 46.22 s / 974.80 tokens per second
llama-server | 11055.41.247.510 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 45225, progress = 0.99, t = 46.96 s / 963.05 tokens per second
llama-server | 11055.42.034.279 I slot print_timing: id 0 | task 2800459 | prompt processing, n_tokens = 45737, progress = 1.00, t = 47.43 s / 964.27 tokens per second
llama-server | 11055.45.477.176 I slot print_timing: id 0 | task 2800459 | n_gen = 102, tg = 31.44 t/s, tg_3s = 31.75 t/s
llama-server | 11055.45.751.186 I slot print_timing: id 0 | task 2800459 | prompt eval time = 48283.20 ms / 45741 tokens ( 1.06 ms per token, 947.35 tokens per second)
llama-server | 11055.45.751.189 I slot print_timing: id 0 | task 2800459 | eval time = 3486.08 ms / 120 tokens ( 29.29 ms per token, 34.14 tokens per second)
llama-server | 11055.45.751.190 I slot print_timing: id 0 | task 2800459 | total time = 51769.28 ms / 45861 tokens
llama-server | 11055.45.751.190 I slot print_timing: id 0 | task 2800459 | graphs reused = 2712005
llama-server | 11055.45.751.193 I slot print_timing: id 0 | task 2800459 | draft acceptance = 0.42632 ( 81 accepted / 190 generated), mean len = 3.13
llama-server | 11055.45.752.440 I slot release: id 0 | task 2800459 | stop processing: n_tokens = 45860, truncated = 0
llama-server | 11055.47.099.601 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 663306451965
llama-server | 11055.47.100.252 I slot launch_slot_: id 1 | task 2800523 | processing task, is_child = 0
llama-server | 11055.47.102.358 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2261.023 MiB)
llama-server | 11055.54.007.515 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.79 s / 1281.60 tokens per second
llama-server | 11055.55.860.043 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.63 s / 1235.47 tokens per second
llama-server | 11055.57.741.590 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.51 s / 1203.16 tokens per second
llama-server | 11055.59.666.588 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.43 s / 1178.56 tokens per second
llama-server | 11056.01.622.659 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.37 s / 1158.73 tokens per second
llama-server | 11056.03.621.741 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.36 s / 1141.08 tokens per second
llama-server | 11056.05.655.495 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.39 s / 1124.85 tokens per second
llama-server | 11056.07.730.252 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.45 s / 1110.11 tokens per second
llama-server | 11056.09.844.422 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.55 s / 1096.16 tokens per second
llama-server | 11056.12.011.332 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.70 s / 1082.77 tokens per second
llama-server | 11056.14.201.827 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.89 s / 1069.67 tokens per second
llama-server | 11056.16.430.466 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 28672, progress = 0.63, t = 27.11 s / 1057.65 tokens per second
llama-server | 11056.18.692.687 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.36 s / 1046.18 tokens per second
llama-server | 11056.21.026.032 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 32768, progress = 0.72, t = 31.65 s / 1035.26 tokens per second
llama-server | 11056.23.358.745 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 34816, progress = 0.76, t = 34.01 s / 1023.66 tokens per second
llama-server | 11056.25.729.351 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 36864, progress = 0.81, t = 36.37 s / 1013.56 tokens per second
llama-server | 11056.28.143.354 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 38912, progress = 0.85, t = 38.77 s / 1003.70 tokens per second
llama-server | 11056.30.602.765 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 40960, progress = 0.89, t = 41.21 s / 993.95 tokens per second
llama-server | 11056.33.079.890 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 43008, progress = 0.94, t = 43.70 s / 984.26 tokens per second
llama-server | 11056.35.593.910 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 45056, progress = 0.98, t = 46.20 s / 975.26 tokens per second
llama-server | 11056.35.935.816 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 45252, progress = 0.99, t = 46.94 s / 964.10 tokens per second
llama-server | 11056.36.704.730 I slot print_timing: id 1 | task 2800523 | prompt processing, n_tokens = 45764, progress = 1.00, t = 47.41 s / 965.19 tokens per second
llama-server | 11056.39.946.573 I slot print_timing: id 1 | task 2800523 | n_gen = 106, tg = 34.48 t/s, tg_3s = 34.81 t/s
llama-server | 11056.41.317.892 I slot print_timing: id 1 | task 2800523 | prompt eval time = 48231.82 ms / 45768 tokens ( 1.05 ms per token, 948.92 tokens per second)
llama-server | 11056.41.317.896 I slot print_timing: id 1 | task 2800523 | eval time = 4416.52 ms / 175 tokens ( 25.38 ms per token, 39.40 tokens per second)
llama-server | 11056.41.317.897 I slot print_timing: id 1 | task 2800523 | total time = 52648.34 ms / 45943 tokens
llama-server | 11056.41.317.898 I slot print_timing: id 1 | task 2800523 | graphs reused = 2712051
llama-server | 11056.41.317.902 I slot print_timing: id 1 | task 2800523 | draft acceptance = 0.52500 ( 126 accepted / 240 generated), mean len = 3.62
llama-server | 11056.41.319.242 I slot release: id 1 | task 2800523 | stop processing: n_tokens = 45942, truncated = 0
llama-server | 11056.42.561.652 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 663361592492
llama-server | 11056.42.562.319 I slot launch_slot_: id 0 | task 2800597 | processing task, is_child = 0
llama-server | 11056.42.564.550 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2100.996 MiB)
llama-server | 11056.49.157.866 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.79 s / 1282.41 tokens per second
llama-server | 11056.51.006.404 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.64 s / 1234.59 tokens per second
llama-server | 11056.52.887.856 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.51 s / 1203.26 tokens per second
llama-server | 11056.54.807.343 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.42 s / 1179.25 tokens per second
llama-server | 11056.56.775.115 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.38 s / 1158.43 tokens per second
llama-server | 11056.58.773.605 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.36 s / 1140.57 tokens per second
llama-server | 11057.00.809.309 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.39 s / 1124.37 tokens per second
llama-server | 11057.02.884.385 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.46 s / 1109.58 tokens per second
llama-server | 11057.05.001.008 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.56 s / 1095.66 tokens per second
llama-server | 11057.07.170.577 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 24576, progress = 0.53, t = 22.71 s / 1082.13 tokens per second
llama-server | 11057.09.363.387 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.91 s / 1068.98 tokens per second
llama-server | 11057.11.596.093 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 28672, progress = 0.62, t = 27.13 s / 1057.00 tokens per second
llama-server | 11057.13.860.361 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.38 s / 1045.49 tokens per second
llama-server | 11057.16.194.036 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 32768, progress = 0.71, t = 31.67 s / 1034.53 tokens per second
llama-server | 11057.18.526.616 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 34816, progress = 0.76, t = 34.03 s / 1023.01 tokens per second
llama-server | 11057.20.899.131 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 36864, progress = 0.80, t = 36.40 s / 1012.88 tokens per second
llama-server | 11057.23.304.495 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 38912, progress = 0.85, t = 38.79 s / 1003.07 tokens per second
llama-server | 11057.25.761.888 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 40960, progress = 0.89, t = 41.22 s / 993.58 tokens per second
llama-server | 11057.28.239.189 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 43008, progress = 0.94, t = 43.71 s / 983.95 tokens per second
llama-server | 11057.30.760.270 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 45056, progress = 0.98, t = 46.21 s / 974.98 tokens per second
llama-server | 11057.31.294.700 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 45429, progress = 0.99, t = 46.96 s / 967.35 tokens per second
llama-server | 11057.32.078.747 I slot print_timing: id 0 | task 2800597 | prompt processing, n_tokens = 45941, progress = 1.00, t = 47.64 s / 964.39 tokens per second
llama-server | 11057.35.346.818 I slot print_timing: id 0 | task 2800597 | n_gen = 106, tg = 34.73 t/s, tg_3s = 35.06 t/s
llama-server | 11057.38.365.922 I slot print_timing: id 0 | task 2800597 | n_gen = 188, tg = 30.95 t/s, tg_3s = 27.16 t/s
llama-server | 11057.41.371.370 I slot print_timing: id 0 | task 2800597 | n_gen = 262, tg = 28.85 t/s, tg_3s = 24.62 t/s
llama-server | 11057.44.380.916 I slot print_timing: id 0 | task 2800597 | n_gen = 349, tg = 28.86 t/s, tg_3s = 28.91 t/s
llama-server | 11057.47.413.819 I slot print_timing: id 0 | task 2800597 | n_gen = 454, tg = 30.02 t/s, tg_3s = 34.62 t/s
llama-server | 11057.50.427.080 I slot print_timing: id 0 | task 2800597 | n_gen = 545, tg = 30.05 t/s, tg_3s = 30.20 t/s
llama-server | 11057.53.463.595 I slot print_timing: id 0 | task 2800597 | n_gen = 650, tg = 30.70 t/s, tg_3s = 34.58 t/s
llama-server | 11057.56.486.872 I slot print_timing: id 0 | task 2800597 | n_gen = 750, tg = 31.00 t/s, tg_3s = 33.08 t/s
llama-server | 11057.59.509.323 I slot print_timing: id 0 | task 2800597 | n_gen = 834, tg = 30.64 t/s, tg_3s = 27.79 t/s
llama-server | 11058.02.549.709 I slot print_timing: id 0 | task 2800597 | n_gen = 908, tg = 30.01 t/s, tg_3s = 24.34 t/s
llama-server | 11058.05.568.054 I slot print_timing: id 0 | task 2800597 | n_gen = 987, tg = 29.66 t/s, tg_3s = 26.17 t/s
llama-server | 11058.08.587.647 I slot print_timing: id 0 | task 2800597 | n_gen = 1057, tg = 29.12 t/s, tg_3s = 23.18 t/s
llama-server | 11058.11.620.173 I slot print_timing: id 0 | task 2800597 | n_gen = 1158, tg = 29.44 t/s, tg_3s = 33.31 t/s
llama-server | 11058.14.669.180 I slot print_timing: id 0 | task 2800597 | n_gen = 1246, tg = 29.40 t/s, tg_3s = 28.86 t/s
llama-server | 11058.17.702.763 I slot print_timing: id 0 | task 2800597 | n_gen = 1320, tg = 29.07 t/s, tg_3s = 24.39 t/s
llama-server | 11058.20.740.741 I slot print_timing: id 0 | task 2800597 | n_gen = 1404, tg = 28.98 t/s, tg_3s = 27.65 t/s
llama-server | 11058.23.794.546 I slot print_timing: id 0 | task 2800597 | n_gen = 1483, tg = 28.79 t/s, tg_3s = 25.87 t/s
llama-server | 11058.26.826.093 I slot print_timing: id 0 | task 2800597 | n_gen = 1541, tg = 28.26 t/s, tg_3s = 19.13 t/s
llama-server | 11058.29.864.359 I slot print_timing: id 0 | task 2800597 | n_gen = 1624, tg = 28.21 t/s, tg_3s = 27.32 t/s
llama-server | 11058.32.924.296 I slot print_timing: id 0 | task 2800597 | n_gen = 1718, tg = 28.33 t/s, tg_3s = 30.72 t/s
llama-server | 11058.35.971.647 I slot print_timing: id 0 | task 2800597 | n_gen = 1805, tg = 28.34 t/s, tg_3s = 28.55 t/s
llama-server | 11058.39.008.776 I slot print_timing: id 0 | task 2800597 | n_gen = 1886, tg = 28.27 t/s, tg_3s = 26.67 t/s
llama-server | 11058.42.074.489 I slot print_timing: id 0 | task 2800597 | n_gen = 1973, tg = 28.27 t/s, tg_3s = 28.38 t/s
llama-server | 11058.45.127.053 I slot print_timing: id 0 | task 2800597 | n_gen = 2063, tg = 28.32 t/s, tg_3s = 29.48 t/s
llama-server | 11058.48.172.826 I slot print_timing: id 0 | task 2800597 | n_gen = 2140, tg = 28.20 t/s, tg_3s = 25.28 t/s
llama-server | 11058.51.242.241 I slot print_timing: id 0 | task 2800597 | n_gen = 2228, tg = 28.22 t/s, tg_3s = 28.67 t/s
llama-server | 11058.54.293.253 I slot print_timing: id 0 | task 2800597 | n_gen = 2316, tg = 28.24 t/s, tg_3s = 28.84 t/s
llama-server | 11058.57.341.104 I slot print_timing: id 0 | task 2800597 | n_gen = 2406, tg = 28.29 t/s, tg_3s = 29.53 t/s
llama-server | 11059.00.416.882 I slot print_timing: id 0 | task 2800597 | n_gen = 2519, tg = 28.58 t/s, tg_3s = 36.74 t/s
llama-server | 11059.03.472.579 I slot print_timing: id 0 | task 2800597 | n_gen = 2614, tg = 28.67 t/s, tg_3s = 31.09 t/s
llama-server | 11059.06.544.900 I slot print_timing: id 0 | task 2800597 | n_gen = 2702, tg = 28.67 t/s, tg_3s = 28.64 t/s
llama-server | 11059.09.611.974 I slot print_timing: id 0 | task 2800597 | n_gen = 2809, tg = 28.86 t/s, tg_3s = 34.89 t/s
llama-server | 11059.12.673.590 I slot print_timing: id 0 | task 2800597 | n_gen = 2882, tg = 28.71 t/s, tg_3s = 23.84 t/s
llama-server | 11059.13.788.938 I slot print_timing: id 0 | task 2800597 | prompt eval time = 48507.82 ms / 45945 tokens ( 1.06 ms per token, 947.17 tokens per second)
llama-server | 11059.13.788.941 I slot print_timing: id 0 | task 2800597 | eval time = 101465.57 ms / 2921 tokens ( 34.75 ms per token, 28.78 tokens per second)
llama-server | 11059.13.788.942 I slot print_timing: id 0 | task 2800597 | total time = 149973.39 ms / 48866 tokens
llama-server | 11059.13.788.943 I slot print_timing: id 0 | task 2800597 | graphs reused = 2713140
llama-server | 11059.13.788.946 I slot print_timing: id 0 | task 2800597 | draft acceptance = 0.33043 ( 1819 accepted / 5505 generated), mean len = 2.65
llama-server | 11059.13.790.169 I slot release: id 0 | task 2800597 | stop processing: n_tokens = 48865, truncated = 0
llama-server | 11059.15.324.568 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 663417159295
llama-server | 11059.15.325.111 I slot launch_slot_: id 1 | task 2801724 | processing task, is_child = 0
llama-server | 11059.15.327.367 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2096.408 MiB)
llama-server | 11059.21.044.779 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.00 s / 1363.21 tokens per second
llama-server | 11059.22.863.602 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.82 s / 1275.85 tokens per second
llama-server | 11059.24.733.570 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.67 s / 1228.21 tokens per second
llama-server | 11059.26.625.140 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.56 s / 1196.44 tokens per second
llama-server | 11059.28.553.725 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 12288, progress = 0.26, t = 10.48 s / 1172.76 tokens per second
llama-server | 11059.30.521.710 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.44 s / 1152.83 tokens per second
llama-server | 11059.32.530.320 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 16384, progress = 0.35, t = 14.43 s / 1135.26 tokens per second
llama-server | 11059.34.574.119 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.47 s / 1119.16 tokens per second
llama-server | 11059.36.657.633 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 20480, progress = 0.44, t = 18.54 s / 1104.45 tokens per second
llama-server | 11059.38.780.347 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.65 s / 1090.75 tokens per second
llama-server | 11059.40.956.441 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 24576, progress = 0.53, t = 22.81 s / 1077.52 tokens per second
llama-server | 11059.43.156.004 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 26624, progress = 0.57, t = 25.01 s / 1064.55 tokens per second
llama-server | 11059.45.394.102 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 28672, progress = 0.62, t = 27.24 s / 1052.75 tokens per second
llama-server | 11059.47.662.921 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 30720, progress = 0.66, t = 29.50 s / 1041.36 tokens per second
llama-server | 11059.50.003.908 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 32768, progress = 0.71, t = 31.80 s / 1030.57 tokens per second
llama-server | 11059.52.347.986 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 34816, progress = 0.75, t = 34.16 s / 1019.14 tokens per second
llama-server | 11059.54.725.752 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 36864, progress = 0.79, t = 36.53 s / 1009.07 tokens per second
llama-server | 11059.57.137.016 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 38912, progress = 0.84, t = 38.94 s / 999.36 tokens per second
llama-server | 11059.59.600.040 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 40960, progress = 0.88, t = 41.38 s / 989.97 tokens per second
llama-server | 11060.02.081.050 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 43008, progress = 0.93, t = 43.86 s / 980.48 tokens per second
llama-server | 11060.04.596.641 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 45056, progress = 0.97, t = 46.37 s / 971.66 tokens per second
llama-server | 11060.05.752.376 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 45919, progress = 0.99, t = 47.71 s / 962.41 tokens per second
llama-server | 11060.06.534.847 I slot print_timing: id 1 | task 2801724 | prompt processing, n_tokens = 46431, progress = 1.00, t = 48.40 s / 959.26 tokens per second
llama-server | 11060.09.819.741 I slot print_timing: id 1 | task 2801724 | n_gen = 121, tg = 39.49 t/s, tg_3s = 39.81 t/s
llama-server | 11060.12.844.186 I slot print_timing: id 1 | task 2801724 | n_gen = 196, tg = 32.16 t/s, tg_3s = 24.80 t/s
llama-server | 11060.15.857.193 I slot print_timing: id 1 | task 2801724 | n_gen = 282, tg = 30.96 t/s, tg_3s = 28.54 t/s
llama-server | 11060.18.871.355 I slot print_timing: id 1 | task 2801724 | n_gen = 361, tg = 29.78 t/s, tg_3s = 26.21 t/s
llama-server | 11060.21.901.675 I slot print_timing: id 1 | task 2801724 | n_gen = 426, tg = 28.11 t/s, tg_3s = 21.45 t/s
llama-server | 11060.24.914.490 I slot print_timing: id 1 | task 2801724 | n_gen = 480, tg = 26.42 t/s, tg_3s = 17.92 t/s
llama-server | 11060.27.933.125 I slot print_timing: id 1 | task 2801724 | n_gen = 545, tg = 25.72 t/s, tg_3s = 21.53 t/s
llama-server | 11060.30.955.268 I slot print_timing: id 1 | task 2801724 | n_gen = 624, tg = 25.77 t/s, tg_3s = 26.14 t/s
llama-server | 11060.33.991.746 I slot print_timing: id 1 | task 2801724 | n_gen = 694, tg = 25.47 t/s, tg_3s = 23.05 t/s
llama-server | 11060.37.014.595 I slot print_timing: id 1 | task 2801724 | n_gen = 766, tg = 25.30 t/s, tg_3s = 23.82 t/s
llama-server | 11060.40.043.550 I slot print_timing: id 1 | task 2801724 | n_gen = 840, tg = 25.22 t/s, tg_3s = 24.43 t/s
llama-server | 11060.43.073.222 I slot print_timing: id 1 | task 2801724 | n_gen = 912, tg = 25.10 t/s, tg_3s = 23.76 t/s
llama-server | 11060.46.126.304 I slot print_timing: id 1 | task 2801724 | n_gen = 997, tg = 25.31 t/s, tg_3s = 27.84 t/s
llama-server | 11060.49.158.957 I slot print_timing: id 1 | task 2801724 | n_gen = 1072, tg = 25.27 t/s, tg_3s = 24.73 t/s
llama-server | 11060.52.195.257 I slot print_timing: id 1 | task 2801724 | n_gen = 1157, tg = 25.45 t/s, tg_3s = 27.99 t/s
llama-server | 11060.55.247.887 I slot print_timing: id 1 | task 2801724 | n_gen = 1232, tg = 25.40 t/s, tg_3s = 24.57 t/s
llama-server | 11060.58.288.213 I slot print_timing: id 1 | task 2801724 | n_gen = 1315, tg = 25.51 t/s, tg_3s = 27.30 t/s
llama-server | 11061.01.330.148 I slot print_timing: id 1 | task 2801724 | n_gen = 1372, tg = 25.13 t/s, tg_3s = 18.74 t/s
llama-server | 11061.04.384.685 I slot print_timing: id 1 | task 2801724 | n_gen = 1456, tg = 25.26 t/s, tg_3s = 27.50 t/s
llama-server | 11061.07.425.701 I slot print_timing: id 1 | task 2801724 | n_gen = 1524, tg = 25.11 t/s, tg_3s = 22.36 t/s
llama-server | 11061.10.474.429 I slot print_timing: id 1 | task 2801724 | n_gen = 1612, tg = 25.29 t/s, tg_3s = 28.86 t/s
llama-server | 11061.13.521.164 I slot print_timing: id 1 | task 2801724 | n_gen = 1671, tg = 25.02 t/s, tg_3s = 19.36 t/s
llama-server | 11061.16.589.944 I slot print_timing: id 1 | task 2801724 | n_gen = 1753, tg = 25.10 t/s, tg_3s = 26.72 t/s
llama-server | 11061.19.642.618 I slot print_timing: id 1 | task 2801724 | n_gen = 1824, tg = 25.02 t/s, tg_3s = 23.26 t/s
llama-server | 11061.22.695.256 I slot print_timing: id 1 | task 2801724 | n_gen = 1894, tg = 24.94 t/s, tg_3s = 22.93 t/s
llama-server | 11061.25.760.154 I slot print_timing: id 1 | task 2801724 | n_gen = 1971, tg = 24.94 t/s, tg_3s = 25.12 t/s
llama-server | 11061.28.819.083 I slot print_timing: id 1 | task 2801724 | n_gen = 2076, tg = 25.29 t/s, tg_3s = 34.33 t/s
llama-server | 11061.31.599.470 I slot print_timing: id 1 | task 2801724 | prompt eval time = 49278.85 ms / 46435 tokens ( 1.06 ms per token, 942.29 tokens per second)
llama-server | 11061.31.599.473 I slot print_timing: id 1 | task 2801724 | eval time = 84818.59 ms / 2147 tokens ( 39.52 ms per token, 25.30 tokens per second)
llama-server | 11061.31.599.474 I slot print_timing: id 1 | task 2801724 | total time = 134097.44 ms / 48582 tokens
llama-server | 11061.31.599.474 I slot print_timing: id 1 | task 2801724 | graphs reused = 2714052
llama-server | 11061.31.599.477 I slot print_timing: id 1 | task 2801724 | draft acceptance = 0.26623 ( 1226 accepted / 4605 generated), mean len = 2.33
llama-server | 11061.31.600.714 I slot release: id 1 | task 2801724 | stop processing: n_tokens = 48582, truncated = 0
llama-server | 11061.32.954.632 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 663569630221
llama-server | 11061.32.955.135 I slot launch_slot_: id 0 | task 2802671 | processing task, is_child = 0
llama-server | 11061.32.957.443 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2093.814 MiB)
llama-server | 11061.38.234.582 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.20 tokens per second
llama-server | 11061.40.052.524 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.82 s / 1275.73 tokens per second
llama-server | 11061.41.910.375 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.66 s / 1230.32 tokens per second
llama-server | 11061.43.796.847 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.54 s / 1198.69 tokens per second
llama-server | 11061.45.737.030 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.47 s / 1173.40 tokens per second
llama-server | 11061.47.701.506 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.43 s / 1153.50 tokens per second
llama-server | 11061.49.706.507 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 16384, progress = 0.35, t = 14.42 s / 1136.18 tokens per second
llama-server | 11061.51.749.548 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.46 s / 1119.99 tokens per second
llama-server | 11061.53.830.265 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 20480, progress = 0.44, t = 18.53 s / 1105.45 tokens per second
llama-server | 11061.55.948.866 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.63 s / 1091.79 tokens per second
llama-server | 11061.58.121.722 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 24576, progress = 0.53, t = 22.79 s / 1078.57 tokens per second
llama-server | 11062.00.319.058 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.99 s / 1065.59 tokens per second
llama-server | 11062.02.552.911 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 28672, progress = 0.62, t = 27.21 s / 1053.79 tokens per second
llama-server | 11062.04.820.114 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.47 s / 1042.48 tokens per second
llama-server | 11062.07.155.415 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 32768, progress = 0.71, t = 31.76 s / 1031.74 tokens per second
llama-server | 11062.09.492.693 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 34816, progress = 0.75, t = 34.12 s / 1020.33 tokens per second
llama-server | 11062.11.875.470 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 36864, progress = 0.80, t = 36.49 s / 1010.34 tokens per second
llama-server | 11062.14.285.294 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 38912, progress = 0.84, t = 38.90 s / 1000.40 tokens per second
llama-server | 11062.16.744.965 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 40960, progress = 0.89, t = 41.33 s / 991.00 tokens per second
llama-server | 11062.19.222.646 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 43008, progress = 0.93, t = 43.82 s / 981.53 tokens per second
llama-server | 11062.21.736.734 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 45056, progress = 0.98, t = 46.32 s / 972.66 tokens per second
llama-server | 11062.22.567.600 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 45654, progress = 0.99, t = 47.66 s / 957.85 tokens per second
llama-server | 11062.23.353.832 I slot print_timing: id 0 | task 2802671 | prompt processing, n_tokens = 46166, progress = 1.00, t = 48.04 s / 960.97 tokens per second
llama-server | 11062.27.493.337 I slot print_timing: id 0 | task 2802671 | n_gen = 100, tg = 25.11 t/s, tg_3s = 25.36 t/s
llama-server | 11062.30.520.168 I slot print_timing: id 0 | task 2802671 | n_gen = 168, tg = 23.96 t/s, tg_3s = 22.47 t/s
llama-server | 11062.33.533.579 I slot print_timing: id 0 | task 2802671 | n_gen = 238, tg = 23.74 t/s, tg_3s = 23.23 t/s
llama-server | 11062.36.546.122 I slot print_timing: id 0 | task 2802671 | n_gen = 324, tg = 24.85 t/s, tg_3s = 28.55 t/s
llama-server | 11062.39.561.279 I slot print_timing: id 0 | task 2802671 | n_gen = 407, tg = 25.36 t/s, tg_3s = 27.53 t/s
llama-server | 11062.42.593.066 I slot print_timing: id 0 | task 2802671 | n_gen = 483, tg = 25.31 t/s, tg_3s = 25.07 t/s
llama-server | 11062.45.616.647 I slot print_timing: id 0 | task 2802671 | n_gen = 562, tg = 25.42 t/s, tg_3s = 26.13 t/s
llama-server | 11062.48.641.769 I slot print_timing: id 0 | task 2802671 | n_gen = 662, tg = 26.34 t/s, tg_3s = 33.06 t/s
llama-server | 11062.51.692.914 I slot print_timing: id 0 | task 2802671 | n_gen = 771, tg = 27.36 t/s, tg_3s = 35.72 t/s
llama-server | 11062.54.727.220 I slot print_timing: id 0 | task 2802671 | n_gen = 872, tg = 27.94 t/s, tg_3s = 33.29 t/s
llama-server | 11062.57.774.359 I slot print_timing: id 0 | task 2802671 | n_gen = 950, tg = 27.73 t/s, tg_3s = 25.60 t/s
llama-server | 11063.00.812.164 I slot print_timing: id 0 | task 2802671 | n_gen = 1035, tg = 27.75 t/s, tg_3s = 27.98 t/s
llama-server | 11063.03.849.812 I slot print_timing: id 0 | task 2802671 | n_gen = 1112, tg = 27.57 t/s, tg_3s = 25.35 t/s
llama-server | 11063.06.904.773 I slot print_timing: id 0 | task 2802671 | n_gen = 1198, tg = 27.61 t/s, tg_3s = 28.15 t/s
llama-server | 11063.09.942.790 I slot print_timing: id 0 | task 2802671 | n_gen = 1266, tg = 27.27 t/s, tg_3s = 22.38 t/s
llama-server | 11063.12.987.256 I slot print_timing: id 0 | task 2802671 | n_gen = 1347, tg = 27.23 t/s, tg_3s = 26.61 t/s
llama-server | 11063.16.027.898 I slot print_timing: id 0 | task 2802671 | n_gen = 1421, tg = 27.06 t/s, tg_3s = 24.34 t/s
llama-server | 11063.19.079.573 I slot print_timing: id 0 | task 2802671 | n_gen = 1502, tg = 27.03 t/s, tg_3s = 26.54 t/s
llama-server | 11063.22.116.209 I slot print_timing: id 0 | task 2802671 | n_gen = 1563, tg = 26.67 t/s, tg_3s = 20.09 t/s
llama-server | 11063.25.156.571 I slot print_timing: id 0 | task 2802671 | n_gen = 1638, tg = 26.57 t/s, tg_3s = 24.67 t/s
llama-server | 11063.28.212.970 I slot print_timing: id 0 | task 2802671 | n_gen = 1723, tg = 26.63 t/s, tg_3s = 27.81 t/s
llama-server | 11063.31.259.249 I slot print_timing: id 0 | task 2802671 | n_gen = 1809, tg = 26.70 t/s, tg_3s = 28.23 t/s
llama-server | 11063.34.300.416 I slot print_timing: id 0 | task 2802671 | n_gen = 1870, tg = 26.42 t/s, tg_3s = 20.06 t/s
llama-server | 11063.37.350.550 I slot print_timing: id 0 | task 2802671 | n_gen = 1940, tg = 26.27 t/s, tg_3s = 22.95 t/s
llama-server | 11063.40.422.799 I slot print_timing: id 0 | task 2802671 | n_gen = 2038, tg = 26.50 t/s, tg_3s = 31.90 t/s
llama-server | 11063.43.479.457 I slot print_timing: id 0 | task 2802671 | n_gen = 2134, tg = 26.69 t/s, tg_3s = 31.41 t/s
llama-server | 11063.46.554.286 I slot print_timing: id 0 | task 2802671 | n_gen = 2224, tg = 26.78 t/s, tg_3s = 29.27 t/s
llama-server | 11063.49.615.151 I slot print_timing: id 0 | task 2802671 | n_gen = 2324, tg = 26.99 t/s, tg_3s = 32.67 t/s
llama-server | 11063.52.674.213 I slot print_timing: id 0 | task 2802671 | n_gen = 2413, tg = 27.06 t/s, tg_3s = 29.09 t/s
llama-server | 11063.55.751.641 I slot print_timing: id 0 | task 2802671 | n_gen = 2504, tg = 27.15 t/s, tg_3s = 29.57 t/s
llama-server | 11063.58.813.115 I slot print_timing: id 0 | task 2802671 | n_gen = 2598, tg = 27.26 t/s, tg_3s = 30.70 t/s
llama-server | 11064.01.875.630 I slot print_timing: id 0 | task 2802671 | n_gen = 2676, tg = 27.21 t/s, tg_3s = 25.47 t/s
llama-server | 11064.04.960.290 I slot print_timing: id 0 | task 2802671 | n_gen = 2762, tg = 27.23 t/s, tg_3s = 27.88 t/s
llama-server | 11064.08.030.877 I slot print_timing: id 0 | task 2802671 | n_gen = 2865, tg = 27.41 t/s, tg_3s = 33.54 t/s
llama-server | 11064.11.091.453 I slot print_timing: id 0 | task 2802671 | n_gen = 2937, tg = 27.30 t/s, tg_3s = 23.52 t/s
llama-server | 11064.14.178.644 I slot print_timing: id 0 | task 2802671 | n_gen = 3019, tg = 27.28 t/s, tg_3s = 26.56 t/s
llama-server | 11064.17.254.862 I slot print_timing: id 0 | task 2802671 | n_gen = 3140, tg = 27.61 t/s, tg_3s = 39.33 t/s
llama-server | 11064.20.327.063 I slot print_timing: id 0 | task 2802671 | n_gen = 3233, tg = 27.68 t/s, tg_3s = 30.27 t/s
llama-server | 11064.23.327.764 I slot print_timing: id 0 | task 2802671 | n_gen = 3320, tg = 27.71 t/s, tg_3s = 28.99 t/s
llama-server | 11064.26.398.039 I slot print_timing: id 0 | task 2802671 | n_gen = 3394, tg = 27.62 t/s, tg_3s = 24.10 t/s
llama-server | 11064.29.471.121 I slot print_timing: id 0 | task 2802671 | n_gen = 3466, tg = 27.52 t/s, tg_3s = 23.43 t/s
llama-server | 11064.32.560.172 I slot print_timing: id 0 | task 2802671 | n_gen = 3552, tg = 27.53 t/s, tg_3s = 27.84 t/s
llama-server | 11064.35.636.137 I slot print_timing: id 0 | task 2802671 | n_gen = 3639, tg = 27.54 t/s, tg_3s = 28.28 t/s
llama-server | 11064.36.756.622 I slot print_timing: id 0 | task 2802671 | prompt eval time = 48860.09 ms / 46170 tokens ( 1.06 ms per token, 944.94 tokens per second)
llama-server | 11064.36.756.625 I slot print_timing: id 0 | task 2802671 | eval time = 133206.36 ms / 3682 tokens ( 36.19 ms per token, 27.63 tokens per second)
llama-server | 11064.36.756.625 I slot print_timing: id 0 | task 2802671 | total time = 182066.46 ms / 49852 tokens
llama-server | 11064.36.756.626 I slot print_timing: id 0 | task 2802671 | graphs reused = 2715477
llama-server | 11064.36.756.629 I slot print_timing: id 0 | task 2802671 | draft acceptance = 0.31125 ( 2241 accepted / 7200 generated), mean len = 2.56
llama-server | 11064.36.758.031 I slot release: id 0 | task 2802671 | stop processing: n_tokens = 49851, truncated = 0
llama-server | 11064.38.223.337 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 663707440766
llama-server | 11064.38.223.826 I slot launch_slot_: id 1 | task 2804137 | processing task, is_child = 0
llama-server | 11064.38.226.154 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2096.541 MiB)
llama-server | 11064.43.105.559 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1361.63 tokens per second
llama-server | 11064.44.921.539 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.82 s / 1274.97 tokens per second
llama-server | 11064.46.779.691 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.66 s / 1229.71 tokens per second
llama-server | 11064.48.667.424 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.55 s / 1198.01 tokens per second
llama-server | 11064.50.606.449 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.48 s / 1172.98 tokens per second
llama-server | 11064.52.570.041 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.43 s / 1153.39 tokens per second
llama-server | 11064.54.574.876 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.42 s / 1136.07 tokens per second
llama-server | 11064.56.615.981 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.46 s / 1120.08 tokens per second
llama-server | 11064.58.700.293 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 20480, progress = 0.44, t = 18.53 s / 1105.47 tokens per second
llama-server | 11065.00.822.133 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.64 s / 1091.52 tokens per second
llama-server | 11065.02.995.730 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 24576, progress = 0.53, t = 22.79 s / 1078.29 tokens per second
llama-server | 11065.05.192.088 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.99 s / 1065.33 tokens per second
llama-server | 11065.07.423.014 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 28672, progress = 0.62, t = 27.21 s / 1053.64 tokens per second
llama-server | 11065.09.689.256 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.47 s / 1042.35 tokens per second
llama-server | 11065.12.026.828 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 32768, progress = 0.71, t = 31.76 s / 1031.65 tokens per second
llama-server | 11065.14.364.768 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 34816, progress = 0.75, t = 34.13 s / 1020.16 tokens per second
llama-server | 11065.16.740.011 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 36864, progress = 0.80, t = 36.49 s / 1010.19 tokens per second
llama-server | 11065.19.154.430 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 38912, progress = 0.84, t = 38.89 s / 1000.47 tokens per second
llama-server | 11065.21.616.928 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 40960, progress = 0.89, t = 41.33 s / 990.95 tokens per second
llama-server | 11065.24.096.446 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 43008, progress = 0.93, t = 43.82 s / 981.40 tokens per second
llama-server | 11065.26.611.277 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 45056, progress = 0.98, t = 46.33 s / 972.54 tokens per second
llama-server | 11065.27.384.334 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 45611, progress = 0.99, t = 47.67 s / 956.84 tokens per second
llama-server | 11065.28.134.375 I slot print_timing: id 1 | task 2804137 | prompt processing, n_tokens = 46123, progress = 1.00, t = 47.95 s / 961.90 tokens per second
llama-server | 11065.32.140.482 I slot print_timing: id 1 | task 2804137 | n_gen = 102, tg = 26.85 t/s, tg_3s = 27.11 t/s
llama-server | 11065.35.143.959 I slot print_timing: id 1 | task 2804137 | n_gen = 190, tg = 27.94 t/s, tg_3s = 29.30 t/s
llama-server | 11065.38.167.898 I slot print_timing: id 1 | task 2804137 | n_gen = 261, tg = 26.56 t/s, tg_3s = 23.48 t/s
llama-server | 11065.41.179.436 I slot print_timing: id 1 | task 2804137 | n_gen = 330, tg = 25.70 t/s, tg_3s = 22.91 t/s
llama-server | 11065.44.191.713 I slot print_timing: id 1 | task 2804137 | n_gen = 421, tg = 26.56 t/s, tg_3s = 30.21 t/s
llama-server | 11065.47.220.997 I slot print_timing: id 1 | task 2804137 | n_gen = 495, tg = 26.22 t/s, tg_3s = 24.43 t/s
llama-server | 11065.50.237.489 I slot print_timing: id 1 | task 2804137 | n_gen = 575, tg = 26.26 t/s, tg_3s = 26.52 t/s
llama-server | 11065.53.258.865 I slot print_timing: id 1 | task 2804137 | n_gen = 655, tg = 26.29 t/s, tg_3s = 26.48 t/s
llama-server | 11065.56.294.461 I slot print_timing: id 1 | task 2804137 | n_gen = 724, tg = 25.90 t/s, tg_3s = 22.73 t/s
llama-server | 11065.59.320.328 I slot print_timing: id 1 | task 2804137 | n_gen = 801, tg = 25.85 t/s, tg_3s = 25.45 t/s
llama-server | 11066.02.349.603 I slot print_timing: id 1 | task 2804137 | n_gen = 879, tg = 25.85 t/s, tg_3s = 25.75 t/s
llama-server | 11066.05.378.738 I slot print_timing: id 1 | task 2804137 | n_gen = 966, tg = 26.08 t/s, tg_3s = 28.72 t/s
llama-server | 11066.08.423.047 I slot print_timing: id 1 | task 2804137 | n_gen = 1034, tg = 25.80 t/s, tg_3s = 22.34 t/s
llama-server | 11066.11.455.567 I slot print_timing: id 1 | task 2804137 | n_gen = 1103, tg = 25.58 t/s, tg_3s = 22.75 t/s
llama-server | 11066.14.490.694 I slot print_timing: id 1 | task 2804137 | n_gen = 1179, tg = 25.55 t/s, tg_3s = 25.04 t/s
llama-server | 11066.17.547.503 I slot print_timing: id 1 | task 2804137 | n_gen = 1255, tg = 25.50 t/s, tg_3s = 24.86 t/s
llama-server | 11066.20.583.755 I slot print_timing: id 1 | task 2804137 | n_gen = 1309, tg = 25.05 t/s, tg_3s = 17.79 t/s
llama-server | 11066.23.628.758 I slot print_timing: id 1 | task 2804137 | n_gen = 1410, tg = 25.50 t/s, tg_3s = 33.17 t/s
llama-server | 11066.26.668.486 I slot print_timing: id 1 | task 2804137 | n_gen = 1472, tg = 25.24 t/s, tg_3s = 20.40 t/s
llama-server | 11066.29.730.245 I slot print_timing: id 1 | task 2804137 | n_gen = 1531, tg = 24.94 t/s, tg_3s = 19.27 t/s
llama-server | 11066.32.781.736 I slot print_timing: id 1 | task 2804137 | n_gen = 1616, tg = 25.08 t/s, tg_3s = 27.86 t/s
llama-server | 11066.35.829.789 I slot print_timing: id 1 | task 2804137 | n_gen = 1704, tg = 25.25 t/s, tg_3s = 28.87 t/s
llama-server | 11066.38.894.494 I slot print_timing: id 1 | task 2804137 | n_gen = 1794, tg = 25.43 t/s, tg_3s = 29.37 t/s
llama-server | 11066.39.729.983 I slot print_timing: id 1 | task 2804137 | prompt eval time = 48820.62 ms / 46127 tokens ( 1.06 ms per token, 944.83 tokens per second)
llama-server | 11066.39.729.986 I slot print_timing: id 1 | task 2804137 | eval time = 71351.67 ms / 1829 tokens ( 39.03 ms per token, 25.62 tokens per second)
llama-server | 11066.39.729.987 I slot print_timing: id 1 | task 2804137 | total time = 120172.29 ms / 47956 tokens
llama-server | 11066.39.729.987 I slot print_timing: id 1 | task 2804137 | graphs reused = 2716245
llama-server | 11066.39.729.990 I slot print_timing: id 1 | task 2804137 | draft acceptance = 0.27139 ( 1053 accepted / 3880 generated), mean len = 2.36
llama-server | 11066.39.731.372 I slot release: id 1 | task 2804137 | stop processing: n_tokens = 47956, truncated = 0
llama-server | 11066.41.188.713 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 663892598083
llama-server | 11066.41.189.242 I slot launch_slot_: id 0 | task 2804939 | processing task, is_child = 0
llama-server | 11066.41.191.466 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2193.727 MiB)
llama-server | 11066.46.798.573 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.82 tokens per second
llama-server | 11066.48.618.223 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.82 s / 1275.98 tokens per second
llama-server | 11066.50.478.474 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.66 s / 1229.95 tokens per second
llama-server | 11066.52.367.286 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.55 s / 1198.08 tokens per second
llama-server | 11066.54.302.638 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.47 s / 1173.15 tokens per second
llama-server | 11066.56.266.614 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.43 s / 1153.60 tokens per second
llama-server | 11066.58.272.142 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.42 s / 1136.15 tokens per second
llama-server | 11067.00.313.418 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.46 s / 1120.14 tokens per second
llama-server | 11067.02.393.998 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.52 s / 1105.55 tokens per second
llama-server | 11067.04.516.299 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.63 s / 1091.78 tokens per second
llama-server | 11067.06.690.204 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 24576, progress = 0.53, t = 22.79 s / 1078.42 tokens per second
llama-server | 11067.08.887.327 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.99 s / 1065.47 tokens per second
llama-server | 11067.11.121.202 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 28672, progress = 0.62, t = 27.21 s / 1053.68 tokens per second
llama-server | 11067.13.389.038 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.47 s / 1042.36 tokens per second
llama-server | 11067.15.725.223 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 32768, progress = 0.71, t = 31.77 s / 1031.57 tokens per second
llama-server | 11067.18.060.731 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 34816, progress = 0.76, t = 34.13 s / 1020.20 tokens per second
llama-server | 11067.20.435.032 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 36864, progress = 0.80, t = 36.49 s / 1010.25 tokens per second
llama-server | 11067.22.843.042 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 38912, progress = 0.85, t = 38.89 s / 1000.53 tokens per second
llama-server | 11067.25.305.506 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 40960, progress = 0.89, t = 41.33 s / 991.13 tokens per second
llama-server | 11067.27.783.990 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 43008, progress = 0.93, t = 43.81 s / 981.59 tokens per second
llama-server | 11067.30.298.125 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 45056, progress = 0.98, t = 46.32 s / 972.77 tokens per second
llama-server | 11067.30.886.831 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 45484, progress = 0.99, t = 47.06 s / 966.54 tokens per second
llama-server | 11067.31.667.419 I slot print_timing: id 0 | task 2804939 | prompt processing, n_tokens = 45996, progress = 1.00, t = 47.78 s / 962.56 tokens per second
llama-server | 11067.35.595.749 I slot print_timing: id 0 | task 2804939 | n_gen = 101, tg = 27.14 t/s, tg_3s = 27.41 t/s
llama-server | 11067.38.606.964 I slot print_timing: id 0 | task 2804939 | n_gen = 188, tg = 27.93 t/s, tg_3s = 28.89 t/s
llama-server | 11067.41.616.888 I slot print_timing: id 0 | task 2804939 | n_gen = 278, tg = 28.54 t/s, tg_3s = 29.90 t/s
llama-server | 11067.44.648.829 I slot print_timing: id 0 | task 2804939 | n_gen = 381, tg = 29.83 t/s, tg_3s = 33.97 t/s
llama-server | 11067.47.660.195 I slot print_timing: id 0 | task 2804939 | n_gen = 455, tg = 28.83 t/s, tg_3s = 24.57 t/s
llama-server | 11067.50.666.764 I slot print_timing: id 0 | task 2804939 | n_gen = 530, tg = 28.20 t/s, tg_3s = 24.95 t/s
llama-server | 11067.53.697.869 I slot print_timing: id 0 | task 2804939 | n_gen = 614, tg = 28.14 t/s, tg_3s = 27.71 t/s
llama-server | 11067.56.717.266 I slot print_timing: id 0 | task 2804939 | n_gen = 684, tg = 27.53 t/s, tg_3s = 23.18 t/s
llama-server | 11067.59.739.785 I slot print_timing: id 0 | task 2804939 | n_gen = 775, tg = 27.81 t/s, tg_3s = 30.11 t/s
llama-server | 11068.02.780.829 I slot print_timing: id 0 | task 2804939 | n_gen = 857, tg = 27.73 t/s, tg_3s = 26.96 t/s
llama-server | 11068.05.803.107 I slot print_timing: id 0 | task 2804939 | n_gen = 931, tg = 27.44 t/s, tg_3s = 24.48 t/s
llama-server | 11068.08.832.597 I slot print_timing: id 0 | task 2804939 | n_gen = 1017, tg = 27.52 t/s, tg_3s = 28.39 t/s
llama-server | 11068.11.859.595 I slot print_timing: id 0 | task 2804939 | n_gen = 1091, tg = 27.28 t/s, tg_3s = 24.45 t/s
llama-server | 11068.14.911.557 I slot print_timing: id 0 | task 2804939 | n_gen = 1173, tg = 27.26 t/s, tg_3s = 26.87 t/s
llama-server | 11068.17.944.121 I slot print_timing: id 0 | task 2804939 | n_gen = 1242, tg = 26.96 t/s, tg_3s = 22.75 t/s
llama-server | 11068.20.977.923 I slot print_timing: id 0 | task 2804939 | n_gen = 1322, tg = 26.92 t/s, tg_3s = 26.37 t/s
llama-server | 11068.24.031.568 I slot print_timing: id 0 | task 2804939 | n_gen = 1393, tg = 26.71 t/s, tg_3s = 23.25 t/s
llama-server | 11068.27.075.081 I slot print_timing: id 0 | task 2804939 | n_gen = 1480, tg = 26.81 t/s, tg_3s = 28.59 t/s
llama-server | 11068.30.110.029 I slot print_timing: id 0 | task 2804939 | n_gen = 1556, tg = 26.72 t/s, tg_3s = 25.04 t/s
llama-server | 11068.33.162.758 I slot print_timing: id 0 | task 2804939 | n_gen = 1614, tg = 26.33 t/s, tg_3s = 19.00 t/s
llama-server | 11068.36.202.964 I slot print_timing: id 0 | task 2804939 | n_gen = 1676, tg = 26.05 t/s, tg_3s = 20.39 t/s
llama-server | 11068.39.249.856 I slot print_timing: id 0 | task 2804939 | n_gen = 1761, tg = 26.14 t/s, tg_3s = 27.90 t/s
llama-server | 11068.42.296.220 I slot print_timing: id 0 | task 2804939 | n_gen = 1854, tg = 26.33 t/s, tg_3s = 30.53 t/s
llama-server | 11068.45.362.158 I slot print_timing: id 0 | task 2804939 | n_gen = 1972, tg = 26.83 t/s, tg_3s = 38.49 t/s
llama-server | 11068.48.415.584 I slot print_timing: id 0 | task 2804939 | n_gen = 2073, tg = 27.08 t/s, tg_3s = 33.08 t/s
llama-server | 11068.51.476.779 I slot print_timing: id 0 | task 2804939 | n_gen = 2159, tg = 27.12 t/s, tg_3s = 28.09 t/s
llama-server | 11068.54.530.703 I slot print_timing: id 0 | task 2804939 | n_gen = 2256, tg = 27.29 t/s, tg_3s = 31.76 t/s
llama-server | 11068.57.580.394 I slot print_timing: id 0 | task 2804939 | n_gen = 2345, tg = 27.36 t/s, tg_3s = 29.18 t/s
llama-server | 11069.00.653.052 I slot print_timing: id 0 | task 2804939 | n_gen = 2445, tg = 27.54 t/s, tg_3s = 32.55 t/s
llama-server | 11069.03.706.086 I slot print_timing: id 0 | task 2804939 | n_gen = 2508, tg = 27.31 t/s, tg_3s = 20.64 t/s
llama-server | 11069.06.758.499 I slot print_timing: id 0 | task 2804939 | n_gen = 2586, tg = 27.25 t/s, tg_3s = 25.55 t/s
llama-server | 11069.09.827.249 I slot print_timing: id 0 | task 2804939 | n_gen = 2654, tg = 27.09 t/s, tg_3s = 22.16 t/s
llama-server | 11069.12.884.372 I slot print_timing: id 0 | task 2804939 | n_gen = 2728, tg = 27.01 t/s, tg_3s = 24.21 t/s
llama-server | 11069.15.948.146 I slot print_timing: id 0 | task 2804939 | n_gen = 2820, tg = 27.10 t/s, tg_3s = 30.03 t/s
llama-server | 11069.19.031.339 I slot print_timing: id 0 | task 2804939 | n_gen = 2908, tg = 27.14 t/s, tg_3s = 28.54 t/s
llama-server | 11069.22.092.555 I slot print_timing: id 0 | task 2804939 | n_gen = 2985, tg = 27.08 t/s, tg_3s = 25.15 t/s
llama-server | 11069.25.156.913 I slot print_timing: id 0 | task 2804939 | n_gen = 3074, tg = 27.14 t/s, tg_3s = 29.04 t/s
llama-server | 11069.28.237.163 I slot print_timing: id 0 | task 2804939 | n_gen = 3166, tg = 27.21 t/s, tg_3s = 29.87 t/s
llama-server | 11069.31.306.679 I slot print_timing: id 0 | task 2804939 | n_gen = 3247, tg = 27.19 t/s, tg_3s = 26.39 t/s
llama-server | 11069.34.376.851 I slot print_timing: id 0 | task 2804939 | n_gen = 3336, tg = 27.23 t/s, tg_3s = 28.99 t/s
llama-server | 11069.37.462.864 I slot print_timing: id 0 | task 2804939 | n_gen = 3429, tg = 27.30 t/s, tg_3s = 30.14 t/s
llama-server | 11069.40.543.108 I slot print_timing: id 0 | task 2804939 | n_gen = 3541, tg = 27.52 t/s, tg_3s = 36.36 t/s
llama-server | 11069.43.618.381 I slot print_timing: id 0 | task 2804939 | n_gen = 3642, tg = 27.64 t/s, tg_3s = 32.84 t/s
llama-server | 11069.46.710.329 I slot print_timing: id 0 | task 2804939 | n_gen = 3735, tg = 27.70 t/s, tg_3s = 30.08 t/s
llama-server | 11069.49.783.523 I slot print_timing: id 0 | task 2804939 | n_gen = 3818, tg = 27.68 t/s, tg_3s = 27.01 t/s
llama-server | 11069.52.862.548 I slot print_timing: id 0 | task 2804939 | n_gen = 3898, tg = 27.65 t/s, tg_3s = 25.98 t/s
llama-server | 11069.55.950.782 I slot print_timing: id 0 | task 2804939 | n_gen = 3977, tg = 27.60 t/s, tg_3s = 25.58 t/s
llama-server | 11069.59.026.119 I slot print_timing: id 0 | task 2804939 | n_gen = 4052, tg = 27.54 t/s, tg_3s = 24.39 t/s
llama-server | 11070.02.108.732 I slot print_timing: id 0 | task 2804939 | n_gen = 4149, tg = 27.62 t/s, tg_3s = 31.47 t/s
llama-server | 11070.05.110.926 I slot print_timing: id 0 | task 2804939 | n_gen = 4233, tg = 27.62 t/s, tg_3s = 27.98 t/s
llama-server | 11070.08.190.680 I slot print_timing: id 0 | task 2804939 | n_gen = 4311, tg = 27.58 t/s, tg_3s = 25.33 t/s
llama-server | 11070.11.273.687 I slot print_timing: id 0 | task 2804939 | n_gen = 4383, tg = 27.50 t/s, tg_3s = 23.35 t/s
llama-server | 11070.14.282.826 I slot print_timing: id 0 | task 2804939 | n_gen = 4472, tg = 27.54 t/s, tg_3s = 29.58 t/s
llama-server | 11070.17.374.752 I slot print_timing: id 0 | task 2804939 | n_gen = 4559, tg = 27.55 t/s, tg_3s = 28.14 t/s
llama-server | 11070.20.463.254 I slot print_timing: id 0 | task 2804939 | n_gen = 4636, tg = 27.50 t/s, tg_3s = 24.93 t/s
llama-server | 11070.23.478.619 I slot print_timing: id 0 | task 2804939 | n_gen = 4707, tg = 27.43 t/s, tg_3s = 23.55 t/s
llama-server | 11070.26.482.217 I slot print_timing: id 0 | task 2804939 | n_gen = 4792, tg = 27.44 t/s, tg_3s = 28.30 t/s
llama-server | 11070.29.571.385 I slot print_timing: id 0 | task 2804939 | n_gen = 4863, tg = 27.37 t/s, tg_3s = 22.98 t/s
llama-server | 11070.32.592.300 I slot print_timing: id 0 | task 2804939 | n_gen = 4954, tg = 27.41 t/s, tg_3s = 30.12 t/s
llama-server | 11070.32.686.475 I slot print_timing: id 0 | task 2804939 | prompt eval time = 48655.18 ms / 46000 tokens ( 1.06 ms per token, 945.43 tokens per second)
llama-server | 11070.32.686.478 I slot print_timing: id 0 | task 2804939 | eval time = 180775.83 ms / 4960 tokens ( 36.45 ms per token, 27.43 tokens per second)
llama-server | 11070.32.686.478 I slot print_timing: id 0 | task 2804939 | total time = 229431.01 ms / 50960 tokens
llama-server | 11070.32.686.479 I slot print_timing: id 0 | task 2804939 | graphs reused = 2718174
llama-server | 11070.32.686.482 I slot print_timing: id 0 | task 2804939 | draft acceptance = 0.30862 ( 3009 accepted / 9750 generated), mean len = 2.54
llama-server | 11070.32.687.707 I slot release: id 0 | task 2804939 | stop processing: n_tokens = 50959, truncated = 0
llama-server | 11070.34.127.318 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 664015571424
llama-server | 11070.34.127.765 I slot launch_slot_: id 1 | task 2806915 | processing task, is_child = 0
llama-server | 11070.34.130.097 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2184.318 MiB)
llama-server | 11070.39.474.466 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1361.71 tokens per second
llama-server | 11070.41.294.306 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.82 s / 1275.14 tokens per second
llama-server | 11070.43.153.683 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.66 s / 1229.34 tokens per second
llama-server | 11070.45.041.825 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.55 s / 1197.82 tokens per second
llama-server | 11070.46.967.943 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.47 s / 1174.12 tokens per second
llama-server | 11070.48.946.395 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.43 s / 1152.91 tokens per second
llama-server | 11070.50.951.608 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.43 s / 1135.71 tokens per second
llama-server | 11070.52.994.635 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.46 s / 1119.64 tokens per second
llama-server | 11070.55.074.560 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.53 s / 1105.07 tokens per second
llama-server | 11070.57.195.616 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.64 s / 1091.45 tokens per second
llama-server | 11070.59.371.306 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.80 s / 1078.08 tokens per second
llama-server | 11071.01.570.739 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 26624, progress = 0.58, t = 25.00 s / 1065.10 tokens per second
llama-server | 11071.03.806.365 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 28672, progress = 0.63, t = 27.22 s / 1053.22 tokens per second
llama-server | 11071.06.075.176 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.48 s / 1041.93 tokens per second
llama-server | 11071.08.413.500 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 32768, progress = 0.72, t = 31.78 s / 1031.15 tokens per second
llama-server | 11071.10.751.099 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 34816, progress = 0.76, t = 34.14 s / 1019.73 tokens per second
llama-server | 11071.13.127.990 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 36864, progress = 0.81, t = 36.51 s / 1009.78 tokens per second
llama-server | 11071.15.538.618 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 38912, progress = 0.85, t = 38.91 s / 1000.03 tokens per second
llama-server | 11071.18.000.112 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 40960, progress = 0.90, t = 41.35 s / 990.63 tokens per second
llama-server | 11071.20.481.940 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 43008, progress = 0.94, t = 43.84 s / 981.10 tokens per second
llama-server | 11071.23.002.178 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 45056, progress = 0.99, t = 46.34 s / 972.20 tokens per second
llama-server | 11071.23.318.300 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 45218, progress = 0.99, t = 47.09 s / 960.35 tokens per second
llama-server | 11071.24.068.081 I slot print_timing: id 1 | task 2806915 | prompt processing, n_tokens = 45730, progress = 1.00, t = 47.52 s / 962.37 tokens per second
llama-server | 11071.27.515.939 I slot print_timing: id 1 | task 2806915 | n_gen = 101, tg = 30.97 t/s, tg_3s = 31.28 t/s
llama-server | 11071.29.894.056 I slot print_timing: id 1 | task 2806915 | prompt eval time = 48358.40 ms / 45734 tokens ( 1.06 ms per token, 945.73 tokens per second)
llama-server | 11071.29.894.059 I slot print_timing: id 1 | task 2806915 | eval time = 5606.74 ms / 200 tokens ( 28.17 ms per token, 35.49 tokens per second)
llama-server | 11071.29.894.060 I slot print_timing: id 1 | task 2806915 | total time = 53965.14 ms / 45934 tokens
llama-server | 11071.29.894.061 I slot print_timing: id 1 | task 2806915 | graphs reused = 2718233
llama-server | 11071.29.894.063 I slot print_timing: id 1 | task 2806915 | draft acceptance = 0.45246 ( 138 accepted / 305 generated), mean len = 3.26
llama-server | 11071.29.895.292 I slot release: id 1 | task 2806915 | stop processing: n_tokens = 45933, truncated = 0
llama-server | 11071.31.268.056 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 664248527760
llama-server | 11071.31.268.682 I slot launch_slot_: id 0 | task 2807002 | processing task, is_child = 0
llama-server | 11071.31.270.789 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2226.511 MiB)
llama-server | 11071.36.069.780 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.01 s / 1362.18 tokens per second
llama-server | 11071.37.882.730 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.81 s / 1277.45 tokens per second
llama-server | 11071.39.733.261 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 8192, progress = 0.18, t = 6.65 s / 1231.88 tokens per second
llama-server | 11071.41.623.806 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 10240, progress = 0.22, t = 8.53 s / 1200.11 tokens per second
llama-server | 11071.43.547.026 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 12288, progress = 0.27, t = 10.45 s / 1176.32 tokens per second
llama-server | 11071.45.512.958 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 14336, progress = 0.31, t = 12.40 s / 1156.25 tokens per second
llama-server | 11071.47.515.031 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 16384, progress = 0.36, t = 14.39 s / 1138.38 tokens per second
llama-server | 11071.49.553.230 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 18432, progress = 0.40, t = 16.42 s / 1122.30 tokens per second
llama-server | 11071.51.632.778 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 20480, progress = 0.45, t = 18.49 s / 1107.57 tokens per second
llama-server | 11071.53.750.489 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 22528, progress = 0.49, t = 20.60 s / 1093.62 tokens per second
llama-server | 11071.55.922.443 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 24576, progress = 0.54, t = 22.75 s / 1080.27 tokens per second
llama-server | 11071.58.117.415 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 26624, progress = 0.58, t = 24.95 s / 1067.25 tokens per second
llama-server | 11072.00.350.147 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 28672, progress = 0.62, t = 27.17 s / 1055.34 tokens per second
llama-server | 11072.02.617.731 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 30720, progress = 0.67, t = 29.43 s / 1043.88 tokens per second
llama-server | 11072.04.955.228 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 32768, progress = 0.71, t = 31.72 s / 1033.00 tokens per second
llama-server | 11072.07.292.471 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 34816, progress = 0.76, t = 34.09 s / 1021.42 tokens per second
llama-server | 11072.09.667.776 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 36864, progress = 0.80, t = 36.45 s / 1011.37 tokens per second
llama-server | 11072.12.077.505 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 38912, progress = 0.85, t = 38.85 s / 1001.54 tokens per second
llama-server | 11072.14.538.572 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 40960, progress = 0.89, t = 41.29 s / 992.06 tokens per second
llama-server | 11072.17.021.254 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 43008, progress = 0.94, t = 43.78 s / 982.46 tokens per second
llama-server | 11072.19.537.214 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 45056, progress = 0.98, t = 46.28 s / 973.47 tokens per second
llama-server | 11072.20.057.650 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 45401, progress = 0.99, t = 47.02 s / 965.47 tokens per second
llama-server | 11072.20.830.355 I slot print_timing: id 0 | task 2807002 | prompt processing, n_tokens = 45913, progress = 1.00, t = 47.68 s / 963.01 tokens per second
llama-server | 11072.24.904.300 I slot print_timing: id 0 | task 2807002 | n_gen = 100, tg = 25.84 t/s, tg_3s = 26.10 t/s
llama-server | 11072.27.920.064 I slot print_timing: id 0 | task 2807002 | n_gen = 187, tg = 27.16 t/s, tg_3s = 28.85 t/s
llama-server | 11072.31.006.973 I slot print_timing: id 0 | task 2807002 | n_gen = 253, tg = 25.37 t/s, tg_3s = 21.38 t/s
llama-server | 11072.34.012.118 I slot print_timing: id 0 | task 2807002 | n_gen = 346, tg = 26.66 t/s, tg_3s = 30.95 t/s
llama-server | 11072.37.036.500 I slot print_timing: id 0 | task 2807002 | n_gen = 434, tg = 27.12 t/s, tg_3s = 29.10 t/s
llama-server | 11072.40.045.059 I slot print_timing: id 0 | task 2807002 | n_gen = 516, tg = 27.14 t/s, tg_3s = 27.26 t/s
llama-server | 11072.43.053.372 I slot print_timing: id 0 | task 2807002 | n_gen = 587, tg = 26.66 t/s, tg_3s = 23.60 t/s
llama-server | 11072.46.068.958 I slot print_timing: id 0 | task 2807002 | n_gen = 674, tg = 26.92 t/s, tg_3s = 28.85 t/s
llama-server | 11072.49.101.866 I slot print_timing: id 0 | task 2807002 | n_gen = 752, tg = 26.79 t/s, tg_3s = 25.72 t/s
llama-server | 11072.52.123.834 I slot print_timing: id 0 | task 2807002 | n_gen = 864, tg = 27.79 t/s, tg_3s = 37.06 t/s
llama-server | 11072.55.159.798 I slot print_timing: id 0 | task 2807002 | n_gen = 935, tg = 27.40 t/s, tg_3s = 23.39 t/s
llama-server | 11072.58.185.699 I slot print_timing: id 0 | task 2807002 | n_gen = 1025, tg = 27.59 t/s, tg_3s = 29.74 t/s
llama-server | 11073.01.210.230 I slot print_timing: id 0 | task 2807002 | n_gen = 1128, tg = 28.08 t/s, tg_3s = 34.05 t/s
llama-server | 11073.04.252.717 I slot print_timing: id 0 | task 2807002 | n_gen = 1213, tg = 28.07 t/s, tg_3s = 27.94 t/s
llama-server | 11073.07.281.825 I slot print_timing: id 0 | task 2807002 | n_gen = 1291, tg = 27.92 t/s, tg_3s = 25.75 t/s
llama-server | 11073.10.316.827 I slot print_timing: id 0 | task 2807002 | n_gen = 1364, tg = 27.68 t/s, tg_3s = 24.05 t/s
llama-server | 11073.13.352.761 I slot print_timing: id 0 | task 2807002 | n_gen = 1432, tg = 27.37 t/s, tg_3s = 22.40 t/s
llama-server | 11073.16.405.592 I slot print_timing: id 0 | task 2807002 | n_gen = 1507, tg = 27.22 t/s, tg_3s = 24.57 t/s
llama-server | 11073.19.445.869 I slot print_timing: id 0 | task 2807002 | n_gen = 1580, tg = 27.05 t/s, tg_3s = 24.01 t/s
llama-server | 11073.22.481.323 I slot print_timing: id 0 | task 2807002 | n_gen = 1648, tg = 26.82 t/s, tg_3s = 22.40 t/s
llama-server | 11073.25.532.931 I slot print_timing: id 0 | task 2807002 | n_gen = 1723, tg = 26.71 t/s, tg_3s = 24.58 t/s
llama-server | 11073.28.575.056 I slot print_timing: id 0 | task 2807002 | n_gen = 1807, tg = 26.75 t/s, tg_3s = 27.61 t/s
llama-server | 11073.31.618.807 I slot print_timing: id 0 | task 2807002 | n_gen = 1884, tg = 26.69 t/s, tg_3s = 25.30 t/s
llama-server | 11073.34.676.117 I slot print_timing: id 0 | task 2807002 | n_gen = 1969, tg = 26.74 t/s, tg_3s = 27.80 t/s
llama-server | 11073.37.719.242 I slot print_timing: id 0 | task 2807002 | n_gen = 2046, tg = 26.68 t/s, tg_3s = 25.30 t/s
llama-server | 11073.40.764.989 I slot print_timing: id 0 | task 2807002 | n_gen = 2131, tg = 26.73 t/s, tg_3s = 27.91 t/s
llama-server | 11073.43.825.635 I slot print_timing: id 0 | task 2807002 | n_gen = 2239, tg = 27.04 t/s, tg_3s = 35.29 t/s
llama-server | 11073.46.872.376 I slot print_timing: id 0 | task 2807002 | n_gen = 2323, tg = 27.06 t/s, tg_3s = 27.57 t/s
llama-server | 11073.49.922.878 I slot print_timing: id 0 | task 2807002 | n_gen = 2408, tg = 27.09 t/s, tg_3s = 27.86 t/s
llama-server | 11073.52.985.037 I slot print_timing: id 0 | task 2807002 | n_gen = 2479, tg = 26.96 t/s, tg_3s = 23.19 t/s
llama-server | 11073.56.034.264 I slot print_timing: id 0 | task 2807002 | n_gen = 2548, tg = 26.82 t/s, tg_3s = 22.63 t/s
llama-server | 11073.59.086.792 I slot print_timing: id 0 | task 2807002 | n_gen = 2636, tg = 26.88 t/s, tg_3s = 28.83 t/s
llama-server | 11074.02.140.624 I slot print_timing: id 0 | task 2807002 | n_gen = 2706, tg = 26.76 t/s, tg_3s = 22.92 t/s
llama-server | 11074.05.215.331 I slot print_timing: id 0 | task 2807002 | n_gen = 2791, tg = 26.79 t/s, tg_3s = 27.64 t/s
llama-server | 11074.08.267.630 I slot print_timing: id 0 | task 2807002 | n_gen = 2852, tg = 26.60 t/s, tg_3s = 19.98 t/s
llama-server | 11074.11.329.461 I slot print_timing: id 0 | task 2807002 | n_gen = 2936, tg = 26.62 t/s, tg_3s = 27.43 t/s
llama-server | 11074.14.406.469 I slot print_timing: id 0 | task 2807002 | n_gen = 3024, tg = 26.67 t/s, tg_3s = 28.60 t/s
llama-server | 11074.17.466.688 I slot print_timing: id 0 | task 2807002 | n_gen = 3107, tg = 26.69 t/s, tg_3s = 27.12 t/s
llama-server | 11074.20.536.520 I slot print_timing: id 0 | task 2807002 | n_gen = 3225, tg = 26.99 t/s, tg_3s = 38.44 t/s
llama-server | 11074.23.623.523 I slot print_timing: id 0 | task 2807002 | n_gen = 3307, tg = 26.98 t/s, tg_3s = 26.56 t/s
llama-server | 11074.26.689.524 I slot print_timing: id 0 | task 2807002 | n_gen = 3378, tg = 26.88 t/s, tg_3s = 23.16 t/s
llama-server | 11074.29.757.799 I slot print_timing: id 0 | task 2807002 | n_gen = 3475, tg = 27.00 t/s, tg_3s = 31.61 t/s
llama-server | 11074.32.846.855 I slot print_timing: id 0 | task 2807002 | n_gen = 3562, tg = 27.02 t/s, tg_3s = 28.16 t/s
llama-server | 11074.35.918.182 I slot print_timing: id 0 | task 2807002 | n_gen = 3659, tg = 27.13 t/s, tg_3s = 31.58 t/s
llama-server | 11074.39.006.990 I slot print_timing: id 0 | task 2807002 | n_gen = 3755, tg = 27.22 t/s, tg_3s = 31.08 t/s
llama-server | 11074.42.082.797 I slot print_timing: id 0 | task 2807002 | n_gen = 3832, tg = 27.17 t/s, tg_3s = 25.03 t/s
llama-server | 11074.45.168.221 I slot print_timing: id 0 | task 2807002 | n_gen = 3941, tg = 27.34 t/s, tg_3s = 35.33 t/s
llama-server | 11074.48.171.322 I slot print_timing: id 0 | task 2807002 | n_gen = 4034, tg = 27.42 t/s, tg_3s = 30.97 t/s
llama-server | 11074.51.251.691 I slot print_timing: id 0 | task 2807002 | n_gen = 4110, tg = 27.36 t/s, tg_3s = 24.67 t/s
llama-server | 11074.54.332.964 I slot print_timing: id 0 | task 2807002 | n_gen = 4179, tg = 27.26 t/s, tg_3s = 22.39 t/s
llama-server | 11074.57.415.938 I slot print_timing: id 0 | task 2807002 | n_gen = 4250, tg = 27.18 t/s, tg_3s = 23.03 t/s
llama-server | 11075.00.246.534 I slot print_timing: id 0 | task 2807002 | prompt eval time = 48545.34 ms / 45917 tokens ( 1.06 ms per token, 945.86 tokens per second)
llama-server | 11075.00.246.538 I slot print_timing: id 0 | task 2807002 | eval time = 159173.80 ms / 4357 tokens ( 36.54 ms per token, 27.37 tokens per second)
llama-server | 11075.00.246.538 I slot print_timing: id 0 | task 2807002 | total time = 207719.14 ms / 50274 tokens
llama-server | 11075.00.246.539 I slot print_timing: id 0 | task 2807002 | graphs reused = 2719937
llama-server | 11075.00.246.542 I slot print_timing: id 0 | task 2807002 | draft acceptance = 0.30604 ( 2635 accepted / 8610 generated), mean len = 2.53
llama-server | 11075.00.247.947 I slot release: id 0 | task 2807002 | stop processing: n_tokens = 50274, truncated = 0
llama-server | 11075.01.713.325 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 664305735344
llama-server | 11075.01.713.886 I slot launch_slot_: id 1 | task 2808750 | processing task, is_child = 0
llama-server | 11075.01.716.232 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2163.504 MiB)
llama-server | 11075.07.199.263 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.01 s / 1362.77 tokens per second
llama-server | 11075.09.015.315 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1276.54 tokens per second
llama-server | 11075.10.872.622 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1230.95 tokens per second
llama-server | 11075.12.774.749 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.54 s / 1199.10 tokens per second
llama-server | 11075.14.700.917 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.47 s / 1173.41 tokens per second
llama-server | 11075.16.676.947 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.43 s / 1152.93 tokens per second
llama-server | 11075.18.683.118 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.43 s / 1135.38 tokens per second
llama-server | 11075.20.725.017 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.47 s / 1119.41 tokens per second
llama-server | 11075.22.805.401 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.54 s / 1104.90 tokens per second
llama-server | 11075.24.929.491 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.64 s / 1091.22 tokens per second
llama-server | 11075.27.103.969 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.80 s / 1077.80 tokens per second
llama-server | 11075.29.302.177 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 26624, progress = 0.68, t = 25.00 s / 1064.90 tokens per second
llama-server | 11075.31.539.172 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 28672, progress = 0.74, t = 27.23 s / 1053.11 tokens per second
llama-server | 11075.33.812.437 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 30720, progress = 0.79, t = 29.49 s / 1041.68 tokens per second
llama-server | 11075.36.152.613 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.79 s / 1030.77 tokens per second
llama-server | 11075.38.490.157 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 34816, progress = 0.89, t = 34.15 s / 1019.39 tokens per second
llama-server | 11075.40.866.264 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 36864, progress = 0.95, t = 36.52 s / 1009.45 tokens per second
llama-server | 11075.42.749.961 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 38407, progress = 0.99, t = 38.92 s / 986.87 tokens per second
llama-server | 11075.43.489.238 I slot print_timing: id 1 | task 2808750 | prompt processing, n_tokens = 38919, progress = 1.00, t = 39.23 s / 991.95 tokens per second
llama-server | 11075.47.739.078 I slot print_timing: id 1 | task 2808750 | n_gen = 103, tg = 25.14 t/s, tg_3s = 25.39 t/s
llama-server | 11075.50.803.242 I slot print_timing: id 1 | task 2808750 | n_gen = 172, tg = 24.01 t/s, tg_3s = 22.52 t/s
llama-server | 11075.53.867.244 I slot print_timing: id 1 | task 2808750 | n_gen = 245, tg = 23.96 t/s, tg_3s = 23.83 t/s
llama-server | 11075.56.788.383 I slot print_timing: id 1 | task 2808750 | prompt eval time = 40026.05 ms / 38923 tokens ( 1.03 ms per token, 972.44 tokens per second)
llama-server | 11075.56.788.387 I slot print_timing: id 1 | task 2808750 | eval time = 13105.77 ms / 354 tokens ( 37.13 ms per token, 26.93 tokens per second)
llama-server | 11075.56.788.387 I slot print_timing: id 1 | task 2808750 | total time = 53131.83 ms / 39277 tokens
llama-server | 11075.56.788.388 I slot print_timing: id 1 | task 2808750 | graphs reused = 2720084
llama-server | 11075.56.788.392 I slot print_timing: id 1 | task 2808750 | draft acceptance = 0.27517 ( 205 accepted / 745 generated), mean len = 2.38
llama-server | 11075.56.789.486 I slot release: id 1 | task 2808750 | stop processing: n_tokens = 39277, truncated = 0
llama-server | 11075.58.066.220 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 664516087999
llama-server | 11075.58.066.905 I slot launch_slot_: id 0 | task 2808921 | processing task, is_child = 0
llama-server | 11075.58.068.881 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2263.351 MiB)
llama-server | 11076.03.475.009 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.00 s / 1363.26 tokens per second
llama-server | 11076.05.289.162 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1277.52 tokens per second
llama-server | 11076.07.144.266 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1231.86 tokens per second
llama-server | 11076.09.028.508 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.53 s / 1200.25 tokens per second
llama-server | 11076.10.960.129 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.45 s / 1175.45 tokens per second
llama-server | 11076.12.927.274 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.41 s / 1155.65 tokens per second
llama-server | 11076.14.929.292 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.40 s / 1137.70 tokens per second
llama-server | 11076.16.968.814 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.43 s / 1121.60 tokens per second
llama-server | 11076.19.047.288 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.50 s / 1107.00 tokens per second
llama-server | 11076.21.165.640 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.61 s / 1093.18 tokens per second
llama-server | 11076.23.337.867 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.76 s / 1079.86 tokens per second
llama-server | 11076.25.534.045 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 26624, progress = 0.69, t = 24.96 s / 1066.80 tokens per second
llama-server | 11076.27.766.844 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 28672, progress = 0.74, t = 27.18 s / 1054.89 tokens per second
llama-server | 11076.30.034.610 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.44 s / 1043.55 tokens per second
llama-server | 11076.32.371.142 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 32768, progress = 0.85, t = 31.73 s / 1032.67 tokens per second
llama-server | 11076.34.708.595 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 34816, progress = 0.90, t = 34.09 s / 1021.15 tokens per second
llama-server | 11076.37.083.938 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 36864, progress = 0.96, t = 36.46 s / 1011.06 tokens per second
llama-server | 11076.38.482.072 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 38013, progress = 0.99, t = 38.29 s / 992.67 tokens per second
llama-server | 11076.39.201.593 I slot print_timing: id 0 | task 2808921 | prompt processing, n_tokens = 38525, progress = 1.00, t = 38.68 s / 996.10 tokens per second
llama-server | 11076.42.565.166 I slot print_timing: id 0 | task 2808921 | n_gen = 101, tg = 31.55 t/s, tg_3s = 31.86 t/s
llama-server | 11076.45.645.178 I slot print_timing: id 0 | task 2808921 | n_gen = 197, tg = 31.36 t/s, tg_3s = 31.17 t/s
llama-server | 11076.48.712.193 I slot print_timing: id 0 | task 2808921 | n_gen = 308, tg = 32.95 t/s, tg_3s = 36.19 t/s
llama-server | 11076.51.798.729 I slot print_timing: id 0 | task 2808921 | n_gen = 417, tg = 33.54 t/s, tg_3s = 35.31 t/s
llama-server | 11076.54.870.625 I slot print_timing: id 0 | task 2808921 | n_gen = 517, tg = 33.34 t/s, tg_3s = 32.55 t/s
llama-server | 11076.57.949.850 I slot print_timing: id 0 | task 2808921 | n_gen = 612, tg = 32.93 t/s, tg_3s = 30.85 t/s
llama-server | 11077.00.955.808 I slot print_timing: id 0 | task 2808921 | n_gen = 714, tg = 33.07 t/s, tg_3s = 33.93 t/s
llama-server | 11077.04.037.530 I slot print_timing: id 0 | task 2808921 | n_gen = 808, tg = 32.75 t/s, tg_3s = 30.50 t/s
llama-server | 11077.07.050.563 I slot print_timing: id 0 | task 2808921 | n_gen = 912, tg = 32.94 t/s, tg_3s = 34.52 t/s
llama-server | 11077.10.052.073 I slot print_timing: id 0 | task 2808921 | n_gen = 1009, tg = 32.88 t/s, tg_3s = 32.32 t/s
llama-server | 11077.13.138.108 I slot print_timing: id 0 | task 2808921 | n_gen = 1105, tg = 32.72 t/s, tg_3s = 31.11 t/s
llama-server | 11077.14.286.434 I slot print_timing: id 0 | task 2808921 | prompt eval time = 39461.19 ms / 38529 tokens ( 1.02 ms per token, 976.38 tokens per second)
llama-server | 11077.14.286.437 I slot print_timing: id 0 | task 2808921 | eval time = 34891.21 ms / 1147 tokens ( 30.45 ms per token, 32.84 tokens per second)
llama-server | 11077.14.286.438 I slot print_timing: id 0 | task 2808921 | total time = 74352.40 ms / 39676 tokens
llama-server | 11077.14.286.438 I slot print_timing: id 0 | task 2808921 | graphs reused = 2720475
llama-server | 11077.14.286.441 I slot print_timing: id 0 | task 2808921 | draft acceptance = 0.37929 ( 751 accepted / 1980 generated), mean len = 2.90
llama-server | 11077.14.287.546 I slot release: id 0 | task 2808921 | stop processing: n_tokens = 39676, truncated = 0
llama-server | 11077.15.667.136 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 664572629538
llama-server | 11077.15.667.635 I slot launch_slot_: id 1 | task 2809339 | processing task, is_child = 0
llama-server | 11077.20.607.183 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.01 s / 1361.48 tokens per second
llama-server | 11077.22.424.422 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.82 s / 1275.97 tokens per second
llama-server | 11077.24.278.902 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.66 s / 1230.18 tokens per second
llama-server | 11077.26.166.242 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.54 s / 1199.12 tokens per second
llama-server | 11077.28.110.167 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.47 s / 1173.76 tokens per second
llama-server | 11077.30.078.315 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.43 s / 1153.35 tokens per second
llama-server | 11077.32.103.847 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.43 s / 1135.78 tokens per second
llama-server | 11077.34.154.088 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.48 s / 1118.37 tokens per second
llama-server | 11077.36.234.276 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.56 s / 1103.48 tokens per second
llama-server | 11077.38.355.595 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.67 s / 1089.95 tokens per second
llama-server | 11077.40.529.394 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.82 s / 1076.85 tokens per second
llama-server | 11077.42.727.909 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 26624, progress = 0.69, t = 25.02 s / 1064.04 tokens per second
llama-server | 11077.44.963.131 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 28672, progress = 0.74, t = 27.25 s / 1052.32 tokens per second
llama-server | 11077.47.231.808 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 30720, progress = 0.79, t = 29.51 s / 1041.10 tokens per second
llama-server | 11077.49.571.336 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.80 s / 1030.36 tokens per second
llama-server | 11077.51.906.811 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 34816, progress = 0.90, t = 34.17 s / 1019.01 tokens per second
llama-server | 11077.54.281.946 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 36864, progress = 0.95, t = 36.53 s / 1009.13 tokens per second
llama-server | 11077.55.978.411 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 38271, progress = 0.99, t = 38.37 s / 997.54 tokens per second
llama-server | 11077.56.708.186 I slot print_timing: id 1 | task 2809339 | prompt processing, n_tokens = 38783, progress = 1.00, t = 39.04 s / 993.35 tokens per second
llama-server | 11077.59.994.489 I slot print_timing: id 1 | task 2809339 | n_gen = 101, tg = 32.33 t/s, tg_3s = 32.65 t/s
llama-server | 11078.03.078.577 I slot print_timing: id 1 | task 2809339 | n_gen = 198, tg = 31.89 t/s, tg_3s = 31.45 t/s
llama-server | 11078.06.148.202 I slot print_timing: id 1 | task 2809339 | n_gen = 302, tg = 32.55 t/s, tg_3s = 33.88 t/s
llama-server | 11078.09.155.452 I slot print_timing: id 1 | task 2809339 | n_gen = 425, tg = 34.60 t/s, tg_3s = 40.90 t/s
llama-server | 11078.12.232.168 I slot print_timing: id 1 | task 2809339 | n_gen = 509, tg = 33.14 t/s, tg_3s = 27.30 t/s
llama-server | 11078.15.313.943 I slot print_timing: id 1 | task 2809339 | n_gen = 620, tg = 33.62 t/s, tg_3s = 36.02 t/s
llama-server | 11078.18.326.984 I slot print_timing: id 1 | task 2809339 | n_gen = 701, tg = 32.67 t/s, tg_3s = 26.88 t/s
llama-server | 11078.21.327.883 I slot print_timing: id 1 | task 2809339 | n_gen = 798, tg = 32.63 t/s, tg_3s = 32.32 t/s
llama-server | 11078.24.430.185 I slot print_timing: id 1 | task 2809339 | n_gen = 903, tg = 32.77 t/s, tg_3s = 33.85 t/s
llama-server | 11078.27.435.216 I slot print_timing: id 1 | task 2809339 | n_gen = 1008, tg = 32.98 t/s, tg_3s = 34.94 t/s
llama-server | 11078.30.436.401 I slot print_timing: id 1 | task 2809339 | n_gen = 1088, tg = 32.41 t/s, tg_3s = 26.66 t/s
llama-server | 11078.33.460.002 I slot print_timing: id 1 | task 2809339 | n_gen = 1183, tg = 32.33 t/s, tg_3s = 31.42 t/s
llama-server | 11078.36.475.749 I slot print_timing: id 1 | task 2809339 | n_gen = 1306, tg = 32.98 t/s, tg_3s = 40.79 t/s
llama-server | 11078.39.503.143 I slot print_timing: id 1 | task 2809339 | n_gen = 1413, tg = 33.14 t/s, tg_3s = 35.34 t/s
llama-server | 11078.42.518.170 I slot print_timing: id 1 | task 2809339 | n_gen = 1520, tg = 33.30 t/s, tg_3s = 35.49 t/s
llama-server | 11078.45.537.275 I slot print_timing: id 1 | task 2809339 | n_gen = 1638, tg = 33.66 t/s, tg_3s = 39.08 t/s
llama-server | 11078.48.566.514 I slot print_timing: id 1 | task 2809339 | n_gen = 1736, tg = 33.58 t/s, tg_3s = 32.35 t/s
llama-server | 11078.51.583.450 I slot print_timing: id 1 | task 2809339 | n_gen = 1827, tg = 33.39 t/s, tg_3s = 30.16 t/s
llama-server | 11078.54.615.602 I slot print_timing: id 1 | task 2809339 | n_gen = 1923, tg = 33.30 t/s, tg_3s = 31.66 t/s
llama-server | 11078.56.577.823 I slot print_timing: id 1 | task 2809339 | prompt eval time = 39839.17 ms / 38787 tokens ( 1.03 ms per token, 973.59 tokens per second)
llama-server | 11078.56.577.827 I slot print_timing: id 1 | task 2809339 | eval time = 59676.54 ms / 2009 tokens ( 29.72 ms per token, 33.65 tokens per second)
llama-server | 11078.56.577.827 I slot print_timing: id 1 | task 2809339 | total time = 99515.71 ms / 40796 tokens
llama-server | 11078.56.577.828 I slot print_timing: id 1 | task 2809339 | graphs reused = 2721140
llama-server | 11078.56.577.831 I slot print_timing: id 1 | task 2809339 | draft acceptance = 0.39614 ( 1335 accepted / 3370 generated), mean len = 2.98
llama-server | 11078.56.579.145 I slot release: id 1 | task 2809339 | stop processing: n_tokens = 40796, truncated = 0
llama-server | 11078.58.073.769 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 664650127598
llama-server | 11078.58.074.303 I slot launch_slot_: id 0 | task 2810035 | processing task, is_child = 0
llama-server | 11078.58.076.339 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2096.242 MiB)
llama-server | 11079.02.785.549 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.00 s / 1363.36 tokens per second
llama-server | 11079.04.602.553 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1276.68 tokens per second
llama-server | 11079.06.456.788 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.66 s / 1230.79 tokens per second
llama-server | 11079.08.350.535 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.54 s / 1199.46 tokens per second
llama-server | 11079.10.291.163 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.47 s / 1173.17 tokens per second
llama-server | 11079.12.263.671 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.43 s / 1153.47 tokens per second
llama-server | 11079.14.272.647 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.43 s / 1135.28 tokens per second
llama-server | 11079.16.315.188 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.47 s / 1119.20 tokens per second
llama-server | 11079.18.397.418 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.54 s / 1104.64 tokens per second
llama-server | 11079.20.520.527 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.65 s / 1090.89 tokens per second
llama-server | 11079.22.704.242 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.81 s / 1077.61 tokens per second
llama-server | 11079.24.909.239 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 26624, progress = 0.69, t = 25.02 s / 1064.15 tokens per second
llama-server | 11079.27.144.707 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 28672, progress = 0.74, t = 27.25 s / 1052.33 tokens per second
llama-server | 11079.29.412.770 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 30720, progress = 0.79, t = 29.51 s / 1041.10 tokens per second
llama-server | 11079.31.751.342 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 32768, progress = 0.85, t = 31.80 s / 1030.40 tokens per second
llama-server | 11079.34.089.776 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 34816, progress = 0.90, t = 34.17 s / 1019.03 tokens per second
llama-server | 11079.36.466.380 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 36864, progress = 0.95, t = 36.53 s / 1009.10 tokens per second
llama-server | 11079.38.124.385 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 38221, progress = 0.99, t = 38.37 s / 996.20 tokens per second
llama-server | 11079.38.858.016 I slot print_timing: id 0 | task 2810035 | prompt processing, n_tokens = 38733, progress = 1.00, t = 39.01 s / 992.90 tokens per second
llama-server | 11079.41.840.381 I slot print_timing: id 0 | task 2810035 | prompt eval time = 39856.54 ms / 38737 tokens ( 1.03 ms per token, 971.91 tokens per second)
llama-server | 11079.41.840.384 I slot print_timing: id 0 | task 2810035 | eval time = 2740.16 ms / 99 tokens ( 27.96 ms per token, 35.76 tokens per second)
llama-server | 11079.41.840.385 I slot print_timing: id 0 | task 2810035 | total time = 42596.70 ms / 38836 tokens
llama-server | 11079.41.840.386 I slot print_timing: id 0 | task 2810035 | graphs reused = 2721170
llama-server | 11079.41.840.390 I slot print_timing: id 0 | task 2810035 | draft acceptance = 0.43226 ( 67 accepted / 155 generated), mean len = 3.16
llama-server | 11079.41.841.534 I slot release: id 0 | task 2810035 | stop processing: n_tokens = 38835, truncated = 0
llama-server | 11079.43.135.123 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 664752419197
llama-server | 11079.43.135.757 I slot launch_slot_: id 1 | task 2810088 | processing task, is_child = 0
llama-server | 11079.43.137.619 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2240.575 MiB)
llama-server | 11079.50.264.208 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1280.52 tokens per second
llama-server | 11079.52.117.534 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.64 s / 1234.14 tokens per second
llama-server | 11079.54.003.877 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.52 s / 1202.27 tokens per second
llama-server | 11079.55.925.713 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.43 s / 1177.80 tokens per second
llama-server | 11079.57.899.964 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.40 s / 1156.37 tokens per second
llama-server | 11079.59.900.757 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.39 s / 1138.96 tokens per second
llama-server | 11080.01.940.554 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.42 s / 1122.73 tokens per second
llama-server | 11080.04.016.728 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.48 s / 1107.93 tokens per second
llama-server | 11080.06.134.161 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 22528, progress = 0.57, t = 20.59 s / 1094.09 tokens per second
llama-server | 11080.08.304.501 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.74 s / 1080.78 tokens per second
llama-server | 11080.10.498.394 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 26624, progress = 0.68, t = 24.93 s / 1067.74 tokens per second
llama-server | 11080.12.731.007 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.16 s / 1055.81 tokens per second
llama-server | 11080.15.003.726 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 30720, progress = 0.78, t = 29.42 s / 1044.33 tokens per second
llama-server | 11080.17.340.943 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.72 s / 1033.20 tokens per second
llama-server | 11080.19.677.894 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 34816, progress = 0.89, t = 34.08 s / 1021.64 tokens per second
llama-server | 11080.22.052.581 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 36864, progress = 0.94, t = 36.44 s / 1011.58 tokens per second
llama-server | 11080.24.316.350 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 38727, progress = 0.99, t = 38.84 s / 997.01 tokens per second
llama-server | 11080.25.094.095 I slot print_timing: id 1 | task 2810088 | prompt processing, n_tokens = 39239, progress = 1.00, t = 39.58 s / 991.51 tokens per second
llama-server | 11080.28.849.208 I slot print_timing: id 1 | task 2810088 | n_gen = 101, tg = 28.33 t/s, tg_3s = 28.61 t/s
llama-server | 11080.31.912.052 I slot print_timing: id 1 | task 2810088 | n_gen = 178, tg = 26.85 t/s, tg_3s = 25.14 t/s
llama-server | 11080.34.916.838 I slot print_timing: id 1 | task 2810088 | n_gen = 258, tg = 26.78 t/s, tg_3s = 26.62 t/s
llama-server | 11080.37.998.215 I slot print_timing: id 1 | task 2810088 | n_gen = 368, tg = 28.94 t/s, tg_3s = 35.70 t/s
llama-server | 11080.39.407.728 I slot print_timing: id 1 | task 2810088 | prompt eval time = 40399.14 ms / 39243 tokens ( 1.03 ms per token, 971.38 tokens per second)
llama-server | 11080.39.407.731 I slot print_timing: id 1 | task 2810088 | eval time = 14088.81 ms / 428 tokens ( 32.99 ms per token, 30.31 tokens per second)
llama-server | 11080.39.407.732 I slot print_timing: id 1 | task 2810088 | total time = 54487.95 ms / 39671 tokens
llama-server | 11080.39.407.733 I slot print_timing: id 1 | task 2810088 | graphs reused = 2721328
llama-server | 11080.39.407.736 I slot print_timing: id 1 | task 2810088 | draft acceptance = 0.33375 ( 267 accepted / 800 generated), mean len = 2.67
llama-server | 11080.39.408.949 I slot release: id 1 | task 2810088 | stop processing: n_tokens = 39670, truncated = 0
llama-server | 11080.40.651.985 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 664797681586
llama-server | 11080.40.652.602 I slot launch_slot_: id 0 | task 2810270 | processing task, is_child = 0
llama-server | 11080.40.654.574 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1874.937 MiB)
llama-server | 11080.47.802.562 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1278.28 tokens per second
llama-server | 11080.49.653.122 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1232.62 tokens per second
llama-server | 11080.51.543.825 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.52 s / 1201.29 tokens per second
llama-server | 11080.53.468.290 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.44 s / 1176.66 tokens per second
llama-server | 11080.55.441.139 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.41 s / 1155.48 tokens per second
llama-server | 11080.57.445.550 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.40 s / 1137.86 tokens per second
llama-server | 11080.59.484.778 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.43 s / 1121.74 tokens per second
llama-server | 11081.01.564.752 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.50 s / 1107.03 tokens per second
llama-server | 11081.03.683.931 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.61 s / 1093.16 tokens per second
llama-server | 11081.05.857.887 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.76 s / 1079.79 tokens per second
llama-server | 11081.08.054.751 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 26624, progress = 0.69, t = 24.96 s / 1066.67 tokens per second
llama-server | 11081.10.285.772 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 28672, progress = 0.74, t = 27.18 s / 1054.82 tokens per second
llama-server | 11081.12.552.301 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 30720, progress = 0.79, t = 29.44 s / 1043.51 tokens per second
llama-server | 11081.14.888.369 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.73 s / 1032.67 tokens per second
llama-server | 11081.17.230.084 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 34816, progress = 0.90, t = 34.09 s / 1021.16 tokens per second
llama-server | 11081.19.605.982 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 36864, progress = 0.95, t = 36.46 s / 1010.94 tokens per second
llama-server | 11081.21.354.987 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 38325, progress = 0.99, t = 38.30 s / 1000.66 tokens per second
llama-server | 11081.22.114.276 I slot print_timing: id 0 | task 2810270 | prompt processing, n_tokens = 38837, progress = 1.00, t = 39.06 s / 994.32 tokens per second
llama-server | 11081.25.677.370 I slot print_timing: id 0 | task 2810270 | n_gen = 100, tg = 29.36 t/s, tg_3s = 29.66 t/s
llama-server | 11081.28.746.630 I slot print_timing: id 0 | task 2810270 | n_gen = 170, tg = 26.24 t/s, tg_3s = 22.81 t/s
llama-server | 11081.31.814.205 I slot print_timing: id 0 | task 2810270 | n_gen = 258, tg = 27.03 t/s, tg_3s = 28.69 t/s
llama-server | 11081.34.901.134 I slot print_timing: id 0 | task 2810270 | n_gen = 348, tg = 27.55 t/s, tg_3s = 29.16 t/s
llama-server | 11081.37.975.402 I slot print_timing: id 0 | task 2810270 | n_gen = 438, tg = 27.89 t/s, tg_3s = 29.28 t/s
llama-server | 11081.41.050.223 I slot print_timing: id 0 | task 2810270 | n_gen = 493, tg = 26.25 t/s, tg_3s = 17.89 t/s
llama-server | 11081.43.800.745 I slot print_timing: id 0 | task 2810270 | prompt eval time = 39855.03 ms / 38841 tokens ( 1.03 ms per token, 974.56 tokens per second)
llama-server | 11081.43.800.748 I slot print_timing: id 0 | task 2810270 | eval time = 21495.03 ms / 609 tokens ( 35.35 ms per token, 28.29 tokens per second)
llama-server | 11081.43.800.749 I slot print_timing: id 0 | task 2810270 | total time = 61350.07 ms / 39450 tokens
llama-server | 11081.43.800.749 I slot print_timing: id 0 | task 2810270 | graphs reused = 2721568
llama-server | 11081.43.800.752 I slot print_timing: id 0 | task 2810270 | draft acceptance = 0.29918 ( 365 accepted / 1220 generated), mean len = 2.50
llama-server | 11081.43.801.874 I slot release: id 0 | task 2810270 | stop processing: n_tokens = 39450, truncated = 0
llama-server | 11081.44.993.467 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 664855249005
llama-server | 11081.44.994.105 I slot launch_slot_: id 1 | task 2810536 | processing task, is_child = 0
llama-server | 11081.44.996.055 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1888.203 MiB)
llama-server | 11081.50.076.602 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.00 s / 1365.26 tokens per second
llama-server | 11081.51.892.724 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1278.13 tokens per second
llama-server | 11081.53.747.726 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1231.89 tokens per second
llama-server | 11081.55.636.990 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.53 s / 1200.21 tokens per second
llama-server | 11081.57.571.090 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.46 s / 1174.96 tokens per second
llama-server | 11081.59.540.336 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.41 s / 1154.76 tokens per second
llama-server | 11082.01.545.191 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.41 s / 1137.03 tokens per second
llama-server | 11082.03.585.737 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.44 s / 1120.93 tokens per second
llama-server | 11082.05.666.551 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.51 s / 1106.27 tokens per second
llama-server | 11082.07.786.216 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.62 s / 1092.43 tokens per second
llama-server | 11082.09.960.887 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.78 s / 1079.04 tokens per second
llama-server | 11082.12.160.174 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.98 s / 1066.00 tokens per second
llama-server | 11082.14.395.125 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.20 s / 1054.07 tokens per second
llama-server | 11082.16.662.936 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.46 s / 1042.70 tokens per second
llama-server | 11082.18.999.768 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.75 s / 1031.93 tokens per second
llama-server | 11082.21.336.118 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 34816, progress = 0.91, t = 34.12 s / 1020.45 tokens per second
llama-server | 11082.23.711.232 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 36864, progress = 0.96, t = 36.48 s / 1010.49 tokens per second
llama-server | 11082.24.810.512 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 37748, progress = 0.99, t = 37.75 s / 999.89 tokens per second
llama-server | 11082.25.578.458 I slot print_timing: id 1 | task 2810536 | prompt processing, n_tokens = 38260, progress = 1.00, t = 38.45 s / 995.18 tokens per second
llama-server | 11082.28.723.043 I slot print_timing: id 1 | task 2810536 | prompt eval time = 39273.95 ms / 38264 tokens ( 1.03 ms per token, 974.28 tokens per second)
llama-server | 11082.28.723.046 I slot print_timing: id 1 | task 2810536 | eval time = 2909.93 ms / 116 tokens ( 25.30 ms per token, 39.52 tokens per second)
llama-server | 11082.28.723.047 I slot print_timing: id 1 | task 2810536 | total time = 42183.89 ms / 38380 tokens
llama-server | 11082.28.723.047 I slot print_timing: id 1 | task 2810536 | graphs reused = 2721600
llama-server | 11082.28.723.050 I slot print_timing: id 1 | task 2810536 | draft acceptance = 0.50303 ( 83 accepted / 165 generated), mean len = 3.52
llama-server | 11082.28.724.344 I slot release: id 1 | task 2810536 | stop processing: n_tokens = 38380, truncated = 0
llama-server | 11082.29.963.555 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 664919641926
llama-server | 11082.29.964.153 I slot launch_slot_: id 0 | task 2810591 | processing task, is_child = 0
llama-server | 11082.29.966.023 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1925.442 MiB)
llama-server | 11082.36.462.602 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1281.22 tokens per second
llama-server | 11082.38.310.502 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.63 s / 1234.99 tokens per second
llama-server | 11082.40.192.929 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.51 s / 1203.60 tokens per second
llama-server | 11082.42.115.228 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.42 s / 1179.29 tokens per second
llama-server | 11082.44.089.231 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.38 s / 1157.82 tokens per second
llama-server | 11082.46.092.216 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.37 s / 1139.88 tokens per second
llama-server | 11082.48.130.304 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.41 s / 1123.42 tokens per second
llama-server | 11082.50.206.395 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.47 s / 1108.68 tokens per second
llama-server | 11082.52.324.113 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.58 s / 1094.77 tokens per second
llama-server | 11082.54.493.797 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.73 s / 1081.37 tokens per second
llama-server | 11082.56.688.228 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.92 s / 1068.25 tokens per second
llama-server | 11082.58.920.616 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.14 s / 1056.27 tokens per second
llama-server | 11083.01.184.725 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.40 s / 1044.81 tokens per second
llama-server | 11083.03.521.932 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.69 s / 1033.90 tokens per second
llama-server | 11083.05.859.098 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.06 s / 1022.31 tokens per second
llama-server | 11083.08.234.676 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 36864, progress = 0.97, t = 36.42 s / 1012.16 tokens per second
llama-server | 11083.09.020.799 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 37474, progress = 0.99, t = 37.69 s / 994.22 tokens per second
llama-server | 11083.09.739.865 I slot print_timing: id 0 | task 2810591 | prompt processing, n_tokens = 37986, progress = 1.00, t = 38.03 s / 998.85 tokens per second
llama-server | 11083.13.357.312 I slot print_timing: id 0 | task 2810591 | n_gen = 101, tg = 29.20 t/s, tg_3s = 29.49 t/s
llama-server | 11083.16.420.868 I slot print_timing: id 0 | task 2810591 | n_gen = 173, tg = 26.51 t/s, tg_3s = 23.50 t/s
llama-server | 11083.19.474.713 I slot print_timing: id 0 | task 2810591 | n_gen = 261, tg = 27.25 t/s, tg_3s = 28.82 t/s
llama-server | 11083.22.529.670 I slot print_timing: id 0 | task 2810591 | n_gen = 347, tg = 27.47 t/s, tg_3s = 28.15 t/s
llama-server | 11083.25.583.594 I slot print_timing: id 0 | task 2810591 | n_gen = 411, tg = 26.20 t/s, tg_3s = 20.96 t/s
llama-server | 11083.28.655.934 I slot print_timing: id 0 | task 2810591 | n_gen = 482, tg = 25.69 t/s, tg_3s = 23.11 t/s
llama-server | 11083.31.714.695 I slot print_timing: id 0 | task 2810591 | n_gen = 554, tg = 25.39 t/s, tg_3s = 23.54 t/s
llama-server | 11083.34.781.405 I slot print_timing: id 0 | task 2810591 | n_gen = 631, tg = 25.35 t/s, tg_3s = 25.11 t/s
llama-server | 11083.37.864.032 I slot print_timing: id 0 | task 2810591 | n_gen = 711, tg = 25.42 t/s, tg_3s = 25.95 t/s
llama-server | 11083.40.934.007 I slot print_timing: id 0 | task 2810591 | n_gen = 802, tg = 25.84 t/s, tg_3s = 29.64 t/s
llama-server | 11083.44.010.455 I slot print_timing: id 0 | task 2810591 | n_gen = 898, tg = 26.32 t/s, tg_3s = 31.20 t/s
llama-server | 11083.47.013.651 I slot print_timing: id 0 | task 2810591 | n_gen = 990, tg = 26.67 t/s, tg_3s = 30.63 t/s
llama-server | 11083.50.087.045 I slot print_timing: id 0 | task 2810591 | n_gen = 1054, tg = 26.22 t/s, tg_3s = 20.82 t/s
llama-server | 11083.53.163.728 I slot print_timing: id 0 | task 2810591 | n_gen = 1146, tg = 26.49 t/s, tg_3s = 29.90 t/s
llama-server | 11083.56.181.547 I slot print_timing: id 0 | task 2810591 | n_gen = 1255, tg = 27.11 t/s, tg_3s = 36.12 t/s
llama-server | 11083.59.264.113 I slot print_timing: id 0 | task 2810591 | n_gen = 1344, tg = 27.22 t/s, tg_3s = 28.87 t/s
llama-server | 11084.02.344.273 I slot print_timing: id 0 | task 2810591 | n_gen = 1420, tg = 27.07 t/s, tg_3s = 24.67 t/s
llama-server | 11084.05.363.149 I slot print_timing: id 0 | task 2810591 | n_gen = 1513, tg = 27.28 t/s, tg_3s = 30.81 t/s
llama-server | 11084.08.366.501 I slot print_timing: id 0 | task 2810591 | n_gen = 1616, tg = 27.64 t/s, tg_3s = 34.30 t/s
llama-server | 11084.11.380.437 I slot print_timing: id 0 | task 2810591 | n_gen = 1695, tg = 27.57 t/s, tg_3s = 26.21 t/s
llama-server | 11084.14.384.214 I slot print_timing: id 0 | task 2810591 | n_gen = 1773, tg = 27.49 t/s, tg_3s = 25.97 t/s
llama-server | 11084.17.387.313 I slot print_timing: id 0 | task 2810591 | n_gen = 1845, tg = 27.34 t/s, tg_3s = 23.98 t/s
llama-server | 11084.20.391.568 I slot print_timing: id 0 | task 2810591 | n_gen = 1940, tg = 27.52 t/s, tg_3s = 31.62 t/s
llama-server | 11084.23.416.424 I slot print_timing: id 0 | task 2810591 | n_gen = 2025, tg = 27.54 t/s, tg_3s = 28.10 t/s
llama-server | 11084.26.426.219 I slot print_timing: id 0 | task 2810591 | n_gen = 2097, tg = 27.40 t/s, tg_3s = 23.92 t/s
llama-server | 11084.29.431.321 I slot print_timing: id 0 | task 2810591 | n_gen = 2186, tg = 27.48 t/s, tg_3s = 29.62 t/s
llama-server | 11084.32.460.535 I slot print_timing: id 0 | task 2810591 | n_gen = 2272, tg = 27.52 t/s, tg_3s = 28.39 t/s
llama-server | 11084.35.472.708 I slot print_timing: id 0 | task 2810591 | n_gen = 2346, tg = 27.41 t/s, tg_3s = 24.57 t/s
llama-server | 11084.38.490.123 I slot print_timing: id 0 | task 2810591 | n_gen = 2439, tg = 27.53 t/s, tg_3s = 30.82 t/s
llama-server | 11084.41.521.468 I slot print_timing: id 0 | task 2810591 | n_gen = 2517, tg = 27.47 t/s, tg_3s = 25.73 t/s
llama-server | 11084.44.536.215 I slot print_timing: id 0 | task 2810591 | n_gen = 2602, tg = 27.49 t/s, tg_3s = 28.19 t/s
llama-server | 11084.47.559.831 I slot print_timing: id 0 | task 2810591 | n_gen = 2704, tg = 27.69 t/s, tg_3s = 33.73 t/s
llama-server | 11084.50.592.097 I slot print_timing: id 0 | task 2810591 | n_gen = 2782, tg = 27.63 t/s, tg_3s = 25.72 t/s
llama-server | 11084.53.611.186 I slot print_timing: id 0 | task 2810591 | n_gen = 2863, tg = 27.60 t/s, tg_3s = 26.83 t/s
llama-server | 11084.56.636.853 I slot print_timing: id 0 | task 2810591 | n_gen = 2948, tg = 27.62 t/s, tg_3s = 28.09 t/s
llama-server | 11084.59.682.977 I slot print_timing: id 0 | task 2810591 | n_gen = 3046, tg = 27.74 t/s, tg_3s = 32.17 t/s
llama-server | 11085.00.040.904 I slot print_timing: id 0 | task 2810591 | prompt eval time = 38811.26 ms / 37990 tokens ( 1.02 ms per token, 978.84 tokens per second)
llama-server | 11085.00.040.908 I slot print_timing: id 0 | task 2810591 | eval time = 110107.88 ms / 3062 tokens ( 35.97 ms per token, 27.80 tokens per second)
llama-server | 11085.00.040.908 I slot print_timing: id 0 | task 2810591 | total time = 148919.14 ms / 41052 tokens
llama-server | 11085.00.040.909 I slot print_timing: id 0 | task 2810591 | graphs reused = 2722834
llama-server | 11085.00.040.912 I slot print_timing: id 0 | task 2810591 | draft acceptance = 0.29110 ( 1815 accepted / 6235 generated), mean len = 2.46
llama-server | 11085.00.042.111 I slot release: id 0 | task 2810591 | stop processing: n_tokens = 41052, truncated = 0
llama-server | 11085.01.528.195 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 664964564396
llama-server | 11085.01.528.977 I slot launch_slot_: id 1 | task 2811860 | processing task, is_child = 0
llama-server | 11085.01.530.990 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1860.241 MiB)
llama-server | 11085.06.583.309 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.00 s / 1363.63 tokens per second
llama-server | 11085.08.400.254 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.82 s / 1274.62 tokens per second
llama-server | 11085.10.255.691 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.66 s / 1229.27 tokens per second
llama-server | 11085.12.149.109 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.55 s / 1198.13 tokens per second
llama-server | 11085.14.090.378 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.48 s / 1172.11 tokens per second
llama-server | 11085.16.055.730 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.44 s / 1152.56 tokens per second
llama-server | 11085.18.063.335 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 16384, progress = 0.44, t = 14.43 s / 1135.15 tokens per second
llama-server | 11085.20.107.670 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.47 s / 1119.08 tokens per second
llama-server | 11085.22.190.432 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.54 s / 1104.45 tokens per second
llama-server | 11085.24.312.744 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.65 s / 1090.75 tokens per second
llama-server | 11085.26.488.983 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.81 s / 1077.47 tokens per second
llama-server | 11085.28.687.878 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 26624, progress = 0.71, t = 25.01 s / 1064.53 tokens per second
llama-server | 11085.30.924.905 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.24 s / 1052.69 tokens per second
llama-server | 11085.33.193.429 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 30720, progress = 0.82, t = 29.50 s / 1041.41 tokens per second
llama-server | 11085.35.532.995 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.79 s / 1030.67 tokens per second
llama-server | 11085.37.875.662 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 34816, progress = 0.93, t = 34.16 s / 1019.23 tokens per second
llama-server | 11085.40.251.484 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.53 s / 1009.22 tokens per second
llama-server | 11085.40.576.525 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 37073, progress = 0.99, t = 37.23 s / 995.77 tokens per second
llama-server | 11085.41.290.442 I slot print_timing: id 1 | task 2811860 | prompt processing, n_tokens = 37585, progress = 1.00, t = 37.67 s / 997.75 tokens per second
llama-server | 11085.44.704.044 I slot print_timing: id 1 | task 2811860 | n_gen = 103, tg = 32.15 t/s, tg_3s = 32.46 t/s
llama-server | 11085.47.756.901 I slot print_timing: id 1 | task 2811860 | n_gen = 211, tg = 33.73 t/s, tg_3s = 35.38 t/s
llama-server | 11085.50.825.847 I slot print_timing: id 1 | task 2811860 | n_gen = 301, tg = 32.28 t/s, tg_3s = 29.33 t/s
llama-server | 11085.53.880.997 I slot print_timing: id 1 | task 2811860 | n_gen = 397, tg = 32.06 t/s, tg_3s = 31.42 t/s
llama-server | 11085.56.943.742 I slot print_timing: id 1 | task 2811860 | n_gen = 512, tg = 33.15 t/s, tg_3s = 37.55 t/s
llama-server | 11085.59.944.187 I slot print_timing: id 1 | task 2811860 | n_gen = 640, tg = 34.70 t/s, tg_3s = 42.66 t/s
llama-server | 11086.03.004.335 I slot print_timing: id 1 | task 2811860 | n_gen = 723, tg = 33.62 t/s, tg_3s = 27.12 t/s
llama-server | 11086.06.080.077 I slot print_timing: id 1 | task 2811860 | n_gen = 816, tg = 33.20 t/s, tg_3s = 30.24 t/s
llama-server | 11086.09.151.548 I slot print_timing: id 1 | task 2811860 | n_gen = 914, tg = 33.06 t/s, tg_3s = 31.91 t/s
llama-server | 11086.12.222.065 I slot print_timing: id 1 | task 2811860 | n_gen = 1006, tg = 32.75 t/s, tg_3s = 29.96 t/s
llama-server | 11086.15.224.964 I slot print_timing: id 1 | task 2811860 | n_gen = 1115, tg = 33.06 t/s, tg_3s = 36.30 t/s
llama-server | 11086.18.304.438 I slot print_timing: id 1 | task 2811860 | n_gen = 1220, tg = 33.15 t/s, tg_3s = 34.10 t/s
llama-server | 11086.21.316.405 I slot print_timing: id 1 | task 2811860 | n_gen = 1333, tg = 33.48 t/s, tg_3s = 37.52 t/s
llama-server | 11086.24.399.624 I slot print_timing: id 1 | task 2811860 | n_gen = 1438, tg = 33.52 t/s, tg_3s = 34.06 t/s
llama-server | 11086.27.480.695 I slot print_timing: id 1 | task 2811860 | n_gen = 1537, tg = 33.43 t/s, tg_3s = 32.13 t/s
llama-server | 11086.30.492.945 I slot print_timing: id 1 | task 2811860 | n_gen = 1630, tg = 33.27 t/s, tg_3s = 30.87 t/s
llama-server | 11086.33.578.436 I slot print_timing: id 1 | task 2811860 | n_gen = 1715, tg = 32.93 t/s, tg_3s = 27.55 t/s
llama-server | 11086.36.660.314 I slot print_timing: id 1 | task 2811860 | n_gen = 1788, tg = 32.41 t/s, tg_3s = 23.69 t/s
llama-server | 11086.39.675.556 I slot print_timing: id 1 | task 2811860 | n_gen = 1872, tg = 32.18 t/s, tg_3s = 27.86 t/s
llama-server | 11086.42.680.646 I slot print_timing: id 1 | task 2811860 | n_gen = 1968, tg = 32.17 t/s, tg_3s = 31.95 t/s
llama-server | 11086.45.683.527 I slot print_timing: id 1 | task 2811860 | n_gen = 2073, tg = 32.30 t/s, tg_3s = 34.97 t/s
llama-server | 11086.48.705.884 I slot print_timing: id 1 | task 2811860 | n_gen = 2182, tg = 32.47 t/s, tg_3s = 36.06 t/s
llama-server | 11086.51.717.549 I slot print_timing: id 1 | task 2811860 | n_gen = 2280, tg = 32.47 t/s, tg_3s = 32.54 t/s
llama-server | 11086.54.756.020 I slot print_timing: id 1 | task 2811860 | n_gen = 2427, tg = 33.13 t/s, tg_3s = 48.38 t/s
llama-server | 11086.57.768.637 I slot print_timing: id 1 | task 2811860 | n_gen = 2523, tg = 33.08 t/s, tg_3s = 31.87 t/s
llama-server | 11087.00.803.026 I slot print_timing: id 1 | task 2811860 | n_gen = 2636, tg = 33.24 t/s, tg_3s = 37.24 t/s
llama-server | 11087.03.831.215 I slot print_timing: id 1 | task 2811860 | n_gen = 2768, tg = 33.62 t/s, tg_3s = 43.59 t/s
llama-server | 11087.04.809.970 I slot print_timing: id 1 | task 2811860 | prompt eval time = 38497.55 ms / 37589 tokens ( 1.02 ms per token, 976.40 tokens per second)
llama-server | 11087.04.809.974 I slot print_timing: id 1 | task 2811860 | eval time = 83278.96 ms / 2814 tokens ( 29.61 ms per token, 33.78 tokens per second)
llama-server | 11087.04.809.974 I slot print_timing: id 1 | task 2811860 | total time = 121776.51 ms / 40403 tokens
llama-server | 11087.04.809.975 I slot print_timing: id 1 | task 2811860 | graphs reused = 2723766
llama-server | 11087.04.809.978 I slot print_timing: id 1 | task 2811860 | draft acceptance = 0.39619 ( 1870 accepted / 4720 generated), mean len = 2.98
llama-server | 11087.04.811.020 I slot release: id 1 | task 2811860 | stop processing: n_tokens = 40403, truncated = 0
llama-server | 11087.06.278.604 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 665115882163
llama-server | 11087.06.279.134 I slot launch_slot_: id 0 | task 2812826 | processing task, is_child = 0
llama-server | 11087.06.281.065 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1888.004 MiB)
llama-server | 11087.11.732.091 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.00 s / 1364.13 tokens per second
llama-server | 11087.13.549.144 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1277.33 tokens per second
llama-server | 11087.15.406.487 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.65 s / 1231.08 tokens per second
llama-server | 11087.17.306.152 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.55 s / 1197.60 tokens per second
llama-server | 11087.19.233.340 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.47 s / 1174.12 tokens per second
llama-server | 11087.21.196.366 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.42 s / 1154.13 tokens per second
llama-server | 11087.23.202.561 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 16384, progress = 0.44, t = 14.41 s / 1136.64 tokens per second
llama-server | 11087.25.242.628 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.45 s / 1120.59 tokens per second
llama-server | 11087.27.323.797 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 20480, progress = 0.55, t = 18.52 s / 1105.98 tokens per second
llama-server | 11087.29.444.064 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.63 s / 1092.17 tokens per second
llama-server | 11087.31.617.373 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.78 s / 1078.88 tokens per second
llama-server | 11087.33.813.696 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 26624, progress = 0.71, t = 24.98 s / 1065.86 tokens per second
llama-server | 11087.36.047.262 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.20 s / 1054.06 tokens per second
llama-server | 11087.38.316.618 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 30720, progress = 0.82, t = 29.46 s / 1042.71 tokens per second
llama-server | 11087.40.655.703 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.76 s / 1031.84 tokens per second
llama-server | 11087.42.993.600 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 34816, progress = 0.93, t = 34.12 s / 1020.35 tokens per second
llama-server | 11087.45.370.059 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.49 s / 1010.34 tokens per second
llama-server | 11087.45.607.109 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 37021, progress = 0.99, t = 37.19 s / 995.47 tokens per second
llama-server | 11087.46.321.138 I slot print_timing: id 0 | task 2812826 | prompt processing, n_tokens = 37533, progress = 1.00, t = 37.54 s / 999.76 tokens per second
llama-server | 11087.49.523.405 I slot print_timing: id 0 | task 2812826 | n_gen = 126, tg = 41.53 t/s, tg_3s = 41.85 t/s
llama-server | 11087.52.572.196 I slot print_timing: id 0 | task 2812826 | n_gen = 219, tg = 35.98 t/s, tg_3s = 30.50 t/s
llama-server | 11087.55.621.076 I slot print_timing: id 0 | task 2812826 | n_gen = 311, tg = 34.04 t/s, tg_3s = 30.18 t/s
llama-server | 11087.58.691.261 I slot print_timing: id 0 | task 2812826 | n_gen = 424, tg = 34.73 t/s, tg_3s = 36.81 t/s
llama-server | 11088.01.746.801 I slot print_timing: id 0 | task 2812826 | n_gen = 513, tg = 33.61 t/s, tg_3s = 29.13 t/s
llama-server | 11088.04.822.597 I slot print_timing: id 0 | task 2812826 | n_gen = 619, tg = 33.75 t/s, tg_3s = 34.46 t/s
llama-server | 11088.07.887.976 I slot print_timing: id 0 | task 2812826 | n_gen = 728, tg = 34.01 t/s, tg_3s = 35.56 t/s
llama-server | 11088.10.954.133 I slot print_timing: id 0 | task 2812826 | n_gen = 845, tg = 34.53 t/s, tg_3s = 38.16 t/s
llama-server | 11088.13.959.328 I slot print_timing: id 0 | task 2812826 | n_gen = 973, tg = 35.41 t/s, tg_3s = 42.59 t/s
llama-server | 11088.17.031.584 I slot print_timing: id 0 | task 2812826 | n_gen = 1073, tg = 35.13 t/s, tg_3s = 32.55 t/s
llama-server | 11088.20.038.549 I slot print_timing: id 0 | task 2812826 | n_gen = 1167, tg = 34.78 t/s, tg_3s = 31.26 t/s
llama-server | 11088.23.119.532 I slot print_timing: id 0 | task 2812826 | n_gen = 1301, tg = 35.51 t/s, tg_3s = 43.49 t/s
llama-server | 11088.26.126.728 I slot print_timing: id 0 | task 2812826 | n_gen = 1401, tg = 35.34 t/s, tg_3s = 33.25 t/s
llama-server | 11088.29.206.785 I slot print_timing: id 0 | task 2812826 | n_gen = 1505, tg = 35.23 t/s, tg_3s = 33.77 t/s
llama-server | 11088.32.282.748 I slot print_timing: id 0 | task 2812826 | n_gen = 1596, tg = 34.85 t/s, tg_3s = 29.58 t/s
llama-server | 11088.35.295.238 I slot print_timing: id 0 | task 2812826 | n_gen = 1680, tg = 34.42 t/s, tg_3s = 27.88 t/s
llama-server | 11088.38.373.840 I slot print_timing: id 0 | task 2812826 | n_gen = 1762, tg = 33.96 t/s, tg_3s = 26.64 t/s
llama-server | 11088.41.454.703 I slot print_timing: id 0 | task 2812826 | n_gen = 1852, tg = 33.69 t/s, tg_3s = 29.21 t/s
llama-server | 11088.44.476.412 I slot print_timing: id 0 | task 2812826 | n_gen = 1956, tg = 33.73 t/s, tg_3s = 34.42 t/s
llama-server | 11088.47.480.102 I slot print_timing: id 0 | task 2812826 | n_gen = 2033, tg = 33.33 t/s, tg_3s = 25.64 t/s
llama-server | 11088.50.483.969 I slot print_timing: id 0 | task 2812826 | n_gen = 2126, tg = 33.22 t/s, tg_3s = 30.96 t/s
llama-server | 11088.53.514.225 I slot print_timing: id 0 | task 2812826 | n_gen = 2242, tg = 33.45 t/s, tg_3s = 38.28 t/s
llama-server | 11088.56.523.397 I slot print_timing: id 0 | task 2812826 | n_gen = 2327, tg = 33.22 t/s, tg_3s = 28.25 t/s
llama-server | 11088.59.553.184 I slot print_timing: id 0 | task 2812826 | n_gen = 2421, tg = 33.13 t/s, tg_3s = 31.03 t/s
llama-server | 11089.02.565.582 I slot print_timing: id 0 | task 2812826 | n_gen = 2503, tg = 32.90 t/s, tg_3s = 27.22 t/s
llama-server | 11089.05.580.078 I slot print_timing: id 0 | task 2812826 | n_gen = 2593, tg = 32.78 t/s, tg_3s = 29.86 t/s
llama-server | 11089.08.611.131 I slot print_timing: id 0 | task 2812826 | n_gen = 2683, tg = 32.67 t/s, tg_3s = 29.69 t/s
llama-server | 11089.11.628.762 I slot print_timing: id 0 | task 2812826 | n_gen = 2782, tg = 32.67 t/s, tg_3s = 32.81 t/s
llama-server | 11089.14.648.311 I slot print_timing: id 0 | task 2812826 | n_gen = 2889, tg = 32.77 t/s, tg_3s = 35.44 t/s
llama-server | 11089.17.691.557 I slot print_timing: id 0 | task 2812826 | n_gen = 3000, tg = 32.89 t/s, tg_3s = 36.47 t/s
llama-server | 11089.20.714.386 I slot print_timing: id 0 | task 2812826 | n_gen = 3113, tg = 33.04 t/s, tg_3s = 37.38 t/s
llama-server | 11089.23.757.055 I slot print_timing: id 0 | task 2812826 | n_gen = 3218, tg = 33.08 t/s, tg_3s = 34.51 t/s
llama-server | 11089.26.784.908 I slot print_timing: id 0 | task 2812826 | n_gen = 3318, tg = 33.08 t/s, tg_3s = 33.03 t/s
llama-server | 11089.29.825.131 I slot print_timing: id 0 | task 2812826 | n_gen = 3422, tg = 33.11 t/s, tg_3s = 34.21 t/s
llama-server | 11089.32.849.186 I slot print_timing: id 0 | task 2812826 | n_gen = 3510, tg = 33.00 t/s, tg_3s = 29.10 t/s
llama-server | 11089.35.874.347 I slot print_timing: id 0 | task 2812826 | n_gen = 3616, tg = 33.06 t/s, tg_3s = 35.04 t/s
llama-server | 11089.38.920.847 I slot print_timing: id 0 | task 2812826 | n_gen = 3716, tg = 33.05 t/s, tg_3s = 32.82 t/s
llama-server | 11089.41.952.978 I slot print_timing: id 0 | task 2812826 | n_gen = 3817, tg = 33.06 t/s, tg_3s = 33.31 t/s
llama-server | 11089.44.986.954 I slot print_timing: id 0 | task 2812826 | n_gen = 3925, tg = 33.12 t/s, tg_3s = 35.60 t/s
llama-server | 11089.48.043.246 I slot print_timing: id 0 | task 2812826 | n_gen = 4006, tg = 32.95 t/s, tg_3s = 26.50 t/s
llama-server | 11089.51.083.225 I slot print_timing: id 0 | task 2812826 | n_gen = 4101, tg = 32.91 t/s, tg_3s = 31.25 t/s
llama-server | 11089.54.138.521 I slot print_timing: id 0 | task 2812826 | n_gen = 4197, tg = 32.88 t/s, tg_3s = 31.42 t/s
llama-server | 11089.57.183.264 I slot print_timing: id 0 | task 2812826 | n_gen = 4293, tg = 32.85 t/s, tg_3s = 31.53 t/s
llama-server | 11090.00.230.216 I slot print_timing: id 0 | task 2812826 | n_gen = 4394, tg = 32.85 t/s, tg_3s = 33.15 t/s
llama-server | 11090.03.292.455 I slot print_timing: id 0 | task 2812826 | n_gen = 4486, tg = 32.79 t/s, tg_3s = 30.04 t/s
llama-server | 11090.06.340.572 I slot print_timing: id 0 | task 2812826 | n_gen = 4577, tg = 32.73 t/s, tg_3s = 29.85 t/s
llama-server | 11090.09.389.281 I slot print_timing: id 0 | task 2812826 | n_gen = 4675, tg = 32.71 t/s, tg_3s = 32.14 t/s
llama-server | 11090.12.451.647 I slot print_timing: id 0 | task 2812826 | n_gen = 4756, tg = 32.58 t/s, tg_3s = 26.45 t/s
llama-server | 11090.15.510.424 I slot print_timing: id 0 | task 2812826 | n_gen = 4875, tg = 32.71 t/s, tg_3s = 38.90 t/s
llama-server | 11090.18.589.388 I slot print_timing: id 0 | task 2812826 | n_gen = 5006, tg = 32.91 t/s, tg_3s = 42.55 t/s
llama-server | 11090.19.494.093 I slot print_timing: id 0 | task 2812826 | prompt eval time = 38321.09 ms / 37537 tokens ( 1.02 ms per token, 979.54 tokens per second)
llama-server | 11090.19.494.096 I slot print_timing: id 0 | task 2812826 | eval time = 152980.89 ms / 5042 tokens ( 30.35 ms per token, 32.95 tokens per second)
llama-server | 11090.19.494.097 I slot print_timing: id 0 | task 2812826 | total time = 191301.98 ms / 42579 tokens
llama-server | 11090.19.494.097 I slot print_timing: id 0 | task 2812826 | graphs reused = 2725468
llama-server | 11090.19.494.100 I slot print_timing: id 0 | task 2812826 | draft acceptance = 0.38514 ( 3318 accepted / 8615 generated), mean len = 2.93
llama-server | 11090.19.495.172 I slot release: id 0 | task 2812826 | stop processing: n_tokens = 42578, truncated = 0
llama-server | 11090.21.260.057 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 665240651073
llama-server | 11090.21.260.528 I slot launch_slot_: id 1 | task 2814571 | processing task, is_child = 0
llama-server | 11090.21.262.627 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1880.689 MiB)
llama-server | 11090.25.944.150 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.01 s / 1361.44 tokens per second
llama-server | 11090.27.762.623 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.82 s / 1275.11 tokens per second
llama-server | 11090.29.623.041 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.66 s / 1229.23 tokens per second
llama-server | 11090.31.511.891 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.55 s / 1197.60 tokens per second
llama-server | 11090.33.439.206 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.47 s / 1173.82 tokens per second
llama-server | 11090.35.421.941 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.44 s / 1152.30 tokens per second
llama-server | 11090.37.429.480 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 16384, progress = 0.44, t = 14.43 s / 1135.08 tokens per second
llama-server | 11090.39.479.279 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.47 s / 1119.01 tokens per second
llama-server | 11090.41.560.888 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 20480, progress = 0.55, t = 18.55 s / 1104.01 tokens per second
llama-server | 11090.43.683.384 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.66 s / 1090.40 tokens per second
llama-server | 11090.45.857.422 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 24576, progress = 0.66, t = 22.81 s / 1077.21 tokens per second
llama-server | 11090.48.054.436 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 26624, progress = 0.71, t = 25.01 s / 1064.42 tokens per second
llama-server | 11090.50.291.119 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.24 s / 1052.66 tokens per second
llama-server | 11090.52.558.525 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 30720, progress = 0.82, t = 29.50 s / 1041.35 tokens per second
llama-server | 11090.54.898.058 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.79 s / 1030.65 tokens per second
llama-server | 11090.57.237.117 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 34816, progress = 0.93, t = 34.16 s / 1019.22 tokens per second
llama-server | 11090.59.615.090 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.53 s / 1009.25 tokens per second
llama-server | 11090.59.811.425 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 36974, progress = 0.99, t = 37.23 s / 993.14 tokens per second
llama-server | 11091.00.552.214 I slot print_timing: id 1 | task 2814571 | prompt processing, n_tokens = 37486, progress = 1.00, t = 37.57 s / 997.84 tokens per second
llama-server | 11091.04.528.375 I slot print_timing: id 1 | task 2814571 | n_gen = 104, tg = 27.38 t/s, tg_3s = 27.64 t/s
llama-server | 11091.07.070.306 I slot print_timing: id 1 | task 2814571 | prompt eval time = 38369.53 ms / 37490 tokens ( 1.02 ms per token, 977.08 tokens per second)
llama-server | 11091.07.070.310 I slot print_timing: id 1 | task 2814571 | eval time = 6303.81 ms / 207 tokens ( 30.60 ms per token, 32.68 tokens per second)
llama-server | 11091.07.070.310 I slot print_timing: id 1 | task 2814571 | total time = 44673.34 ms / 37697 tokens
llama-server | 11091.07.070.311 I slot print_timing: id 1 | task 2814571 | graphs reused = 2725538
llama-server | 11091.07.070.314 I slot print_timing: id 1 | task 2814571 | draft acceptance = 0.37222 ( 134 accepted / 360 generated), mean len = 2.86
llama-server | 11091.07.071.538 I slot release: id 1 | task 2814571 | stop processing: n_tokens = 37696, truncated = 0
llama-server | 11091.08.797.014 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 665435335224
llama-server | 11091.08.797.686 I slot launch_slot_: id 0 | task 2814665 | processing task, is_child = 0
llama-server | 11091.08.799.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1845.113 MiB)
llama-server | 11091.15.233.089 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1280.39 tokens per second
llama-server | 11091.17.087.114 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.64 s / 1234.28 tokens per second
llama-server | 11091.18.971.692 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.52 s / 1202.12 tokens per second
llama-server | 11091.20.893.179 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.43 s / 1178.03 tokens per second
llama-server | 11091.22.862.840 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.39 s / 1157.01 tokens per second
llama-server | 11091.24.864.825 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.38 s / 1139.36 tokens per second
llama-server | 11091.26.902.467 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.41 s / 1123.18 tokens per second
llama-server | 11091.28.980.009 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.48 s / 1108.34 tokens per second
llama-server | 11091.31.097.576 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.58 s / 1094.48 tokens per second
llama-server | 11091.33.269.197 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.73 s / 1081.00 tokens per second
llama-server | 11091.35.462.889 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.93 s / 1067.91 tokens per second
llama-server | 11091.37.695.080 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.15 s / 1056.00 tokens per second
llama-server | 11091.39.961.708 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.41 s / 1044.50 tokens per second
llama-server | 11091.42.301.338 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.70 s / 1033.60 tokens per second
llama-server | 11091.44.637.349 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.07 s / 1021.96 tokens per second
llama-server | 11091.47.011.588 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 36864, progress = 0.97, t = 36.43 s / 1011.89 tokens per second
llama-server | 11091.47.835.838 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 37506, progress = 0.99, t = 37.70 s / 994.85 tokens per second
llama-server | 11091.48.550.203 I slot print_timing: id 0 | task 2814665 | prompt processing, n_tokens = 38018, progress = 1.00, t = 38.07 s / 998.59 tokens per second
llama-server | 11091.51.823.495 I slot print_timing: id 0 | task 2814665 | n_gen = 109, tg = 35.05 t/s, tg_3s = 35.37 t/s
llama-server | 11091.54.122.033 I slot print_timing: id 0 | task 2814665 | prompt eval time = 38852.77 ms / 38022 tokens ( 1.02 ms per token, 978.62 tokens per second)
llama-server | 11091.54.122.037 I slot print_timing: id 0 | task 2814665 | eval time = 5379.71 ms / 201 tokens ( 26.90 ms per token, 37.18 tokens per second)
llama-server | 11091.54.122.038 I slot print_timing: id 0 | task 2814665 | total time = 44232.48 ms / 38223 tokens
llama-server | 11091.54.122.039 I slot print_timing: id 0 | task 2814665 | graphs reused = 2725597
llama-server | 11091.54.122.043 I slot print_timing: id 0 | task 2814665 | draft acceptance = 0.45574 ( 139 accepted / 305 generated), mean len = 3.28
llama-server | 11091.54.123.177 I slot release: id 0 | task 2814665 | stop processing: n_tokens = 38222, truncated = 0
llama-server | 11091.55.310.363 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 665482911591
llama-server | 11091.55.311.061 I slot launch_slot_: id 1 | task 2814748 | processing task, is_child = 0
llama-server | 11091.55.313.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1933.954 MiB)
llama-server | 11092.02.242.198 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.79 s / 1281.57 tokens per second
llama-server | 11092.04.089.988 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.63 s / 1235.11 tokens per second
llama-server | 11092.05.972.599 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.51 s / 1203.63 tokens per second
llama-server | 11092.07.896.556 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.42 s / 1179.47 tokens per second
llama-server | 11092.09.867.572 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.38 s / 1158.09 tokens per second
llama-server | 11092.11.868.009 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.37 s / 1140.07 tokens per second
llama-server | 11092.13.904.429 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.40 s / 1123.80 tokens per second
llama-server | 11092.15.980.853 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.47 s / 1108.99 tokens per second
llama-server | 11092.18.096.556 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.57 s / 1095.17 tokens per second
llama-server | 11092.20.265.924 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.72 s / 1081.75 tokens per second
llama-server | 11092.22.459.473 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.91 s / 1068.64 tokens per second
llama-server | 11092.24.690.516 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.14 s / 1056.64 tokens per second
llama-server | 11092.26.958.137 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.39 s / 1045.13 tokens per second
llama-server | 11092.29.293.924 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.69 s / 1034.15 tokens per second
llama-server | 11092.31.628.794 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.05 s / 1022.53 tokens per second
llama-server | 11092.34.009.736 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 36864, progress = 0.97, t = 36.41 s / 1012.45 tokens per second
llama-server | 11092.34.797.839 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 37481, progress = 0.99, t = 37.69 s / 994.57 tokens per second
llama-server | 11092.35.513.944 I slot print_timing: id 1 | task 2814748 | prompt processing, n_tokens = 37993, progress = 1.00, t = 38.02 s / 999.20 tokens per second
llama-server | 11092.38.007.833 I slot print_timing: id 1 | task 2814748 | prompt eval time = 38804.64 ms / 37997 tokens ( 1.02 ms per token, 979.19 tokens per second)
llama-server | 11092.38.007.836 I slot print_timing: id 1 | task 2814748 | eval time = 2300.92 ms / 141 tokens ( 16.44 ms per token, 60.85 tokens per second)
llama-server | 11092.38.007.837 I slot print_timing: id 1 | task 2814748 | total time = 41105.56 ms / 38138 tokens
llama-server | 11092.38.007.838 I slot print_timing: id 1 | task 2814748 | graphs reused = 2725622
llama-server | 11092.38.007.851 I slot print_timing: id 1 | task 2814748 | draft acceptance = 0.87692 ( 114 accepted / 130 generated), mean len = 5.38
llama-server | 11092.38.008.945 I slot release: id 1 | task 2814748 | stop processing: n_tokens = 38137, truncated = 0
llama-server | 11092.39.659.119 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 665529963229
llama-server | 11092.39.659.723 I slot launch_slot_: id 0 | task 2814796 | processing task, is_child = 0
llama-server | 11092.39.661.696 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1912.375 MiB)
llama-server | 11092.46.874.239 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.79 s / 1282.93 tokens per second
llama-server | 11092.48.724.841 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.63 s / 1236.36 tokens per second
llama-server | 11092.50.605.784 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.50 s / 1204.27 tokens per second
llama-server | 11092.52.534.628 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.43 s / 1178.67 tokens per second
llama-server | 11092.54.491.230 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.37 s / 1158.89 tokens per second
llama-server | 11092.56.490.909 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.36 s / 1141.20 tokens per second
llama-server | 11092.58.525.860 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.38 s / 1124.93 tokens per second
llama-server | 11093.00.600.937 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.45 s / 1110.08 tokens per second
llama-server | 11093.02.715.972 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.55 s / 1096.11 tokens per second
llama-server | 11093.04.884.171 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.70 s / 1082.64 tokens per second
llama-server | 11093.07.077.976 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.90 s / 1069.44 tokens per second
llama-server | 11093.09.308.601 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.12 s / 1057.39 tokens per second
llama-server | 11093.11.572.179 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.37 s / 1045.91 tokens per second
llama-server | 11093.13.908.055 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.66 s / 1034.90 tokens per second
llama-server | 11093.16.243.311 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 34816, progress = 0.91, t = 34.02 s / 1023.25 tokens per second
llama-server | 11093.18.617.310 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 36864, progress = 0.96, t = 36.39 s / 1013.08 tokens per second
llama-server | 11093.19.761.987 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 37777, progress = 0.99, t = 37.66 s / 1003.13 tokens per second
llama-server | 11093.20.493.313 I slot print_timing: id 0 | task 2814796 | prompt processing, n_tokens = 38289, progress = 1.00, t = 38.36 s / 998.15 tokens per second
llama-server | 11093.24.245.869 I slot print_timing: id 0 | task 2814796 | n_gen = 103, tg = 29.04 t/s, tg_3s = 29.33 t/s
llama-server | 11093.27.326.513 I slot print_timing: id 0 | task 2814796 | n_gen = 197, tg = 29.73 t/s, tg_3s = 30.51 t/s
llama-server | 11093.29.695.746 I slot print_timing: id 0 | task 2814796 | prompt eval time = 39194.12 ms / 38293 tokens ( 1.02 ms per token, 977.01 tokens per second)
llama-server | 11093.29.695.749 I slot print_timing: id 0 | task 2814796 | eval time = 8961.80 ms / 299 tokens ( 30.07 ms per token, 33.25 tokens per second)
llama-server | 11093.29.695.750 I slot print_timing: id 0 | task 2814796 | total time = 48155.92 ms / 38592 tokens
llama-server | 11093.29.695.751 I slot print_timing: id 0 | task 2814796 | graphs reused = 2725722
llama-server | 11093.29.695.753 I slot print_timing: id 0 | task 2814796 | draft acceptance = 0.38627 ( 197 accepted / 510 generated), mean len = 2.93
llama-server | 11093.29.696.838 I slot release: id 0 | task 2814796 | stop processing: n_tokens = 38592, truncated = 0
llama-server | 11093.31.177.066 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 665573848997
llama-server | 11093.31.177.779 I slot launch_slot_: id 1 | task 2814920 | processing task, is_child = 0
llama-server | 11093.31.179.559 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1984.692 MiB)
llama-server | 11093.38.215.526 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1279.00 tokens per second
llama-server | 11093.40.072.746 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1232.25 tokens per second
llama-server | 11093.41.958.210 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.53 s / 1200.26 tokens per second
llama-server | 11093.43.889.467 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.45 s / 1175.49 tokens per second
llama-server | 11093.45.850.770 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.41 s / 1155.60 tokens per second
llama-server | 11093.47.855.868 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.40 s / 1138.05 tokens per second
llama-server | 11093.49.897.090 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.43 s / 1121.78 tokens per second
llama-server | 11093.51.978.682 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.50 s / 1106.92 tokens per second
llama-server | 11093.54.098.336 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.61 s / 1093.05 tokens per second
llama-server | 11093.56.269.971 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.76 s / 1079.72 tokens per second
llama-server | 11093.58.464.907 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 26624, progress = 0.69, t = 24.96 s / 1066.74 tokens per second
llama-server | 11094.00.697.754 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.18 s / 1054.84 tokens per second
llama-server | 11094.02.965.250 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.44 s / 1043.45 tokens per second
llama-server | 11094.05.302.413 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 32768, progress = 0.85, t = 31.73 s / 1032.63 tokens per second
llama-server | 11094.07.642.688 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 34816, progress = 0.91, t = 34.10 s / 1021.09 tokens per second
llama-server | 11094.10.016.834 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 36864, progress = 0.96, t = 36.46 s / 1010.99 tokens per second
llama-server | 11094.11.209.369 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 37859, progress = 0.99, t = 37.73 s / 1003.30 tokens per second
llama-server | 11094.11.937.492 I slot print_timing: id 1 | task 2814920 | prompt processing, n_tokens = 38371, progress = 1.00, t = 38.48 s / 997.13 tokens per second
llama-server | 11094.15.400.638 I slot print_timing: id 1 | task 2814920 | n_gen = 102, tg = 30.89 t/s, tg_3s = 31.20 t/s
llama-server | 11094.16.012.857 I slot print_timing: id 1 | task 2814920 | prompt eval time = 39267.89 ms / 38375 tokens ( 1.02 ms per token, 977.26 tokens per second)
llama-server | 11094.16.012.860 I slot print_timing: id 1 | task 2814920 | eval time = 3881.65 ms / 131 tokens ( 29.86 ms per token, 33.49 tokens per second)
llama-server | 11094.16.012.860 I slot print_timing: id 1 | task 2814920 | total time = 43149.54 ms / 38506 tokens
llama-server | 11094.16.012.861 I slot print_timing: id 1 | task 2814920 | graphs reused = 2725764
llama-server | 11094.16.012.864 I slot print_timing: id 1 | task 2814920 | draft acceptance = 0.39091 ( 86 accepted / 220 generated), mean len = 2.95
llama-server | 11094.16.014.545 I slot release: id 1 | task 2814920 | stop processing: n_tokens = 38505, truncated = 0
llama-server | 11094.17.533.635 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 665625536890
llama-server | 11094.17.534.266 I slot launch_slot_: id 0 | task 2814986 | processing task, is_child = 0
llama-server | 11094.17.536.253 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1822.370 MiB)
llama-server | 11094.24.015.705 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.79 s / 1281.57 tokens per second
llama-server | 11094.25.863.939 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.63 s / 1234.87 tokens per second
llama-server | 11094.27.744.849 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.51 s / 1203.64 tokens per second
llama-server | 11094.29.663.867 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.42 s / 1179.57 tokens per second
llama-server | 11094.31.634.654 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.37 s / 1158.52 tokens per second
llama-server | 11094.33.632.860 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.36 s / 1140.59 tokens per second
llama-server | 11094.35.667.822 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.39 s / 1124.36 tokens per second
llama-server | 11094.37.743.191 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.46 s / 1109.65 tokens per second
llama-server | 11094.39.859.291 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.56 s / 1095.63 tokens per second
llama-server | 11094.42.029.037 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.71 s / 1082.24 tokens per second
llama-server | 11094.44.221.398 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.90 s / 1069.08 tokens per second
llama-server | 11094.46.451.363 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.12 s / 1057.07 tokens per second
llama-server | 11094.48.716.516 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.38 s / 1045.58 tokens per second
llama-server | 11094.51.051.431 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.67 s / 1034.62 tokens per second
llama-server | 11094.53.386.288 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.03 s / 1023.01 tokens per second
llama-server | 11094.55.759.249 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 36864, progress = 0.97, t = 36.40 s / 1012.87 tokens per second
llama-server | 11094.56.319.367 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 37310, progress = 0.99, t = 37.10 s / 1005.64 tokens per second
llama-server | 11094.57.062.787 I slot print_timing: id 0 | task 2814986 | prompt processing, n_tokens = 37822, progress = 1.00, t = 37.80 s / 1000.65 tokens per second
llama-server | 11095.00.654.615 I slot print_timing: id 0 | task 2814986 | prompt eval time = 38628.03 ms / 37826 tokens ( 1.02 ms per token, 979.24 tokens per second)
llama-server | 11095.00.654.617 I slot print_timing: id 0 | task 2814986 | eval time = 3352.04 ms / 100 tokens ( 33.86 ms per token, 29.53 tokens per second)
llama-server | 11095.00.654.618 I slot print_timing: id 0 | task 2814986 | total time = 41980.08 ms / 37926 tokens
llama-server | 11095.00.654.619 I slot print_timing: id 0 | task 2814986 | graphs reused = 2725800
llama-server | 11095.00.654.621 I slot print_timing: id 0 | task 2814986 | draft acceptance = 0.32105 ( 61 accepted / 190 generated), mean len = 2.61
llama-server | 11095.00.655.715 I slot release: id 0 | task 2814986 | stop processing: n_tokens = 37925, truncated = 0
llama-server | 11095.04.130.860 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 665671854597
llama-server | 11095.04.131.545 I slot launch_slot_: id 1 | task 2815046 | processing task, is_child = 0
llama-server | 11095.04.134.050 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1839.859 MiB)
llama-server | 11095.10.912.629 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.78 s / 1285.20 tokens per second
llama-server | 11095.12.769.017 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.62 s / 1237.11 tokens per second
llama-server | 11095.14.646.611 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.50 s / 1205.23 tokens per second
llama-server | 11095.16.561.536 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.40 s / 1181.40 tokens per second
llama-server | 11095.18.521.795 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.35 s / 1161.16 tokens per second
llama-server | 11095.20.519.064 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.34 s / 1142.89 tokens per second
llama-server | 11095.22.553.680 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.36 s / 1126.39 tokens per second
llama-server | 11095.24.626.078 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.43 s / 1111.44 tokens per second
llama-server | 11095.26.740.170 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.53 s / 1097.42 tokens per second
llama-server | 11095.28.908.780 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.68 s / 1083.80 tokens per second
llama-server | 11095.31.111.999 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 26624, progress = 0.69, t = 24.87 s / 1070.56 tokens per second
llama-server | 11095.33.348.036 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.10 s / 1057.93 tokens per second
llama-server | 11095.35.612.553 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.36 s / 1046.20 tokens per second
llama-server | 11095.37.946.001 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.65 s / 1035.25 tokens per second
llama-server | 11095.40.281.829 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 34816, progress = 0.91, t = 34.01 s / 1023.57 tokens per second
llama-server | 11095.42.654.977 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 36864, progress = 0.96, t = 36.38 s / 1013.39 tokens per second
llama-server | 11095.43.802.817 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 37799, progress = 0.99, t = 37.65 s / 1004.06 tokens per second
llama-server | 11095.44.527.978 I slot print_timing: id 1 | task 2815046 | prompt processing, n_tokens = 38311, progress = 1.00, t = 38.35 s / 999.10 tokens per second
llama-server | 11095.47.779.807 I slot print_timing: id 1 | task 2815046 | n_gen = 100, tg = 32.88 t/s, tg_3s = 33.21 t/s
llama-server | 11095.50.840.893 I slot print_timing: id 1 | task 2815046 | n_gen = 204, tg = 33.43 t/s, tg_3s = 33.97 t/s
llama-server | 11095.53.903.192 I slot print_timing: id 1 | task 2815046 | n_gen = 294, tg = 32.08 t/s, tg_3s = 29.39 t/s
llama-server | 11095.56.980.578 I slot print_timing: id 1 | task 2815046 | n_gen = 388, tg = 31.69 t/s, tg_3s = 30.55 t/s
llama-server | 11096.00.051.763 I slot print_timing: id 1 | task 2815046 | n_gen = 496, tg = 32.39 t/s, tg_3s = 35.17 t/s
llama-server | 11096.03.117.052 I slot print_timing: id 1 | task 2815046 | n_gen = 571, tg = 31.07 t/s, tg_3s = 24.47 t/s
llama-server | 11096.06.203.303 I slot print_timing: id 1 | task 2815046 | n_gen = 635, tg = 29.58 t/s, tg_3s = 20.74 t/s
llama-server | 11096.09.269.696 I slot print_timing: id 1 | task 2815046 | n_gen = 715, tg = 29.14 t/s, tg_3s = 26.09 t/s
llama-server | 11096.12.337.972 I slot print_timing: id 1 | task 2815046 | n_gen = 805, tg = 29.16 t/s, tg_3s = 29.33 t/s
llama-server | 11096.15.345.359 I slot print_timing: id 1 | task 2815046 | n_gen = 877, tg = 28.65 t/s, tg_3s = 23.94 t/s
llama-server | 11096.18.426.812 I slot print_timing: id 1 | task 2815046 | n_gen = 962, tg = 28.55 t/s, tg_3s = 27.58 t/s
llama-server | 11096.21.504.789 I slot print_timing: id 1 | task 2815046 | n_gen = 1031, tg = 28.04 t/s, tg_3s = 22.42 t/s
llama-server | 11096.24.516.859 I slot print_timing: id 1 | task 2815046 | n_gen = 1111, tg = 27.93 t/s, tg_3s = 26.56 t/s
llama-server | 11096.27.602.924 I slot print_timing: id 1 | task 2815046 | n_gen = 1202, tg = 28.04 t/s, tg_3s = 29.49 t/s
llama-server | 11096.30.687.689 I slot print_timing: id 1 | task 2815046 | n_gen = 1279, tg = 27.83 t/s, tg_3s = 24.96 t/s
llama-server | 11096.33.691.347 I slot print_timing: id 1 | task 2815046 | n_gen = 1369, tg = 27.96 t/s, tg_3s = 29.96 t/s
llama-server | 11096.36.711.501 I slot print_timing: id 1 | task 2815046 | n_gen = 1464, tg = 28.17 t/s, tg_3s = 31.46 t/s
llama-server | 11096.39.716.010 I slot print_timing: id 1 | task 2815046 | n_gen = 1551, tg = 28.21 t/s, tg_3s = 28.96 t/s
llama-server | 11096.42.735.541 I slot print_timing: id 1 | task 2815046 | n_gen = 1636, tg = 28.21 t/s, tg_3s = 28.15 t/s
llama-server | 11096.45.743.511 I slot print_timing: id 1 | task 2815046 | n_gen = 1707, tg = 27.98 t/s, tg_3s = 23.60 t/s
llama-server | 11096.48.746.461 I slot print_timing: id 1 | task 2815046 | n_gen = 1776, tg = 27.74 t/s, tg_3s = 22.98 t/s
llama-server | 11096.51.756.171 I slot print_timing: id 1 | task 2815046 | n_gen = 1855, tg = 27.68 t/s, tg_3s = 26.25 t/s
llama-server | 11096.54.788.392 I slot print_timing: id 1 | task 2815046 | n_gen = 1945, tg = 27.76 t/s, tg_3s = 29.68 t/s
llama-server | 11096.57.794.822 I slot print_timing: id 1 | task 2815046 | n_gen = 2016, tg = 27.59 t/s, tg_3s = 23.62 t/s
llama-server | 11097.00.804.052 I slot print_timing: id 1 | task 2815046 | n_gen = 2074, tg = 27.26 t/s, tg_3s = 19.27 t/s
llama-server | 11097.03.840.599 I slot print_timing: id 1 | task 2815046 | n_gen = 2190, tg = 27.68 t/s, tg_3s = 38.20 t/s
llama-server | 11097.06.862.283 I slot print_timing: id 1 | task 2815046 | n_gen = 2292, tg = 27.91 t/s, tg_3s = 33.76 t/s
llama-server | 11097.09.876.232 I slot print_timing: id 1 | task 2815046 | n_gen = 2388, tg = 28.05 t/s, tg_3s = 31.85 t/s
llama-server | 11097.12.911.117 I slot print_timing: id 1 | task 2815046 | n_gen = 2491, tg = 28.25 t/s, tg_3s = 33.94 t/s
llama-server | 11097.15.938.283 I slot print_timing: id 1 | task 2815046 | n_gen = 2610, tg = 28.62 t/s, tg_3s = 39.31 t/s
llama-server | 11097.16.472.867 I slot print_timing: id 1 | task 2815046 | prompt eval time = 39180.23 ms / 38315 tokens ( 1.02 ms per token, 977.92 tokens per second)
llama-server | 11097.16.472.870 I slot print_timing: id 1 | task 2815046 | eval time = 91704.15 ms / 2637 tokens ( 34.79 ms per token, 28.74 tokens per second)
llama-server | 11097.16.472.871 I slot print_timing: id 1 | task 2815046 | total time = 130884.38 ms / 40952 tokens
llama-server | 11097.16.472.871 I slot print_timing: id 1 | task 2815046 | graphs reused = 2726827
llama-server | 11097.16.472.874 I slot print_timing: id 1 | task 2815046 | draft acceptance = 0.30790 ( 1598 accepted / 5190 generated), mean len = 2.54
llama-server | 11097.16.473.971 I slot release: id 1 | task 2815046 | stop processing: n_tokens = 40951, truncated = 0
llama-server | 11097.17.903.471 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 665716495767
llama-server | 11097.17.904.055 I slot launch_slot_: id 0 | task 2816106 | processing task, is_child = 0
llama-server | 11097.17.906.034 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1837.033 MiB)
llama-server | 11097.23.205.736 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.01 s / 1360.78 tokens per second
llama-server | 11097.25.026.399 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.82 s / 1273.88 tokens per second
llama-server | 11097.26.890.970 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.67 s / 1227.96 tokens per second
llama-server | 11097.28.782.720 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.56 s / 1196.09 tokens per second
llama-server | 11097.30.726.082 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.50 s / 1170.61 tokens per second
llama-server | 11097.32.694.198 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.45 s / 1151.16 tokens per second
llama-server | 11097.34.703.232 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 16384, progress = 0.44, t = 14.45 s / 1133.82 tokens per second
llama-server | 11097.36.748.316 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.49 s / 1117.72 tokens per second
llama-server | 11097.38.833.005 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.56 s / 1103.32 tokens per second
llama-server | 11097.40.958.593 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.68 s / 1089.57 tokens per second
llama-server | 11097.43.136.206 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.83 s / 1076.32 tokens per second
llama-server | 11097.45.337.827 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 26624, progress = 0.71, t = 25.04 s / 1063.46 tokens per second
llama-server | 11097.47.576.658 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.27 s / 1051.60 tokens per second
llama-server | 11097.49.846.043 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 30720, progress = 0.82, t = 29.53 s / 1040.35 tokens per second
llama-server | 11097.52.186.517 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.82 s / 1029.68 tokens per second
llama-server | 11097.54.525.225 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.19 s / 1018.35 tokens per second
llama-server | 11097.56.910.493 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.55 s / 1008.46 tokens per second
llama-server | 11097.57.299.145 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 37124, progress = 0.99, t = 37.27 s / 996.15 tokens per second
llama-server | 11097.58.050.090 I slot print_timing: id 0 | task 2816106 | prompt processing, n_tokens = 37636, progress = 1.00, t = 37.80 s / 995.76 tokens per second
llama-server | 11098.01.272.585 I slot print_timing: id 0 | task 2816106 | prompt eval time = 38633.79 ms / 37640 tokens ( 1.03 ms per token, 974.28 tokens per second)
llama-server | 11098.01.272.588 I slot print_timing: id 0 | task 2816106 | eval time = 2982.14 ms / 97 tokens ( 31.06 ms per token, 32.19 tokens per second)
llama-server | 11098.01.272.589 I slot print_timing: id 0 | task 2816106 | total time = 41615.93 ms / 37737 tokens
llama-server | 11098.01.272.589 I slot print_timing: id 0 | task 2816106 | graphs reused = 2726860
llama-server | 11098.01.272.593 I slot print_timing: id 0 | task 2816106 | draft acceptance = 0.37059 ( 63 accepted / 170 generated), mean len = 2.85
llama-server | 11098.01.273.828 I slot release: id 0 | task 2816106 | stop processing: n_tokens = 37737, truncated = 0
llama-server | 11098.02.547.360 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 665852314023
llama-server | 11098.02.548.186 I slot launch_slot_: id 1 | task 2816162 | processing task, is_child = 0
llama-server | 11098.02.550.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1852.161 MiB)
llama-server | 11098.09.545.734 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1281.29 tokens per second
llama-server | 11098.11.401.302 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.63 s / 1234.84 tokens per second
llama-server | 11098.13.299.922 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.53 s / 1200.27 tokens per second
llama-server | 11098.15.226.935 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.44 s / 1176.72 tokens per second
llama-server | 11098.17.185.890 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.40 s / 1156.30 tokens per second
llama-server | 11098.19.187.121 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.39 s / 1138.77 tokens per second
llama-server | 11098.21.223.490 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.42 s / 1122.71 tokens per second
llama-server | 11098.23.299.108 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.48 s / 1108.13 tokens per second
llama-server | 11098.25.416.881 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.59 s / 1094.29 tokens per second
llama-server | 11098.27.586.832 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.74 s / 1080.88 tokens per second
llama-server | 11098.29.781.532 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.93 s / 1067.84 tokens per second
llama-server | 11098.32.012.791 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.15 s / 1055.90 tokens per second
llama-server | 11098.34.278.007 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.41 s / 1044.45 tokens per second
llama-server | 11098.36.614.816 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.70 s / 1033.56 tokens per second
llama-server | 11098.38.950.734 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.07 s / 1022.03 tokens per second
llama-server | 11098.41.325.110 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 36864, progress = 0.97, t = 36.43 s / 1011.92 tokens per second
llama-server | 11098.41.929.199 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 37372, progress = 0.99, t = 37.14 s / 1006.34 tokens per second
llama-server | 11098.42.679.102 I slot print_timing: id 1 | task 2816162 | prompt processing, n_tokens = 37884, progress = 1.00, t = 37.88 s / 1000.05 tokens per second
llama-server | 11098.45.940.006 I slot print_timing: id 1 | task 2816162 | n_gen = 111, tg = 35.85 t/s, tg_3s = 36.17 t/s
llama-server | 11098.46.377.224 I slot print_timing: id 1 | task 2816162 | prompt eval time = 38666.09 ms / 37888 tokens ( 1.02 ms per token, 979.88 tokens per second)
llama-server | 11098.46.377.227 I slot print_timing: id 1 | task 2816162 | eval time = 3505.75 ms / 136 tokens ( 25.97 ms per token, 38.51 tokens per second)
llama-server | 11098.46.377.227 I slot print_timing: id 1 | task 2816162 | total time = 42171.84 ms / 38024 tokens
llama-server | 11098.46.377.228 I slot print_timing: id 1 | task 2816162 | graphs reused = 2726899
llama-server | 11098.46.377.231 I slot print_timing: id 1 | task 2816162 | draft acceptance = 0.47500 ( 95 accepted / 200 generated), mean len = 3.38
llama-server | 11098.46.378.371 I slot release: id 1 | task 2816162 | stop processing: n_tokens = 38023, truncated = 0
llama-server | 11098.47.655.065 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 665897113880
llama-server | 11098.47.655.743 I slot launch_slot_: id 0 | task 2816224 | processing task, is_child = 0
llama-server | 11098.47.657.526 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1849.269 MiB)
llama-server | 11098.54.094.449 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.79 s / 1282.08 tokens per second
llama-server | 11098.55.941.965 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.63 s / 1235.72 tokens per second
llama-server | 11098.57.822.487 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.50 s / 1204.35 tokens per second
llama-server | 11098.59.750.786 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.43 s / 1178.64 tokens per second
llama-server | 11099.01.710.414 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.37 s / 1159.08 tokens per second
llama-server | 11099.03.709.624 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.36 s / 1141.21 tokens per second
llama-server | 11099.05.745.294 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.39 s / 1124.82 tokens per second
llama-server | 11099.07.819.495 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.45 s / 1110.00 tokens per second
llama-server | 11099.09.937.972 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.55 s / 1096.03 tokens per second
llama-server | 11099.12.107.834 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.71 s / 1082.30 tokens per second
llama-server | 11099.14.300.476 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 26624, progress = 0.71, t = 24.90 s / 1069.22 tokens per second
llama-server | 11099.16.532.414 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.12 s / 1057.16 tokens per second
llama-server | 11099.18.805.932 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.38 s / 1045.64 tokens per second
llama-server | 11099.21.142.270 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.68 s / 1034.33 tokens per second
llama-server | 11099.23.477.434 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.04 s / 1022.73 tokens per second
llama-server | 11099.25.851.751 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.40 s / 1012.62 tokens per second
llama-server | 11099.26.351.594 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 37242, progress = 0.99, t = 37.11 s / 1003.56 tokens per second
llama-server | 11099.27.070.356 I slot print_timing: id 0 | task 2816224 | prompt processing, n_tokens = 37754, progress = 1.00, t = 37.72 s / 1000.81 tokens per second
llama-server | 11099.30.375.593 I slot print_timing: id 0 | task 2816224 | n_gen = 101, tg = 32.61 t/s, tg_3s = 32.93 t/s
llama-server | 11099.33.444.738 I slot print_timing: id 0 | task 2816224 | n_gen = 210, tg = 34.06 t/s, tg_3s = 35.51 t/s
llama-server | 11099.36.495.922 I slot print_timing: id 0 | task 2816224 | n_gen = 326, tg = 35.38 t/s, tg_3s = 38.02 t/s
llama-server | 11099.39.558.157 I slot print_timing: id 0 | task 2816224 | n_gen = 407, tg = 33.15 t/s, tg_3s = 26.45 t/s
llama-server | 11099.42.612.078 I slot print_timing: id 0 | task 2816224 | n_gen = 493, tg = 32.15 t/s, tg_3s = 28.16 t/s
llama-server | 11099.45.670.420 I slot print_timing: id 0 | task 2816224 | n_gen = 607, tg = 33.00 t/s, tg_3s = 37.28 t/s
llama-server | 11099.48.751.241 I slot print_timing: id 0 | task 2816224 | n_gen = 714, tg = 33.25 t/s, tg_3s = 34.73 t/s
llama-server | 11099.51.819.250 I slot print_timing: id 0 | task 2816224 | n_gen = 804, tg = 32.76 t/s, tg_3s = 29.33 t/s
llama-server | 11099.54.882.779 I slot print_timing: id 0 | task 2816224 | n_gen = 876, tg = 31.73 t/s, tg_3s = 23.50 t/s
llama-server | 11099.57.969.984 I slot print_timing: id 0 | task 2816224 | n_gen = 990, tg = 32.26 t/s, tg_3s = 36.93 t/s
llama-server | 11100.01.044.541 I slot print_timing: id 0 | task 2816224 | n_gen = 1085, tg = 32.13 t/s, tg_3s = 30.90 t/s
llama-server | 11100.04.061.323 I slot print_timing: id 0 | task 2816224 | n_gen = 1204, tg = 32.73 t/s, tg_3s = 39.45 t/s
llama-server | 11100.07.064.385 I slot print_timing: id 0 | task 2816224 | n_gen = 1306, tg = 32.83 t/s, tg_3s = 33.97 t/s
llama-server | 11100.09.917.271 I slot print_timing: id 0 | task 2816224 | prompt eval time = 38552.32 ms / 37758 tokens ( 1.02 ms per token, 979.40 tokens per second)
llama-server | 11100.09.917.274 I slot print_timing: id 0 | task 2816224 | eval time = 42608.27 ms / 1462 tokens ( 29.16 ms per token, 34.29 tokens per second)
llama-server | 11100.09.917.275 I slot print_timing: id 0 | task 2816224 | total time = 81160.59 ms / 39220 tokens
llama-server | 11100.09.917.275 I slot print_timing: id 0 | task 2816224 | graphs reused = 2727377
llama-server | 11100.09.917.278 I slot print_timing: id 0 | task 2816224 | draft acceptance = 0.40289 ( 977 accepted / 2425 generated), mean len = 3.01
llama-server | 11100.09.918.384 I slot release: id 0 | task 2816224 | stop processing: n_tokens = 39220, truncated = 0
llama-server | 11100.11.428.209 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 665942218423
llama-server | 11100.11.428.690 I slot launch_slot_: id 1 | task 2816731 | processing task, is_child = 0
llama-server | 11100.11.430.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1829.984 MiB)
llama-server | 11100.18.633.438 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1278.55 tokens per second
llama-server | 11100.20.490.532 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.65 s / 1232.08 tokens per second
llama-server | 11100.22.376.736 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.53 s / 1200.18 tokens per second
llama-server | 11100.24.311.715 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.46 s / 1174.90 tokens per second
llama-server | 11100.26.273.094 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.41 s / 1155.13 tokens per second
llama-server | 11100.28.276.660 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 16384, progress = 0.44, t = 14.40 s / 1137.71 tokens per second
llama-server | 11100.30.318.449 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.43 s / 1121.56 tokens per second
llama-server | 11100.32.398.534 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 20480, progress = 0.55, t = 18.51 s / 1106.72 tokens per second
llama-server | 11100.34.519.207 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.61 s / 1092.85 tokens per second
llama-server | 11100.36.691.033 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.77 s / 1079.51 tokens per second
llama-server | 11100.38.887.650 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 26624, progress = 0.71, t = 24.96 s / 1066.54 tokens per second
llama-server | 11100.41.121.042 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.19 s / 1054.64 tokens per second
llama-server | 11100.43.395.597 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 30720, progress = 0.82, t = 29.45 s / 1043.27 tokens per second
llama-server | 11100.45.734.833 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.75 s / 1032.10 tokens per second
llama-server | 11100.48.070.088 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 34816, progress = 0.93, t = 34.11 s / 1020.69 tokens per second
llama-server | 11100.50.443.277 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.47 s / 1010.72 tokens per second
llama-server | 11100.50.739.424 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 37033, progress = 0.99, t = 37.17 s / 996.18 tokens per second
llama-server | 11100.51.453.688 I slot print_timing: id 1 | task 2816731 | prompt processing, n_tokens = 37545, progress = 1.00, t = 37.59 s / 998.87 tokens per second
llama-server | 11100.55.077.833 I slot print_timing: id 1 | task 2816731 | n_gen = 102, tg = 29.43 t/s, tg_3s = 29.72 t/s
llama-server | 11100.58.124.695 I slot print_timing: id 1 | task 2816731 | n_gen = 198, tg = 30.41 t/s, tg_3s = 31.51 t/s
llama-server | 11101.01.183.382 I slot print_timing: id 1 | task 2816731 | n_gen = 335, tg = 35.02 t/s, tg_3s = 44.79 t/s
llama-server | 11101.01.988.706 I slot print_timing: id 1 | task 2816731 | prompt eval time = 38365.54 ms / 37549 tokens ( 1.02 ms per token, 978.72 tokens per second)
llama-server | 11101.01.988.709 I slot print_timing: id 1 | task 2816731 | eval time = 10342.86 ms / 378 tokens ( 27.43 ms per token, 36.45 tokens per second)
llama-server | 11101.01.988.710 I slot print_timing: id 1 | task 2816731 | total time = 48708.40 ms / 37927 tokens
llama-server | 11101.01.988.711 I slot print_timing: id 1 | task 2816731 | graphs reused = 2727492
llama-server | 11101.01.988.713 I slot print_timing: id 1 | task 2816731 | draft acceptance = 0.43898 ( 259 accepted / 590 generated), mean len = 3.19
llama-server | 11101.01.989.960 I slot release: id 1 | task 2816731 | stop processing: n_tokens = 37926, truncated = 0
llama-server | 11101.03.324.849 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 666025758436
llama-server | 11101.03.325.450 I slot launch_slot_: id 0 | task 2816871 | processing task, is_child = 0
llama-server | 11101.03.327.316 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1930.596 MiB)
llama-server | 11101.10.531.293 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1278.93 tokens per second
llama-server | 11101.12.388.650 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.65 s / 1232.67 tokens per second
llama-server | 11101.14.275.276 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.53 s / 1200.46 tokens per second
llama-server | 11101.16.213.219 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.46 s / 1174.73 tokens per second
llama-server | 11101.18.172.006 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.41 s / 1155.31 tokens per second
llama-server | 11101.20.173.787 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.40 s / 1137.98 tokens per second
llama-server | 11101.22.212.625 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.43 s / 1121.90 tokens per second
llama-server | 11101.24.290.546 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.50 s / 1107.26 tokens per second
llama-server | 11101.26.410.237 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.60 s / 1093.37 tokens per second
llama-server | 11101.28.582.311 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.76 s / 1079.95 tokens per second
llama-server | 11101.30.779.162 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.95 s / 1066.92 tokens per second
llama-server | 11101.33.012.041 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.18 s / 1055.02 tokens per second
llama-server | 11101.35.277.449 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.44 s / 1043.64 tokens per second
llama-server | 11101.37.612.537 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.73 s / 1032.83 tokens per second
llama-server | 11101.39.946.327 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.09 s / 1021.39 tokens per second
llama-server | 11101.42.318.611 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.45 s / 1011.42 tokens per second
llama-server | 11101.42.865.688 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 37266, progress = 0.99, t = 37.15 s / 1003.06 tokens per second
llama-server | 11101.43.585.025 I slot print_timing: id 0 | task 2816871 | prompt processing, n_tokens = 37778, progress = 1.00, t = 37.81 s / 999.07 tokens per second
llama-server | 11101.47.113.434 I slot print_timing: id 0 | task 2816871 | n_gen = 102, tg = 30.28 t/s, tg_3s = 30.57 t/s
llama-server | 11101.50.180.919 I slot print_timing: id 0 | task 2816871 | n_gen = 211, tg = 32.79 t/s, tg_3s = 35.53 t/s
llama-server | 11101.53.240.078 I slot print_timing: id 0 | task 2816871 | n_gen = 346, tg = 36.46 t/s, tg_3s = 44.13 t/s
llama-server | 11101.54.048.152 I slot print_timing: id 0 | task 2816871 | prompt eval time = 38595.94 ms / 37782 tokens ( 1.02 ms per token, 978.91 tokens per second)
llama-server | 11101.54.048.156 I slot print_timing: id 0 | task 2816871 | eval time = 10270.73 ms / 391 tokens ( 26.34 ms per token, 37.97 tokens per second)
llama-server | 11101.54.048.156 I slot print_timing: id 0 | task 2816871 | total time = 48866.67 ms / 38173 tokens
llama-server | 11101.54.048.157 I slot print_timing: id 0 | task 2816871 | graphs reused = 2727606
llama-server | 11101.54.048.160 I slot print_timing: id 0 | task 2816871 | draft acceptance = 0.46667 ( 273 accepted / 585 generated), mean len = 3.33
llama-server | 11101.54.049.272 I slot release: id 0 | task 2816871 | stop processing: n_tokens = 38172, truncated = 0
llama-server | 11101.55.577.833 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 666077830012
llama-server | 11101.55.578.562 I slot launch_slot_: id 1 | task 2817010 | processing task, is_child = 0
llama-server | 11101.55.580.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1823.734 MiB)
llama-server | 11102.02.587.610 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1280.80 tokens per second
llama-server | 11102.04.441.308 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.63 s / 1234.80 tokens per second
llama-server | 11102.06.324.175 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.51 s / 1202.65 tokens per second
llama-server | 11102.08.257.599 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.44 s / 1176.96 tokens per second
llama-server | 11102.10.219.569 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.39 s / 1157.14 tokens per second
llama-server | 11102.12.221.298 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.38 s / 1139.37 tokens per second
llama-server | 11102.14.260.548 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.41 s / 1123.04 tokens per second
llama-server | 11102.16.338.466 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.48 s / 1108.21 tokens per second
llama-server | 11102.18.457.362 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.59 s / 1094.32 tokens per second
llama-server | 11102.20.629.344 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.74 s / 1080.90 tokens per second
llama-server | 11102.22.824.541 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.93 s / 1067.74 tokens per second
llama-server | 11102.25.055.600 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.16 s / 1055.82 tokens per second
llama-server | 11102.27.320.478 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.41 s / 1044.43 tokens per second
llama-server | 11102.29.657.008 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.71 s / 1033.52 tokens per second
llama-server | 11102.31.993.596 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 34816, progress = 0.91, t = 34.07 s / 1021.96 tokens per second
llama-server | 11102.34.367.832 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 36864, progress = 0.97, t = 36.43 s / 1011.89 tokens per second
llama-server | 11102.35.379.291 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 37680, progress = 0.99, t = 37.70 s / 999.44 tokens per second
llama-server | 11102.36.133.403 I slot print_timing: id 1 | task 2817010 | prompt processing, n_tokens = 38192, progress = 1.00, t = 38.29 s / 997.46 tokens per second
llama-server | 11102.39.410.165 I slot print_timing: id 1 | task 2817010 | n_gen = 121, tg = 38.91 t/s, tg_3s = 39.23 t/s
llama-server | 11102.42.482.500 I slot print_timing: id 1 | task 2817010 | n_gen = 227, tg = 36.71 t/s, tg_3s = 34.50 t/s
llama-server | 11102.45.538.475 I slot print_timing: id 1 | task 2817010 | n_gen = 309, tg = 33.43 t/s, tg_3s = 26.83 t/s
llama-server | 11102.48.596.631 I slot print_timing: id 1 | task 2817010 | n_gen = 404, tg = 32.84 t/s, tg_3s = 31.06 t/s
llama-server | 11102.51.676.647 I slot print_timing: id 1 | task 2817010 | n_gen = 528, tg = 34.33 t/s, tg_3s = 40.26 t/s
llama-server | 11102.54.740.031 I slot print_timing: id 1 | task 2817010 | n_gen = 630, tg = 34.16 t/s, tg_3s = 33.30 t/s
llama-server | 11102.57.824.771 I slot print_timing: id 1 | task 2817010 | n_gen = 740, tg = 34.37 t/s, tg_3s = 35.66 t/s
llama-server | 11103.00.901.272 I slot print_timing: id 1 | task 2817010 | n_gen = 841, tg = 34.18 t/s, tg_3s = 32.83 t/s
llama-server | 11103.03.972.855 I slot print_timing: id 1 | task 2817010 | n_gen = 937, tg = 33.86 t/s, tg_3s = 31.25 t/s
llama-server | 11103.06.976.437 I slot print_timing: id 1 | task 2817010 | n_gen = 1029, tg = 33.54 t/s, tg_3s = 30.63 t/s
llama-server | 11103.10.051.913 I slot print_timing: id 1 | task 2817010 | n_gen = 1105, tg = 32.73 t/s, tg_3s = 24.71 t/s
llama-server | 11103.13.128.124 I slot print_timing: id 1 | task 2817010 | n_gen = 1183, tg = 32.12 t/s, tg_3s = 25.36 t/s
llama-server | 11103.16.144.305 I slot print_timing: id 1 | task 2817010 | n_gen = 1281, tg = 32.15 t/s, tg_3s = 32.49 t/s
llama-server | 11103.19.148.207 I slot print_timing: id 1 | task 2817010 | n_gen = 1395, tg = 32.55 t/s, tg_3s = 37.95 t/s
llama-server | 11103.22.173.452 I slot print_timing: id 1 | task 2817010 | n_gen = 1517, tg = 33.07 t/s, tg_3s = 40.33 t/s
llama-server | 11103.25.259.878 I slot print_timing: id 1 | task 2817010 | n_gen = 1608, tg = 32.84 t/s, tg_3s = 29.48 t/s
llama-server | 11103.28.261.178 I slot print_timing: id 1 | task 2817010 | n_gen = 1701, tg = 32.73 t/s, tg_3s = 30.99 t/s
llama-server | 11103.31.287.781 I slot print_timing: id 1 | task 2817010 | n_gen = 1790, tg = 32.55 t/s, tg_3s = 29.41 t/s
llama-server | 11103.34.292.022 I slot print_timing: id 1 | task 2817010 | n_gen = 1867, tg = 32.19 t/s, tg_3s = 25.63 t/s
llama-server | 11103.37.299.214 I slot print_timing: id 1 | task 2817010 | n_gen = 1962, tg = 32.16 t/s, tg_3s = 31.59 t/s
llama-server | 11103.40.320.376 I slot print_timing: id 1 | task 2817010 | n_gen = 2045, tg = 31.94 t/s, tg_3s = 27.47 t/s
llama-server | 11103.43.330.983 I slot print_timing: id 1 | task 2817010 | n_gen = 2127, tg = 31.73 t/s, tg_3s = 27.24 t/s
llama-server | 11103.46.342.811 I slot print_timing: id 1 | task 2817010 | n_gen = 2214, tg = 31.61 t/s, tg_3s = 28.89 t/s
llama-server | 11103.49.376.392 I slot print_timing: id 1 | task 2817010 | n_gen = 2313, tg = 31.65 t/s, tg_3s = 32.63 t/s
llama-server | 11103.50.442.313 I slot print_timing: id 1 | task 2817010 | prompt eval time = 39079.92 ms / 38196 tokens ( 1.02 ms per token, 977.38 tokens per second)
llama-server | 11103.50.442.316 I slot print_timing: id 1 | task 2817010 | eval time = 74116.27 ms / 2359 tokens ( 31.43 ms per token, 31.81 tokens per second)
llama-server | 11103.50.442.317 I slot print_timing: id 1 | task 2817010 | total time = 113196.18 ms / 40555 tokens
llama-server | 11103.50.442.317 I slot print_timing: id 1 | task 2817010 | graphs reused = 2728436
llama-server | 11103.50.442.320 I slot print_timing: id 1 | task 2817010 | draft acceptance = 0.36143 ( 1518 accepted / 4200 generated), mean len = 2.81
llama-server | 11103.50.443.425 I slot release: id 1 | task 2817010 | stop processing: n_tokens = 40554, truncated = 0
llama-server | 11103.54.144.662 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 666129889324
llama-server | 11103.54.145.220 I slot launch_slot_: id 0 | task 2817872 | processing task, is_child = 0
llama-server | 11103.54.148.110 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1833.243 MiB)
llama-server | 11104.00.650.587 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1278.88 tokens per second
llama-server | 11104.02.517.837 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.66 s / 1229.91 tokens per second
llama-server | 11104.04.401.519 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.54 s / 1198.80 tokens per second
llama-server | 11104.06.323.837 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.45 s / 1175.38 tokens per second
llama-server | 11104.08.283.640 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.41 s / 1155.65 tokens per second
llama-server | 11104.10.286.335 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.40 s / 1138.15 tokens per second
llama-server | 11104.12.324.992 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.43 s / 1122.01 tokens per second
llama-server | 11104.14.402.577 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.49 s / 1107.43 tokens per second
llama-server | 11104.16.519.819 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.60 s / 1093.62 tokens per second
llama-server | 11104.18.694.606 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.75 s / 1080.31 tokens per second
llama-server | 11104.20.890.992 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 26624, progress = 0.69, t = 24.95 s / 1067.08 tokens per second
llama-server | 11104.23.123.579 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 28672, progress = 0.74, t = 27.17 s / 1055.16 tokens per second
llama-server | 11104.25.390.169 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 30720, progress = 0.79, t = 29.43 s / 1043.75 tokens per second
llama-server | 11104.27.725.393 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 32768, progress = 0.85, t = 31.72 s / 1032.93 tokens per second
llama-server | 11104.30.062.444 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 34816, progress = 0.90, t = 34.09 s / 1021.41 tokens per second
llama-server | 11104.32.446.200 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 36864, progress = 0.95, t = 36.45 s / 1011.34 tokens per second
llama-server | 11104.34.108.770 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 38223, progress = 0.99, t = 38.29 s / 998.14 tokens per second
llama-server | 11104.34.850.761 I slot print_timing: id 0 | task 2817872 | prompt processing, n_tokens = 38735, progress = 1.00, t = 38.95 s / 994.50 tokens per second
llama-server | 11104.38.200.544 I slot print_timing: id 0 | task 2817872 | n_gen = 100, tg = 31.85 t/s, tg_3s = 32.17 t/s
llama-server | 11104.38.730.069 I slot print_timing: id 0 | task 2817872 | prompt eval time = 39796.06 ms / 38739 tokens ( 1.03 ms per token, 973.44 tokens per second)
llama-server | 11104.38.730.072 I slot print_timing: id 0 | task 2817872 | eval time = 3637.66 ms / 133 tokens ( 27.56 ms per token, 36.29 tokens per second)
llama-server | 11104.38.730.073 I slot print_timing: id 0 | task 2817872 | total time = 43433.72 ms / 38872 tokens
llama-server | 11104.38.730.074 I slot print_timing: id 0 | task 2817872 | graphs reused = 2728476
llama-server | 11104.38.730.078 I slot print_timing: id 0 | task 2817872 | draft acceptance = 0.44878 ( 92 accepted / 205 generated), mean len = 3.24
llama-server | 11104.38.731.363 I slot release: id 0 | task 2817872 | stop processing: n_tokens = 38872, truncated = 0
llama-server | 11104.40.023.964 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 666246283477
llama-server | 11104.40.024.511 I slot launch_slot_: id 1 | task 2817935 | processing task, is_child = 0
llama-server | 11104.40.026.389 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1873.042 MiB)
llama-server | 11104.46.834.512 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.79 s / 1281.53 tokens per second
llama-server | 11104.48.685.803 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.63 s / 1235.34 tokens per second
llama-server | 11104.50.569.359 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.51 s / 1203.33 tokens per second
llama-server | 11104.52.501.355 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.43 s / 1177.84 tokens per second
llama-server | 11104.54.465.911 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.38 s / 1157.68 tokens per second
llama-server | 11104.56.466.224 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.38 s / 1139.72 tokens per second
llama-server | 11104.58.503.650 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.41 s / 1123.49 tokens per second
llama-server | 11105.00.579.855 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.47 s / 1108.72 tokens per second
llama-server | 11105.02.695.110 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.58 s / 1094.86 tokens per second
llama-server | 11105.04.863.406 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.72 s / 1081.53 tokens per second
llama-server | 11105.07.055.994 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 26624, progress = 0.69, t = 24.92 s / 1068.48 tokens per second
llama-server | 11105.09.287.006 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 28672, progress = 0.74, t = 27.14 s / 1056.54 tokens per second
llama-server | 11105.11.551.052 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.39 s / 1045.10 tokens per second
llama-server | 11105.13.886.352 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 32768, progress = 0.85, t = 31.68 s / 1034.19 tokens per second
llama-server | 11105.16.221.298 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 34816, progress = 0.90, t = 34.05 s / 1022.59 tokens per second
llama-server | 11105.18.595.724 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 36864, progress = 0.95, t = 36.41 s / 1012.54 tokens per second
llama-server | 11105.20.107.963 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 38091, progress = 0.99, t = 38.24 s / 996.05 tokens per second
llama-server | 11105.20.835.641 I slot print_timing: id 1 | task 2817935 | prompt processing, n_tokens = 38603, progress = 1.00, t = 38.75 s / 996.22 tokens per second
llama-server | 11105.24.570.918 I slot print_timing: id 1 | task 2817935 | n_gen = 101, tg = 28.24 t/s, tg_3s = 28.52 t/s
llama-server | 11105.27.634.739 I slot print_timing: id 1 | task 2817935 | n_gen = 218, tg = 32.85 t/s, tg_3s = 38.19 t/s
llama-server | 11105.30.715.029 I slot print_timing: id 1 | task 2817935 | n_gen = 328, tg = 33.76 t/s, tg_3s = 35.71 t/s
llama-server | 11105.33.784.454 I slot print_timing: id 1 | task 2817935 | n_gen = 434, tg = 33.95 t/s, tg_3s = 34.53 t/s
llama-server | 11105.36.859.136 I slot print_timing: id 1 | task 2817935 | n_gen = 537, tg = 33.86 t/s, tg_3s = 33.50 t/s
llama-server | 11105.39.863.616 I slot print_timing: id 1 | task 2817935 | n_gen = 636, tg = 33.72 t/s, tg_3s = 32.95 t/s
llama-server | 11105.42.939.494 I slot print_timing: id 1 | task 2817935 | n_gen = 723, tg = 32.95 t/s, tg_3s = 28.28 t/s
llama-server | 11105.46.021.501 I slot print_timing: id 1 | task 2817935 | n_gen = 802, tg = 32.05 t/s, tg_3s = 25.63 t/s
llama-server | 11105.49.034.823 I slot print_timing: id 1 | task 2817935 | n_gen = 921, tg = 32.85 t/s, tg_3s = 39.49 t/s
llama-server | 11105.52.038.798 I slot print_timing: id 1 | task 2817935 | n_gen = 1055, tg = 33.99 t/s, tg_3s = 44.61 t/s
llama-server | 11105.55.050.091 I slot print_timing: id 1 | task 2817935 | n_gen = 1151, tg = 33.80 t/s, tg_3s = 31.88 t/s
llama-server | 11105.58.055.722 I slot print_timing: id 1 | task 2817935 | n_gen = 1248, tg = 33.68 t/s, tg_3s = 32.27 t/s
llama-server | 11106.01.075.258 I slot print_timing: id 1 | task 2817935 | n_gen = 1343, tg = 33.51 t/s, tg_3s = 31.46 t/s
llama-server | 11106.03.733.142 I slot print_timing: id 1 | task 2817935 | prompt eval time = 39533.76 ms / 38607 tokens ( 1.02 ms per token, 976.56 tokens per second)
llama-server | 11106.03.733.145 I slot print_timing: id 1 | task 2817935 | eval time = 42703.26 ms / 1439 tokens ( 29.70 ms per token, 33.67 tokens per second)
llama-server | 11106.03.733.145 I slot print_timing: id 1 | task 2817935 | total time = 82237.03 ms / 40046 tokens
llama-server | 11106.03.733.146 I slot print_timing: id 1 | task 2817935 | graphs reused = 2728953
llama-server | 11106.03.733.149 I slot print_timing: id 1 | task 2817935 | draft acceptance = 0.39421 ( 954 accepted / 2420 generated), mean len = 2.97
llama-server | 11106.03.734.261 I slot release: id 1 | task 2817935 | stop processing: n_tokens = 40045, truncated = 0
llama-server | 11106.05.121.987 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 666294571416
llama-server | 11106.05.122.610 I slot launch_slot_: id 0 | task 2818441 | processing task, is_child = 0
llama-server | 11106.05.124.525 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1830.018 MiB)
llama-server | 11106.10.160.269 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.00 s / 1364.48 tokens per second
llama-server | 11106.11.976.069 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1277.51 tokens per second
llama-server | 11106.13.833.702 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.65 s / 1231.68 tokens per second
llama-server | 11106.15.721.442 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.54 s / 1199.70 tokens per second
llama-server | 11106.17.647.482 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.45 s / 1175.63 tokens per second
llama-server | 11106.19.622.933 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.42 s / 1154.37 tokens per second
llama-server | 11106.21.628.526 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 16384, progress = 0.44, t = 14.41 s / 1136.92 tokens per second
llama-server | 11106.23.668.823 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.45 s / 1120.81 tokens per second
llama-server | 11106.25.748.758 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.51 s / 1106.19 tokens per second
llama-server | 11106.27.870.350 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.62 s / 1092.29 tokens per second
llama-server | 11106.30.047.938 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.78 s / 1078.94 tokens per second
llama-server | 11106.32.244.500 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 26624, progress = 0.71, t = 24.98 s / 1065.79 tokens per second
llama-server | 11106.34.477.499 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.20 s / 1054.05 tokens per second
llama-server | 11106.36.745.419 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 30720, progress = 0.82, t = 29.46 s / 1042.69 tokens per second
llama-server | 11106.39.082.796 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.76 s / 1031.88 tokens per second
llama-server | 11106.41.420.289 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 34816, progress = 0.93, t = 34.12 s / 1020.44 tokens per second
llama-server | 11106.43.795.102 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.48 s / 1010.42 tokens per second
llama-server | 11106.44.123.669 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 37088, progress = 0.99, t = 37.19 s / 997.35 tokens per second
llama-server | 11106.44.842.107 I slot print_timing: id 0 | task 2818441 | prompt processing, n_tokens = 37600, progress = 1.00, t = 37.63 s / 999.10 tokens per second
llama-server | 11106.48.036.460 I slot print_timing: id 0 | task 2818441 | n_gen = 123, tg = 40.64 t/s, tg_3s = 40.97 t/s
llama-server | 11106.48.123.589 I slot print_timing: id 0 | task 2818441 | prompt eval time = 38413.17 ms / 37604 tokens ( 1.02 ms per token, 978.94 tokens per second)
llama-server | 11106.48.123.592 I slot print_timing: id 0 | task 2818441 | eval time = 3089.17 ms / 125 tokens ( 24.91 ms per token, 40.14 tokens per second)
llama-server | 11106.48.123.593 I slot print_timing: id 0 | task 2818441 | total time = 41502.33 ms / 37729 tokens
llama-server | 11106.48.123.593 I slot print_timing: id 0 | task 2818441 | graphs reused = 2728986
llama-server | 11106.48.123.596 I slot print_timing: id 0 | task 2818441 | draft acceptance = 0.50857 ( 89 accepted / 175 generated), mean len = 3.54
llama-server | 11106.48.124.796 I slot release: id 0 | task 2818441 | stop processing: n_tokens = 37728, truncated = 0
llama-server | 11106.49.391.601 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 666379574313
llama-server | 11106.49.392.429 I slot launch_slot_: id 1 | task 2818498 | processing task, is_child = 0
llama-server | 11106.49.394.193 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1838.197 MiB)
llama-server | 11106.55.889.554 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1278.97 tokens per second
llama-server | 11106.57.740.730 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.64 s / 1232.82 tokens per second
llama-server | 11106.59.625.015 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.52 s / 1201.52 tokens per second
llama-server | 11107.01.554.223 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.44 s / 1176.69 tokens per second
llama-server | 11107.03.518.577 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.39 s / 1156.83 tokens per second
llama-server | 11107.05.519.943 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.39 s / 1138.89 tokens per second
llama-server | 11107.07.558.263 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.42 s / 1122.74 tokens per second
llama-server | 11107.09.635.962 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.49 s / 1107.92 tokens per second
llama-server | 11107.11.752.537 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 22528, progress = 0.59, t = 20.59 s / 1094.19 tokens per second
llama-server | 11107.13.923.012 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.74 s / 1080.80 tokens per second
llama-server | 11107.16.116.049 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.93 s / 1067.74 tokens per second
llama-server | 11107.18.349.504 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 28672, progress = 0.75, t = 27.15 s / 1055.97 tokens per second
llama-server | 11107.20.616.590 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.42 s / 1044.34 tokens per second
llama-server | 11107.22.950.362 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 32768, progress = 0.86, t = 31.71 s / 1033.49 tokens per second
llama-server | 11107.25.284.519 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.07 s / 1021.97 tokens per second
llama-server | 11107.27.657.382 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 36864, progress = 0.97, t = 36.43 s / 1011.94 tokens per second
llama-server | 11107.28.438.477 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 37466, progress = 0.99, t = 37.70 s / 993.89 tokens per second
llama-server | 11107.29.196.166 I slot print_timing: id 1 | task 2818498 | prompt processing, n_tokens = 37978, progress = 1.00, t = 38.07 s / 997.59 tokens per second
llama-server | 11107.32.984.014 I slot print_timing: id 1 | task 2818498 | n_gen = 104, tg = 28.61 t/s, tg_3s = 28.88 t/s
llama-server | 11107.36.053.693 I slot print_timing: id 1 | task 2818498 | n_gen = 205, tg = 30.58 t/s, tg_3s = 32.90 t/s
llama-server | 11107.39.108.812 I slot print_timing: id 1 | task 2818498 | n_gen = 305, tg = 31.26 t/s, tg_3s = 32.73 t/s
llama-server | 11107.42.166.017 I slot print_timing: id 1 | task 2818498 | n_gen = 419, tg = 32.70 t/s, tg_3s = 37.29 t/s
llama-server | 11107.45.245.602 I slot print_timing: id 1 | task 2818498 | n_gen = 541, tg = 34.04 t/s, tg_3s = 39.62 t/s
llama-server | 11107.48.307.557 I slot print_timing: id 1 | task 2818498 | n_gen = 652, tg = 34.40 t/s, tg_3s = 36.25 t/s
llama-server | 11107.51.392.086 I slot print_timing: id 1 | task 2818498 | n_gen = 741, tg = 33.62 t/s, tg_3s = 28.85 t/s
llama-server | 11107.54.461.701 I slot print_timing: id 1 | task 2818498 | n_gen = 828, tg = 32.98 t/s, tg_3s = 28.34 t/s
llama-server | 11107.57.531.479 I slot print_timing: id 1 | task 2818498 | n_gen = 927, tg = 32.90 t/s, tg_3s = 32.25 t/s
llama-server | 11108.00.538.697 I slot print_timing: id 1 | task 2818498 | n_gen = 1031, tg = 33.06 t/s, tg_3s = 34.58 t/s
llama-server | 11108.03.616.656 I slot print_timing: id 1 | task 2818498 | n_gen = 1115, tg = 32.54 t/s, tg_3s = 27.29 t/s
llama-server | 11108.06.626.317 I slot print_timing: id 1 | task 2818498 | n_gen = 1216, tg = 32.62 t/s, tg_3s = 33.56 t/s
llama-server | 11108.08.658.231 I slot print_timing: id 1 | task 2818498 | prompt eval time = 38844.38 ms / 37982 tokens ( 1.02 ms per token, 977.80 tokens per second)
llama-server | 11108.08.658.235 I slot print_timing: id 1 | task 2818498 | eval time = 39274.73 ms / 1312 tokens ( 29.96 ms per token, 33.38 tokens per second)
llama-server | 11108.08.658.236 I slot print_timing: id 1 | task 2818498 | total time = 78119.11 ms / 39294 tokens
llama-server | 11108.08.658.236 I slot print_timing: id 1 | task 2818498 | graphs reused = 2729427
llama-server | 11108.08.658.241 I slot print_timing: id 1 | task 2818498 | draft acceptance = 0.38702 ( 865 accepted / 2235 generated), mean len = 2.94
llama-server | 11108.08.659.330 I slot release: id 1 | task 2818498 | stop processing: n_tokens = 39294, truncated = 0
llama-server | 11108.10.196.481 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 666423964849
llama-server | 11108.10.197.030 I slot launch_slot_: id 0 | task 2818967 | processing task, is_child = 0
llama-server | 11108.10.199.044 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1917.396 MiB)
llama-server | 11108.14.876.283 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.00 s / 1363.32 tokens per second
llama-server | 11108.16.693.118 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.81 s / 1277.02 tokens per second
llama-server | 11108.18.549.519 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.65 s / 1231.20 tokens per second
llama-server | 11108.20.436.796 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.54 s / 1199.39 tokens per second
llama-server | 11108.22.363.120 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.45 s / 1175.38 tokens per second
llama-server | 11108.24.340.637 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.42 s / 1154.42 tokens per second
llama-server | 11108.26.345.359 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 16384, progress = 0.44, t = 14.41 s / 1136.65 tokens per second
llama-server | 11108.28.384.733 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.45 s / 1120.64 tokens per second
llama-server | 11108.30.463.616 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 20480, progress = 0.55, t = 18.52 s / 1106.08 tokens per second
llama-server | 11108.32.583.144 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.62 s / 1092.37 tokens per second
llama-server | 11108.34.754.467 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 24576, progress = 0.66, t = 22.77 s / 1079.12 tokens per second
llama-server | 11108.36.949.432 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 26624, progress = 0.71, t = 24.97 s / 1066.20 tokens per second
llama-server | 11108.39.183.844 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 28672, progress = 0.77, t = 27.19 s / 1054.34 tokens per second
llama-server | 11108.41.451.100 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 30720, progress = 0.82, t = 29.45 s / 1042.97 tokens per second
llama-server | 11108.43.789.596 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.75 s / 1032.11 tokens per second
llama-server | 11108.46.127.071 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 34816, progress = 0.93, t = 34.11 s / 1020.64 tokens per second
llama-server | 11108.48.501.711 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.48 s / 1010.65 tokens per second
llama-server | 11108.48.687.251 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 36950, progress = 0.99, t = 37.18 s / 993.88 tokens per second
llama-server | 11108.49.403.739 I slot print_timing: id 0 | task 2818967 | prompt processing, n_tokens = 37462, progress = 1.00, t = 37.48 s / 999.58 tokens per second
llama-server | 11108.52.711.246 I slot print_timing: id 0 | task 2818967 | n_gen = 104, tg = 33.56 t/s, tg_3s = 33.88 t/s
llama-server | 11108.55.783.552 I slot print_timing: id 0 | task 2818967 | n_gen = 226, tg = 36.64 t/s, tg_3s = 39.71 t/s
llama-server | 11108.57.966.607 I slot print_timing: id 0 | task 2818967 | prompt eval time = 38306.87 ms / 37466 tokens ( 1.02 ms per token, 978.05 tokens per second)
llama-server | 11108.57.966.610 I slot print_timing: id 0 | task 2818967 | eval time = 8324.63 ms / 325 tokens ( 25.69 ms per token, 38.92 tokens per second)
llama-server | 11108.57.966.611 I slot print_timing: id 0 | task 2818967 | total time = 46631.51 ms / 37791 tokens
llama-server | 11108.57.966.611 I slot print_timing: id 0 | task 2818967 | graphs reused = 2729520
llama-server | 11108.57.966.614 I slot print_timing: id 0 | task 2818967 | draft acceptance = 0.48211 ( 229 accepted / 475 generated), mean len = 3.41
llama-server | 11108.57.967.784 I slot release: id 0 | task 2818967 | stop processing: n_tokens = 37790, truncated = 0
llama-server | 11108.59.254.137 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 666504499383
llama-server | 11108.59.254.877 I slot launch_slot_: id 1 | task 2819084 | processing task, is_child = 0
llama-server | 11108.59.256.659 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1861.471 MiB)
llama-server | 11109.06.102.371 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1280.00 tokens per second
llama-server | 11109.07.952.540 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.64 s / 1233.76 tokens per second
llama-server | 11109.09.834.850 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.52 s / 1202.50 tokens per second
llama-server | 11109.11.765.014 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 12288, progress = 0.33, t = 10.44 s / 1177.44 tokens per second
llama-server | 11109.13.731.467 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.39 s / 1157.48 tokens per second
llama-server | 11109.15.732.975 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.38 s / 1139.24 tokens per second
llama-server | 11109.17.770.521 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.41 s / 1123.11 tokens per second
llama-server | 11109.19.847.048 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.48 s / 1108.29 tokens per second
llama-server | 11109.21.966.911 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.58 s / 1094.51 tokens per second
llama-server | 11109.24.145.538 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.74 s / 1080.89 tokens per second
llama-server | 11109.26.342.811 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.94 s / 1067.41 tokens per second
llama-server | 11109.28.573.755 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.16 s / 1055.52 tokens per second
llama-server | 11109.30.840.830 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.42 s / 1044.02 tokens per second
llama-server | 11109.33.177.058 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.71 s / 1033.22 tokens per second
llama-server | 11109.35.512.495 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.08 s / 1021.67 tokens per second
llama-server | 11109.37.885.354 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 36864, progress = 0.98, t = 36.44 s / 1011.65 tokens per second
llama-server | 11109.38.430.313 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 37264, progress = 0.99, t = 37.14 s / 1003.23 tokens per second
llama-server | 11109.39.169.542 I slot print_timing: id 1 | task 2819084 | prompt processing, n_tokens = 37776, progress = 1.00, t = 37.82 s / 998.79 tokens per second
llama-server | 11109.43.165.285 I slot print_timing: id 1 | task 2819084 | n_gen = 100, tg = 26.36 t/s, tg_3s = 26.62 t/s
llama-server | 11109.46.235.281 I slot print_timing: id 1 | task 2819084 | n_gen = 225, tg = 32.82 t/s, tg_3s = 40.72 t/s
llama-server | 11109.49.290.470 I slot print_timing: id 1 | task 2819084 | n_gen = 353, tg = 35.62 t/s, tg_3s = 41.90 t/s
llama-server | 11109.52.362.402 I slot print_timing: id 1 | task 2819084 | n_gen = 462, tg = 35.59 t/s, tg_3s = 35.48 t/s
llama-server | 11109.55.420.869 I slot print_timing: id 1 | task 2819084 | n_gen = 594, tg = 37.04 t/s, tg_3s = 43.16 t/s
llama-server | 11109.58.498.040 I slot print_timing: id 1 | task 2819084 | n_gen = 713, tg = 37.30 t/s, tg_3s = 38.67 t/s
llama-server | 11110.01.564.391 I slot print_timing: id 1 | task 2819084 | n_gen = 831, tg = 37.46 t/s, tg_3s = 38.48 t/s
llama-server | 11110.04.568.713 I slot print_timing: id 1 | task 2819084 | n_gen = 977, tg = 38.79 t/s, tg_3s = 48.60 t/s
llama-server | 11110.07.642.202 I slot print_timing: id 1 | task 2819084 | n_gen = 1092, tg = 38.64 t/s, tg_3s = 37.42 t/s
llama-server | 11110.10.648.481 I slot print_timing: id 1 | task 2819084 | n_gen = 1203, tg = 38.48 t/s, tg_3s = 36.92 t/s
llama-server | 11110.13.725.651 I slot print_timing: id 1 | task 2819084 | n_gen = 1314, tg = 38.26 t/s, tg_3s = 36.07 t/s
llama-server | 11110.16.732.378 I slot print_timing: id 1 | task 2819084 | n_gen = 1407, tg = 37.67 t/s, tg_3s = 30.93 t/s
llama-server | 11110.19.812.375 I slot print_timing: id 1 | task 2819084 | n_gen = 1494, tg = 36.95 t/s, tg_3s = 28.25 t/s
llama-server | 11110.22.895.156 I slot print_timing: id 1 | task 2819084 | n_gen = 1620, tg = 37.23 t/s, tg_3s = 40.87 t/s
llama-server | 11110.25.907.409 I slot print_timing: id 1 | task 2819084 | n_gen = 1737, tg = 37.34 t/s, tg_3s = 38.84 t/s
llama-server | 11110.28.911.817 I slot print_timing: id 1 | task 2819084 | n_gen = 1860, tg = 37.55 t/s, tg_3s = 40.94 t/s
llama-server | 11110.31.933.353 I slot print_timing: id 1 | task 2819084 | n_gen = 1986, tg = 37.79 t/s, tg_3s = 41.70 t/s
llama-server | 11110.34.937.133 I slot print_timing: id 1 | task 2819084 | n_gen = 2084, tg = 37.51 t/s, tg_3s = 32.63 t/s
llama-server | 11110.37.962.032 I slot print_timing: id 1 | task 2819084 | n_gen = 2195, tg = 37.47 t/s, tg_3s = 36.70 t/s
llama-server | 11110.40.974.551 I slot print_timing: id 1 | task 2819084 | n_gen = 2315, tg = 37.59 t/s, tg_3s = 39.83 t/s
llama-server | 11110.43.984.360 I slot print_timing: id 1 | task 2819084 | n_gen = 2403, tg = 37.20 t/s, tg_3s = 29.24 t/s
llama-server | 11110.47.010.999 I slot print_timing: id 1 | task 2819084 | n_gen = 2483, tg = 36.72 t/s, tg_3s = 26.43 t/s
llama-server | 11110.50.024.637 I slot print_timing: id 1 | task 2819084 | n_gen = 2587, tg = 36.62 t/s, tg_3s = 34.51 t/s
llama-server | 11110.53.060.119 I slot print_timing: id 1 | task 2819084 | n_gen = 2709, tg = 36.77 t/s, tg_3s = 40.19 t/s
llama-server | 11110.56.075.225 I slot print_timing: id 1 | task 2819084 | n_gen = 2818, tg = 36.74 t/s, tg_3s = 36.15 t/s
llama-server | 11110.59.095.366 I slot print_timing: id 1 | task 2819084 | n_gen = 2919, tg = 36.62 t/s, tg_3s = 33.44 t/s
llama-server | 11111.02.131.910 I slot print_timing: id 1 | task 2819084 | n_gen = 3007, tg = 36.34 t/s, tg_3s = 28.98 t/s
llama-server | 11111.05.151.690 I slot print_timing: id 1 | task 2819084 | n_gen = 3109, tg = 36.25 t/s, tg_3s = 33.78 t/s
llama-server | 11111.08.191.954 I slot print_timing: id 1 | task 2819084 | n_gen = 3209, tg = 36.13 t/s, tg_3s = 32.89 t/s
llama-server | 11111.11.223.455 I slot print_timing: id 1 | task 2819084 | n_gen = 3326, tg = 36.21 t/s, tg_3s = 38.59 t/s
llama-server | 11111.14.275.493 I slot print_timing: id 1 | task 2819084 | n_gen = 3449, tg = 36.35 t/s, tg_3s = 40.30 t/s
llama-server | 11111.17.309.320 I slot print_timing: id 1 | task 2819084 | n_gen = 3546, tg = 36.21 t/s, tg_3s = 31.97 t/s
llama-server | 11111.20.348.803 I slot print_timing: id 1 | task 2819084 | n_gen = 3665, tg = 36.30 t/s, tg_3s = 39.15 t/s
llama-server | 11111.23.411.294 I slot print_timing: id 1 | task 2819084 | n_gen = 3791, tg = 36.44 t/s, tg_3s = 41.14 t/s
llama-server | 11111.23.857.328 I slot print_timing: id 1 | task 2819084 | prompt eval time = 38652.97 ms / 37780 tokens ( 1.02 ms per token, 977.42 tokens per second)
llama-server | 11111.23.857.332 I slot print_timing: id 1 | task 2819084 | eval time = 104447.83 ms / 3807 tokens ( 27.44 ms per token, 36.44 tokens per second)
llama-server | 11111.23.857.332 I slot print_timing: id 1 | task 2819084 | total time = 143100.79 ms / 41587 tokens
llama-server | 11111.23.857.333 I slot print_timing: id 1 | task 2819084 | graphs reused = 2730684
llama-server | 11111.23.857.335 I slot print_timing: id 1 | task 2819084 | draft acceptance = 0.44508 ( 2626 accepted / 5900 generated), mean len = 3.23
llama-server | 11111.23.858.412 I slot release: id 1 | task 2819084 | stop processing: n_tokens = 41586, truncated = 0
llama-server | 11111.25.390.406 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 666553807836
llama-server | 11111.25.391.173 I slot launch_slot_: id 0 | task 2820286 | processing task, is_child = 0
llama-server | 11111.25.393.177 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1900.472 MiB)
llama-server | 11111.30.641.577 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 4096, progress = 0.11, t = 3.01 s / 1361.16 tokens per second
llama-server | 11111.32.461.933 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.82 s / 1275.46 tokens per second
llama-server | 11111.34.319.606 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 8192, progress = 0.22, t = 6.66 s / 1229.57 tokens per second
llama-server | 11111.36.207.539 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.55 s / 1198.06 tokens per second
llama-server | 11111.38.133.690 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.46 s / 1174.32 tokens per second
llama-server | 11111.40.107.673 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 14336, progress = 0.38, t = 12.43 s / 1153.29 tokens per second
llama-server | 11111.42.112.832 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.42 s / 1136.09 tokens per second
llama-server | 11111.44.153.043 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 18432, progress = 0.49, t = 16.46 s / 1120.14 tokens per second
llama-server | 11111.46.233.292 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 20480, progress = 0.54, t = 18.52 s / 1105.55 tokens per second
llama-server | 11111.48.352.212 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 22528, progress = 0.60, t = 20.63 s / 1091.90 tokens per second
llama-server | 11111.50.526.589 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 24576, progress = 0.65, t = 22.79 s / 1078.57 tokens per second
llama-server | 11111.52.722.772 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 26624, progress = 0.70, t = 24.98 s / 1065.70 tokens per second
llama-server | 11111.54.954.967 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 28672, progress = 0.76, t = 27.21 s / 1053.92 tokens per second
llama-server | 11111.57.222.684 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 30720, progress = 0.81, t = 29.47 s / 1042.58 tokens per second
llama-server | 11111.59.560.992 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 32768, progress = 0.87, t = 31.76 s / 1031.76 tokens per second
llama-server | 11112.01.898.826 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 34816, progress = 0.92, t = 34.12 s / 1020.28 tokens per second
llama-server | 11112.04.273.611 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 36864, progress = 0.97, t = 36.49 s / 1010.29 tokens per second
llama-server | 11112.04.864.132 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 37326, progress = 0.99, t = 37.19 s / 1003.55 tokens per second
llama-server | 11112.05.578.426 I slot print_timing: id 0 | task 2820286 | prompt processing, n_tokens = 37838, progress = 1.00, t = 37.89 s / 998.60 tokens per second
llama-server | 11112.10.152.618 I slot print_timing: id 0 | task 2820286 | n_gen = 103, tg = 23.28 t/s, tg_3s = 23.51 t/s
llama-server | 11112.13.208.560 I slot print_timing: id 0 | task 2820286 | n_gen = 219, tg = 29.31 t/s, tg_3s = 37.96 t/s
llama-server | 11112.13.907.998 I slot print_timing: id 0 | task 2820286 | prompt eval time = 38675.07 ms / 37842 tokens ( 1.02 ms per token, 978.46 tokens per second)
llama-server | 11112.13.908.001 I slot print_timing: id 0 | task 2820286 | eval time = 8137.18 ms / 251 tokens ( 32.55 ms per token, 30.72 tokens per second)
llama-server | 11112.13.908.002 I slot print_timing: id 0 | task 2820286 | total time = 46812.25 ms / 38093 tokens
llama-server | 11112.13.908.002 I slot print_timing: id 0 | task 2820286 | graphs reused = 2730775
llama-server | 11112.13.908.005 I slot print_timing: id 0 | task 2820286 | draft acceptance = 0.33763 ( 157 accepted / 465 generated), mean len = 2.69
llama-server | 11112.13.909.096 I slot release: id 0 | task 2820286 | stop processing: n_tokens = 38092, truncated = 0
llama-server | 11112.28.364.946 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 666699698464
llama-server | 11112.28.365.609 I slot launch_slot_: id 1 | task 2820401 | processing task, is_child = 0
llama-server | 11112.28.368.265 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1823.434 MiB)
llama-server | 11112.34.800.376 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.75 s / 1293.15 tokens per second
llama-server | 11112.36.629.607 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.58 s / 1245.84 tokens per second
llama-server | 11112.38.492.908 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 10240, progress = 0.27, t = 8.43 s / 1214.46 tokens per second
llama-server | 11112.40.394.882 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 12288, progress = 0.32, t = 10.32 s / 1190.22 tokens per second
llama-server | 11112.42.337.095 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.26 s / 1169.66 tokens per second
llama-server | 11112.44.320.643 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 16384, progress = 0.43, t = 14.23 s / 1151.60 tokens per second
llama-server | 11112.46.342.944 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 18432, progress = 0.48, t = 16.24 s / 1134.84 tokens per second
llama-server | 11112.48.406.289 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 20480, progress = 0.53, t = 18.29 s / 1119.49 tokens per second
llama-server | 11112.50.509.260 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.39 s / 1105.08 tokens per second
llama-server | 11112.52.670.192 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 24576, progress = 0.64, t = 22.52 s / 1091.07 tokens per second
llama-server | 11112.54.854.980 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 26624, progress = 0.69, t = 24.71 s / 1077.43 tokens per second
llama-server | 11112.57.078.816 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 28672, progress = 0.74, t = 26.92 s / 1064.94 tokens per second
llama-server | 11112.59.336.245 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 30720, progress = 0.80, t = 29.17 s / 1052.99 tokens per second
llama-server | 11113.01.664.145 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 32768, progress = 0.85, t = 31.46 s / 1041.66 tokens per second
llama-server | 11113.03.994.831 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 34816, progress = 0.90, t = 33.81 s / 1029.61 tokens per second
llama-server | 11113.06.363.921 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 36864, progress = 0.96, t = 36.17 s / 1019.13 tokens per second
llama-server | 11113.07.744.346 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 37996, progress = 0.99, t = 38.00 s / 999.89 tokens per second
llama-server | 11113.08.476.493 I slot print_timing: id 1 | task 2820401 | prompt processing, n_tokens = 38508, progress = 1.00, t = 38.39 s / 1003.20 tokens per second
llama-server | 11113.11.747.437 I slot print_timing: id 1 | task 2820401 | n_gen = 119, tg = 38.34 t/s, tg_3s = 38.66 t/s
llama-server | 11113.14.825.313 I slot print_timing: id 1 | task 2820401 | n_gen = 218, tg = 35.25 t/s, tg_3s = 32.17 t/s
llama-server | 11113.17.893.613 I slot print_timing: id 1 | task 2820401 | n_gen = 362, tg = 39.14 t/s, tg_3s = 46.93 t/s
llama-server | 11113.18.421.438 I slot print_timing: id 1 | task 2820401 | prompt eval time = 39166.69 ms / 38512 tokens ( 1.02 ms per token, 983.28 tokens per second)
llama-server | 11113.18.421.441 I slot print_timing: id 1 | task 2820401 | eval time = 9751.83 ms / 396 tokens ( 24.69 ms per token, 40.51 tokens per second)
llama-server | 11113.18.421.442 I slot print_timing: id 1 | task 2820401 | total time = 48918.53 ms / 38908 tokens
llama-server | 11113.18.421.442 I slot print_timing: id 1 | task 2820401 | graphs reused = 2730884
llama-server | 11113.18.421.455 I slot print_timing: id 1 | task 2820401 | draft acceptance = 0.51171 ( 284 accepted / 555 generated), mean len = 3.56
llama-server | 11113.18.422.730 I slot release: id 1 | task 2820401 | stop processing: n_tokens = 38907, truncated = 0
llama-server | 11113.32.087.416 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 666749749148
llama-server | 11113.32.088.048 I slot launch_slot_: id 0 | task 2820534 | processing task, is_child = 0
llama-server | 11113.32.090.787 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1875.502 MiB)
llama-server | 11113.38.484.333 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.75 s / 1293.49 tokens per second
llama-server | 11113.40.311.327 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.57 s / 1247.56 tokens per second
llama-server | 11113.42.173.389 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.42 s / 1216.04 tokens per second
llama-server | 11113.44.080.298 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.31 s / 1191.65 tokens per second
llama-server | 11113.46.023.496 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.25 s / 1170.26 tokens per second
llama-server | 11113.48.007.572 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.22 s / 1152.09 tokens per second
llama-server | 11113.50.030.135 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.24 s / 1135.23 tokens per second
llama-server | 11113.52.094.701 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.29 s / 1119.77 tokens per second
llama-server | 11113.54.200.706 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.38 s / 1105.22 tokens per second
llama-server | 11113.56.360.767 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.52 s / 1091.15 tokens per second
llama-server | 11113.58.542.865 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 26624, progress = 0.68, t = 24.71 s / 1077.58 tokens per second
llama-server | 11114.00.769.470 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 28672, progress = 0.73, t = 26.92 s / 1065.16 tokens per second
llama-server | 11114.03.028.121 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 30720, progress = 0.79, t = 29.17 s / 1053.07 tokens per second
llama-server | 11114.05.357.528 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.46 s / 1041.70 tokens per second
llama-server | 11114.07.686.545 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 34816, progress = 0.89, t = 33.81 s / 1029.64 tokens per second
llama-server | 11114.10.055.205 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 36864, progress = 0.94, t = 36.17 s / 1019.15 tokens per second
llama-server | 11114.12.030.758 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 38498, progress = 0.99, t = 38.56 s / 998.31 tokens per second
llama-server | 11114.12.756.421 I slot print_timing: id 0 | task 2820534 | prompt processing, n_tokens = 39010, progress = 1.00, t = 38.97 s / 1001.02 tokens per second
llama-server | 11114.15.954.244 I slot print_timing: id 0 | task 2820534 | n_gen = 142, tg = 46.93 t/s, tg_3s = 47.26 t/s
llama-server | 11114.19.038.734 I slot print_timing: id 0 | task 2820534 | n_gen = 259, tg = 42.37 t/s, tg_3s = 37.93 t/s
llama-server | 11114.22.104.162 I slot print_timing: id 0 | task 2820534 | n_gen = 364, tg = 39.65 t/s, tg_3s = 34.25 t/s
llama-server | 11114.25.113.390 I slot print_timing: id 0 | task 2820534 | n_gen = 486, tg = 39.87 t/s, tg_3s = 40.54 t/s
llama-server | 11114.28.190.879 I slot print_timing: id 0 | task 2820534 | n_gen = 592, tg = 38.78 t/s, tg_3s = 34.44 t/s
llama-server | 11114.31.194.498 I slot print_timing: id 0 | task 2820534 | n_gen = 683, tg = 37.38 t/s, tg_3s = 30.30 t/s
llama-server | 11114.34.280.957 I slot print_timing: id 0 | task 2820534 | n_gen = 784, tg = 36.71 t/s, tg_3s = 32.72 t/s
llama-server | 11114.37.281.086 I slot print_timing: id 0 | task 2820534 | n_gen = 877, tg = 36.00 t/s, tg_3s = 31.00 t/s
llama-server | 11114.40.290.689 I slot print_timing: id 0 | task 2820534 | n_gen = 957, tg = 34.97 t/s, tg_3s = 26.58 t/s
llama-server | 11114.43.379.850 I slot print_timing: id 0 | task 2820534 | n_gen = 1050, tg = 34.47 t/s, tg_3s = 30.11 t/s
llama-server | 11114.46.384.081 I slot print_timing: id 0 | task 2820534 | n_gen = 1155, tg = 34.52 t/s, tg_3s = 34.95 t/s
llama-server | 11114.49.412.524 I slot print_timing: id 0 | task 2820534 | n_gen = 1270, tg = 34.80 t/s, tg_3s = 37.97 t/s
llama-server | 11114.52.425.600 I slot print_timing: id 0 | task 2820534 | n_gen = 1391, tg = 35.21 t/s, tg_3s = 40.16 t/s
llama-server | 11114.55.450.770 I slot print_timing: id 0 | task 2820534 | n_gen = 1491, tg = 35.06 t/s, tg_3s = 33.06 t/s
llama-server | 11114.58.466.849 I slot print_timing: id 0 | task 2820534 | n_gen = 1606, tg = 35.26 t/s, tg_3s = 38.13 t/s
llama-server | 11115.01.476.832 I slot print_timing: id 0 | task 2820534 | n_gen = 1687, tg = 34.74 t/s, tg_3s = 26.91 t/s
llama-server | 11115.04.509.527 I slot print_timing: id 0 | task 2820534 | n_gen = 1794, tg = 34.78 t/s, tg_3s = 35.28 t/s
llama-server | 11115.07.530.445 I slot print_timing: id 0 | task 2820534 | n_gen = 1897, tg = 34.74 t/s, tg_3s = 34.10 t/s
llama-server | 11115.10.567.079 I slot print_timing: id 0 | task 2820534 | n_gen = 1992, tg = 34.56 t/s, tg_3s = 31.28 t/s
llama-server | 11115.13.592.798 I slot print_timing: id 0 | task 2820534 | n_gen = 2090, tg = 34.45 t/s, tg_3s = 32.39 t/s
llama-server | 11115.16.618.574 I slot print_timing: id 0 | task 2820534 | n_gen = 2185, tg = 34.30 t/s, tg_3s = 31.40 t/s
llama-server | 11115.19.669.050 I slot print_timing: id 0 | task 2820534 | n_gen = 2256, tg = 33.80 t/s, tg_3s = 23.28 t/s
llama-server | 11115.22.703.246 I slot print_timing: id 0 | task 2820534 | n_gen = 2349, tg = 33.66 t/s, tg_3s = 30.65 t/s
llama-server | 11115.25.736.771 I slot print_timing: id 0 | task 2820534 | n_gen = 2439, tg = 33.49 t/s, tg_3s = 29.67 t/s
llama-server | 11115.28.796.627 I slot print_timing: id 0 | task 2820534 | n_gen = 2533, tg = 33.38 t/s, tg_3s = 30.72 t/s
llama-server | 11115.31.835.560 I slot print_timing: id 0 | task 2820534 | n_gen = 2617, tg = 33.16 t/s, tg_3s = 27.64 t/s
llama-server | 11115.34.890.119 I slot print_timing: id 0 | task 2820534 | n_gen = 2740, tg = 33.43 t/s, tg_3s = 40.27 t/s
llama-server | 11115.37.931.954 I slot print_timing: id 0 | task 2820534 | n_gen = 2863, tg = 33.68 t/s, tg_3s = 40.44 t/s
llama-server | 11115.40.991.862 I slot print_timing: id 0 | task 2820534 | n_gen = 2983, tg = 33.87 t/s, tg_3s = 39.22 t/s
llama-server | 11115.44.036.668 I slot print_timing: id 0 | task 2820534 | n_gen = 3083, tg = 33.84 t/s, tg_3s = 32.84 t/s
llama-server | 11115.47.080.572 I slot print_timing: id 0 | task 2820534 | n_gen = 3175, tg = 33.72 t/s, tg_3s = 30.22 t/s
llama-server | 11115.50.149.449 I slot print_timing: id 0 | task 2820534 | n_gen = 3290, tg = 33.84 t/s, tg_3s = 37.47 t/s
llama-server | 11115.50.329.254 I slot print_timing: id 0 | task 2820534 | prompt eval time = 39754.39 ms / 39014 tokens ( 1.02 ms per token, 981.38 tokens per second)
llama-server | 11115.50.329.257 I slot print_timing: id 0 | task 2820534 | eval time = 97379.54 ms / 3298 tokens ( 29.54 ms per token, 33.86 tokens per second)
llama-server | 11115.50.329.257 I slot print_timing: id 0 | task 2820534 | total time = 137133.93 ms / 42312 tokens
llama-server | 11115.50.329.258 I slot print_timing: id 0 | task 2820534 | graphs reused = 2731965
llama-server | 11115.50.329.261 I slot print_timing: id 0 | task 2820534 | draft acceptance = 0.40237 ( 2203 accepted / 5475 generated), mean len = 3.01
llama-server | 11115.50.330.358 I slot release: id 0 | task 2820534 | stop processing: n_tokens = 42312, truncated = 0
llama-server | 11115.51.878.210 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 666814262783
llama-server | 11115.51.878.775 I slot launch_slot_: id 1 | task 2821651 | processing task, is_child = 0
llama-server | 11115.51.880.744 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1825.496 MiB)
llama-server | 11115.57.063.897 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.01 s / 1362.39 tokens per second
llama-server | 11115.58.880.736 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.82 s / 1275.86 tokens per second
llama-server | 11116.00.739.525 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.66 s / 1230.10 tokens per second
llama-server | 11116.02.627.801 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.54 s / 1198.45 tokens per second
llama-server | 11116.04.562.740 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.47 s / 1173.49 tokens per second
llama-server | 11116.06.526.208 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.42 s / 1153.86 tokens per second
llama-server | 11116.08.531.761 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.42 s / 1136.47 tokens per second
llama-server | 11116.10.572.354 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.45 s / 1120.35 tokens per second
llama-server | 11116.12.652.460 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.52 s / 1105.80 tokens per second
llama-server | 11116.14.772.001 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 22528, progress = 0.57, t = 20.63 s / 1092.11 tokens per second
llama-server | 11116.16.944.664 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.78 s / 1078.85 tokens per second
llama-server | 11116.19.141.186 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 26624, progress = 0.68, t = 24.98 s / 1065.85 tokens per second
llama-server | 11116.21.374.236 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.20 s / 1054.05 tokens per second
llama-server | 11116.23.644.908 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 30720, progress = 0.78, t = 29.46 s / 1042.71 tokens per second
llama-server | 11116.25.982.695 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.76 s / 1031.82 tokens per second
llama-server | 11116.28.320.205 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 34816, progress = 0.89, t = 34.12 s / 1020.34 tokens per second
llama-server | 11116.30.698.838 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 36864, progress = 0.94, t = 36.49 s / 1010.33 tokens per second
llama-server | 11116.32.915.199 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 38716, progress = 0.99, t = 38.89 s / 995.49 tokens per second
llama-server | 11116.33.645.925 I slot print_timing: id 1 | task 2821651 | prompt processing, n_tokens = 39228, progress = 1.00, t = 39.53 s / 992.48 tokens per second
llama-server | 11116.36.851.071 I slot print_timing: id 1 | task 2821651 | n_gen = 111, tg = 36.53 t/s, tg_3s = 36.86 t/s
llama-server | 11116.37.995.551 I slot print_timing: id 1 | task 2821651 | prompt eval time = 40321.08 ms / 39232 tokens ( 1.03 ms per token, 972.99 tokens per second)
llama-server | 11116.37.995.554 I slot print_timing: id 1 | task 2821651 | eval time = 4155.74 ms / 158 tokens ( 26.47 ms per token, 37.78 tokens per second)
llama-server | 11116.37.995.555 I slot print_timing: id 1 | task 2821651 | total time = 44476.82 ms / 39390 tokens
llama-server | 11116.37.995.556 I slot print_timing: id 1 | task 2821651 | graphs reused = 2732011
llama-server | 11116.37.995.559 I slot print_timing: id 1 | task 2821651 | draft acceptance = 0.47234 ( 111 accepted / 235 generated), mean len = 3.36
llama-server | 11116.37.996.792 I slot release: id 1 | task 2821651 | stop processing: n_tokens = 39390, truncated = 0
llama-server | 11116.39.306.077 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 666966170410
llama-server | 11116.39.306.787 I slot launch_slot_: id 0 | task 2821720 | processing task, is_child = 0
llama-server | 11116.39.308.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1951.709 MiB)
llama-server | 11116.46.541.552 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.79 s / 1281.98 tokens per second
llama-server | 11116.48.395.317 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.63 s / 1235.28 tokens per second
llama-server | 11116.50.278.051 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.51 s / 1202.89 tokens per second
llama-server | 11116.52.210.472 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.44 s / 1177.28 tokens per second
llama-server | 11116.54.169.340 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.39 s / 1157.51 tokens per second
llama-server | 11116.56.171.253 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.37 s / 1139.87 tokens per second
llama-server | 11116.58.208.646 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.40 s / 1123.57 tokens per second
llama-server | 11117.00.284.957 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.47 s / 1108.81 tokens per second
llama-server | 11117.02.406.794 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.58 s / 1094.83 tokens per second
llama-server | 11117.04.578.528 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.73 s / 1081.18 tokens per second
llama-server | 11117.06.772.712 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 26624, progress = 0.68, t = 24.93 s / 1068.09 tokens per second
llama-server | 11117.09.003.325 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.15 s / 1056.14 tokens per second
llama-server | 11117.11.267.457 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 30720, progress = 0.78, t = 29.40 s / 1044.75 tokens per second
llama-server | 11117.13.603.963 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.70 s / 1033.85 tokens per second
llama-server | 11117.15.939.169 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 34816, progress = 0.89, t = 34.06 s / 1022.28 tokens per second
llama-server | 11117.18.311.004 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 36864, progress = 0.94, t = 36.42 s / 1012.19 tokens per second
llama-server | 11117.20.486.127 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 38660, progress = 0.99, t = 38.82 s / 995.96 tokens per second
llama-server | 11117.21.249.972 I slot print_timing: id 0 | task 2821720 | prompt processing, n_tokens = 39172, progress = 1.00, t = 39.45 s / 992.96 tokens per second
llama-server | 11117.24.449.157 I slot print_timing: id 0 | task 2821720 | n_gen = 121, tg = 39.85 t/s, tg_3s = 40.18 t/s
llama-server | 11117.27.516.793 I slot print_timing: id 0 | task 2821720 | n_gen = 217, tg = 35.53 t/s, tg_3s = 31.29 t/s
llama-server | 11117.28.676.908 I slot print_timing: id 0 | task 2821720 | prompt eval time = 40234.74 ms / 39176 tokens ( 1.03 ms per token, 973.69 tokens per second)
llama-server | 11117.28.676.912 I slot print_timing: id 0 | task 2821720 | eval time = 7239.19 ms / 266 tokens ( 27.32 ms per token, 36.61 tokens per second)
llama-server | 11117.28.676.912 I slot print_timing: id 0 | task 2821720 | total time = 47473.93 ms / 39442 tokens
llama-server | 11117.28.676.913 I slot print_timing: id 0 | task 2821720 | graphs reused = 2732091
llama-server | 11117.28.676.916 I slot print_timing: id 0 | task 2821720 | draft acceptance = 0.44634 ( 183 accepted / 410 generated), mean len = 3.23
llama-server | 11117.28.678.067 I slot release: id 0 | task 2821720 | stop processing: n_tokens = 39441, truncated = 0
llama-server | 11117.29.979.579 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 667013836843
llama-server | 11117.29.980.418 I slot launch_slot_: id 1 | task 2821824 | processing task, is_child = 0
llama-server | 11117.29.982.263 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1835.537 MiB)
llama-server | 11117.35.174.186 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.00 s / 1365.28 tokens per second
llama-server | 11117.36.985.353 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1278.82 tokens per second
llama-server | 11117.38.837.456 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.64 s / 1233.45 tokens per second
llama-server | 11117.40.719.613 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.52 s / 1201.81 tokens per second
llama-server | 11117.42.640.764 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.43 s / 1177.97 tokens per second
llama-server | 11117.44.609.800 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.39 s / 1157.09 tokens per second
llama-server | 11117.46.611.944 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.38 s / 1139.39 tokens per second
llama-server | 11117.48.649.342 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.41 s / 1123.15 tokens per second
llama-server | 11117.50.725.953 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.48 s / 1108.39 tokens per second
llama-server | 11117.52.841.502 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.58 s / 1094.55 tokens per second
llama-server | 11117.55.011.652 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.73 s / 1081.15 tokens per second
llama-server | 11117.57.205.282 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 26624, progress = 0.68, t = 24.93 s / 1068.13 tokens per second
llama-server | 11117.59.436.183 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.15 s / 1056.16 tokens per second
llama-server | 11118.01.700.580 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 30720, progress = 0.78, t = 29.40 s / 1044.75 tokens per second
llama-server | 11118.04.040.297 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.70 s / 1033.85 tokens per second
llama-server | 11118.06.376.993 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 34816, progress = 0.89, t = 34.06 s / 1022.14 tokens per second
llama-server | 11118.08.751.036 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 36864, progress = 0.94, t = 36.42 s / 1012.07 tokens per second
llama-server | 11118.10.893.753 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 38629, progress = 0.99, t = 38.82 s / 994.99 tokens per second
llama-server | 11118.11.618.696 I slot print_timing: id 1 | task 2821824 | prompt processing, n_tokens = 39141, progress = 1.00, t = 39.39 s / 993.71 tokens per second
llama-server | 11118.14.882.764 I slot print_timing: id 1 | task 2821824 | n_gen = 109, tg = 35.68 t/s, tg_3s = 36.00 t/s
llama-server | 11118.15.851.844 I slot print_timing: id 1 | task 2821824 | prompt eval time = 40219.22 ms / 39145 tokens ( 1.03 ms per token, 973.29 tokens per second)
llama-server | 11118.15.851.847 I slot print_timing: id 1 | task 2821824 | eval time = 3996.32 ms / 155 tokens ( 25.95 ms per token, 38.54 tokens per second)
llama-server | 11118.15.851.848 I slot print_timing: id 1 | task 2821824 | total time = 44215.55 ms / 39300 tokens
llama-server | 11118.15.851.848 I slot print_timing: id 1 | task 2821824 | graphs reused = 2732134
llama-server | 11118.15.851.851 I slot print_timing: id 1 | task 2821824 | draft acceptance = 0.48444 ( 109 accepted / 225 generated), mean len = 3.42
llama-server | 11118.15.852.981 I slot release: id 1 | task 2821824 | stop processing: n_tokens = 39299, truncated = 0
llama-server | 11118.17.146.191 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 667064518119
llama-server | 11118.17.146.886 I slot launch_slot_: id 0 | task 2821891 | processing task, is_child = 0
llama-server | 11118.17.148.821 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1862.635 MiB)
llama-server | 11118.23.608.115 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.79 s / 1281.70 tokens per second
llama-server | 11118.25.464.029 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.63 s / 1235.28 tokens per second
llama-server | 11118.27.351.212 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.51 s / 1202.60 tokens per second
llama-server | 11118.29.270.523 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.43 s / 1178.21 tokens per second
llama-server | 11118.31.235.092 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.39 s / 1157.52 tokens per second
llama-server | 11118.33.234.053 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.37 s / 1140.09 tokens per second
llama-server | 11118.35.273.479 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.40 s / 1123.93 tokens per second
llama-server | 11118.37.348.360 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.47 s / 1108.99 tokens per second
llama-server | 11118.39.464.087 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.57 s / 1095.17 tokens per second
llama-server | 11118.41.634.253 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.72 s / 1081.69 tokens per second
llama-server | 11118.43.827.654 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 26624, progress = 0.68, t = 24.91 s / 1068.59 tokens per second
llama-server | 11118.46.059.331 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.14 s / 1056.61 tokens per second
llama-server | 11118.48.324.541 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 30720, progress = 0.79, t = 29.39 s / 1045.11 tokens per second
llama-server | 11118.50.660.007 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.69 s / 1034.16 tokens per second
llama-server | 11118.52.995.287 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 34816, progress = 0.89, t = 34.05 s / 1022.58 tokens per second
llama-server | 11118.55.368.772 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 36864, progress = 0.94, t = 36.41 s / 1012.48 tokens per second
llama-server | 11118.57.480.437 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 38603, progress = 0.99, t = 38.81 s / 994.75 tokens per second
llama-server | 11118.58.197.450 I slot print_timing: id 0 | task 2821891 | prompt processing, n_tokens = 39115, progress = 1.00, t = 39.34 s / 994.38 tokens per second
llama-server | 11119.01.413.528 I slot print_timing: id 0 | task 2821891 | n_gen = 106, tg = 34.72 t/s, tg_3s = 35.05 t/s
llama-server | 11119.04.489.177 I slot print_timing: id 0 | task 2821891 | n_gen = 190, tg = 30.99 t/s, tg_3s = 27.31 t/s
llama-server | 11119.07.566.876 I slot print_timing: id 0 | task 2821891 | n_gen = 290, tg = 31.49 t/s, tg_3s = 32.49 t/s
llama-server | 11119.10.575.386 I slot print_timing: id 0 | task 2821891 | n_gen = 379, tg = 31.02 t/s, tg_3s = 29.58 t/s
llama-server | 11119.13.661.114 I slot print_timing: id 0 | task 2821891 | n_gen = 500, tg = 32.68 t/s, tg_3s = 39.21 t/s
llama-server | 11119.16.672.839 I slot print_timing: id 0 | task 2821891 | n_gen = 611, tg = 33.36 t/s, tg_3s = 36.86 t/s
llama-server | 11119.19.676.556 I slot print_timing: id 0 | task 2821891 | n_gen = 722, tg = 33.87 t/s, tg_3s = 36.95 t/s
llama-server | 11119.22.764.204 I slot print_timing: id 0 | task 2821891 | n_gen = 805, tg = 32.99 t/s, tg_3s = 26.88 t/s
llama-server | 11119.25.785.635 I slot print_timing: id 0 | task 2821891 | n_gen = 913, tg = 33.29 t/s, tg_3s = 35.74 t/s
llama-server | 11119.28.799.835 I slot print_timing: id 0 | task 2821891 | n_gen = 1033, tg = 33.94 t/s, tg_3s = 39.81 t/s
llama-server | 11119.30.764.526 I slot print_timing: id 0 | task 2821891 | prompt eval time = 40120.21 ms / 39119 tokens ( 1.03 ms per token, 975.04 tokens per second)
llama-server | 11119.30.764.529 I slot print_timing: id 0 | task 2821891 | eval time = 32374.99 ms / 1103 tokens ( 29.38 ms per token, 34.04 tokens per second)
llama-server | 11119.30.764.530 I slot print_timing: id 0 | task 2821891 | total time = 72495.20 ms / 40222 tokens
llama-server | 11119.30.764.531 I slot print_timing: id 0 | task 2821891 | graphs reused = 2732494
llama-server | 11119.30.764.533 I slot print_timing: id 0 | task 2821891 | draft acceptance = 0.40219 ( 736 accepted / 1830 generated), mean len = 3.01
llama-server | 11119.30.765.641 I slot release: id 0 | task 2821891 | stop processing: n_tokens = 40221, truncated = 0
llama-server | 11119.32.160.065 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 667111693033
llama-server | 11119.32.160.609 I slot launch_slot_: id 1 | task 2822279 | processing task, is_child = 0
llama-server | 11119.32.162.510 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1975.847 MiB)
llama-server | 11119.39.394.021 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1278.92 tokens per second
llama-server | 11119.41.251.807 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.65 s / 1232.43 tokens per second
llama-server | 11119.43.139.301 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.53 s / 1200.14 tokens per second
llama-server | 11119.45.072.058 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.46 s / 1175.01 tokens per second
llama-server | 11119.47.034.348 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 14336, progress = 0.37, t = 12.41 s / 1155.24 tokens per second
llama-server | 11119.49.042.754 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 16384, progress = 0.42, t = 14.40 s / 1137.66 tokens per second
llama-server | 11119.51.083.610 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.44 s / 1121.23 tokens per second
llama-server | 11119.53.165.464 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.51 s / 1106.55 tokens per second
llama-server | 11119.55.285.602 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 22528, progress = 0.58, t = 20.62 s / 1092.58 tokens per second
llama-server | 11119.57.459.914 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 24576, progress = 0.63, t = 22.77 s / 1079.20 tokens per second
llama-server | 11119.59.656.444 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 26624, progress = 0.68, t = 24.97 s / 1066.22 tokens per second
llama-server | 11120.01.890.305 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.19 s / 1054.37 tokens per second
llama-server | 11120.04.153.869 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 30720, progress = 0.79, t = 29.45 s / 1043.08 tokens per second
llama-server | 11120.06.489.391 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 32768, progress = 0.84, t = 31.74 s / 1032.33 tokens per second
llama-server | 11120.08.824.498 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 34816, progress = 0.89, t = 34.10 s / 1020.91 tokens per second
llama-server | 11120.11.198.227 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 36864, progress = 0.94, t = 36.47 s / 1010.89 tokens per second
llama-server | 11120.13.313.082 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 38616, progress = 0.99, t = 38.86 s / 993.60 tokens per second
llama-server | 11120.14.051.405 I slot print_timing: id 1 | task 2822279 | prompt processing, n_tokens = 39128, progress = 1.00, t = 39.42 s / 992.71 tokens per second
llama-server | 11120.16.491.573 I slot print_timing: id 1 | task 2822279 | prompt eval time = 40201.83 ms / 39132 tokens ( 1.03 ms per token, 973.39 tokens per second)
llama-server | 11120.16.491.576 I slot print_timing: id 1 | task 2822279 | eval time = 2247.64 ms / 90 tokens ( 25.25 ms per token, 39.60 tokens per second)
llama-server | 11120.16.491.577 I slot print_timing: id 1 | task 2822279 | total time = 42449.47 ms / 39222 tokens
llama-server | 11120.16.491.578 I slot print_timing: id 1 | task 2822279 | graphs reused = 2732517
llama-server | 11120.16.491.581 I slot print_timing: id 1 | task 2822279 | draft acceptance = 0.52000 ( 65 accepted / 125 generated), mean len = 3.60
llama-server | 11120.16.492.681 I slot release: id 1 | task 2822279 | stop processing: n_tokens = 39222, truncated = 0
llama-server | 11120.17.762.295 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 667186605693
llama-server | 11120.17.762.958 I slot launch_slot_: id 0 | task 2822326 | processing task, is_child = 0
llama-server | 11120.17.764.777 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1878.694 MiB)
llama-server | 11120.24.701.582 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 6144, progress = 0.16, t = 4.80 s / 1280.16 tokens per second
llama-server | 11120.26.553.675 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 8192, progress = 0.21, t = 6.64 s / 1234.38 tokens per second
llama-server | 11120.28.435.921 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 10240, progress = 0.26, t = 8.52 s / 1202.52 tokens per second
llama-server | 11120.30.360.560 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 12288, progress = 0.31, t = 10.43 s / 1178.56 tokens per second
llama-server | 11120.32.329.852 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 14336, progress = 0.36, t = 12.39 s / 1157.20 tokens per second
llama-server | 11120.34.329.528 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 16384, progress = 0.41, t = 14.38 s / 1139.56 tokens per second
llama-server | 11120.36.364.598 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 18432, progress = 0.47, t = 16.41 s / 1123.48 tokens per second
llama-server | 11120.38.440.571 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 20480, progress = 0.52, t = 18.47 s / 1108.86 tokens per second
llama-server | 11120.40.555.932 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 22528, progress = 0.57, t = 20.57 s / 1094.96 tokens per second
llama-server | 11120.42.724.313 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 24576, progress = 0.62, t = 22.72 s / 1081.58 tokens per second
llama-server | 11120.44.916.444 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 26624, progress = 0.67, t = 24.92 s / 1068.55 tokens per second
llama-server | 11120.47.145.785 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 28672, progress = 0.73, t = 27.13 s / 1056.65 tokens per second
llama-server | 11120.49.408.911 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 30720, progress = 0.78, t = 29.39 s / 1045.22 tokens per second
llama-server | 11120.51.741.629 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 32768, progress = 0.83, t = 31.68 s / 1034.37 tokens per second
llama-server | 11120.54.074.249 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 34816, progress = 0.88, t = 34.04 s / 1022.84 tokens per second
llama-server | 11120.56.447.338 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 36864, progress = 0.93, t = 36.40 s / 1012.76 tokens per second
llama-server | 11120.58.852.980 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 38912, progress = 0.98, t = 38.80 s / 1002.93 tokens per second
llama-server | 11120.59.060.885 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 39027, progress = 0.99, t = 39.51 s / 987.86 tokens per second
llama-server | 11120.59.780.328 I slot print_timing: id 0 | task 2822326 | prompt processing, n_tokens = 39539, progress = 1.00, t = 39.83 s / 992.82 tokens per second
llama-server | 11121.03.386.437 I slot print_timing: id 0 | task 2822326 | n_gen = 101, tg = 29.66 t/s, tg_3s = 29.95 t/s
llama-server | 11121.06.404.429 I slot print_timing: id 0 | task 2822326 | n_gen = 206, tg = 32.08 t/s, tg_3s = 34.79 t/s
llama-server | 11121.09.409.816 I slot print_timing: id 0 | task 2822326 | n_gen = 316, tg = 33.53 t/s, tg_3s = 36.60 t/s
llama-server | 11121.12.435.601 I slot print_timing: id 0 | task 2822326 | n_gen = 419, tg = 33.65 t/s, tg_3s = 34.04 t/s
llama-server | 11121.15.438.394 I slot print_timing: id 0 | task 2822326 | n_gen = 500, tg = 32.35 t/s, tg_3s = 26.97 t/s
llama-server | 11121.18.448.192 I slot print_timing: id 0 | task 2822326 | n_gen = 619, tg = 33.53 t/s, tg_3s = 39.54 t/s
llama-server | 11121.21.473.748 I slot print_timing: id 0 | task 2822326 | n_gen = 717, tg = 33.37 t/s, tg_3s = 32.39 t/s
llama-server | 11121.24.491.724 I slot print_timing: id 0 | task 2822326 | n_gen = 828, tg = 33.79 t/s, tg_3s = 36.78 t/s
llama-server | 11121.27.525.420 I slot print_timing: id 0 | task 2822326 | n_gen = 940, tg = 34.13 t/s, tg_3s = 36.92 t/s
llama-server | 11121.30.540.038 I slot print_timing: id 0 | task 2822326 | n_gen = 1047, tg = 34.27 t/s, tg_3s = 35.49 t/s
llama-server | 11121.33.557.309 I slot print_timing: id 0 | task 2822326 | n_gen = 1151, tg = 34.28 t/s, tg_3s = 34.47 t/s
llama-server | 11121.36.600.225 I slot print_timing: id 0 | task 2822326 | n_gen = 1254, tg = 34.25 t/s, tg_3s = 33.85 t/s
llama-server | 11121.39.636.003 I slot print_timing: id 0 | task 2822326 | n_gen = 1384, tg = 34.91 t/s, tg_3s = 42.82 t/s
llama-server | 11121.42.676.522 I slot print_timing: id 0 | task 2822326 | n_gen = 1462, tg = 34.25 t/s, tg_3s = 25.65 t/s
llama-server | 11121.45.706.069 I slot print_timing: id 0 | task 2822326 | n_gen = 1561, tg = 34.14 t/s, tg_3s = 32.68 t/s
llama-server | 11121.48.735.003 I slot print_timing: id 0 | task 2822326 | n_gen = 1667, tg = 34.20 t/s, tg_3s = 35.00 t/s
llama-server | 11121.51.781.700 I slot print_timing: id 0 | task 2822326 | n_gen = 1756, tg = 33.90 t/s, tg_3s = 29.21 t/s
llama-server | 11121.54.817.506 I slot print_timing: id 0 | task 2822326 | n_gen = 1864, tg = 33.99 t/s, tg_3s = 35.58 t/s
llama-server | 11121.57.868.729 I slot print_timing: id 0 | task 2822326 | n_gen = 1968, tg = 34.00 t/s, tg_3s = 34.08 t/s
llama-server | 11122.00.905.736 I slot print_timing: id 0 | task 2822326 | n_gen = 2072, tg = 34.01 t/s, tg_3s = 34.24 t/s
llama-server | 11122.03.942.811 I slot print_timing: id 0 | task 2822326 | n_gen = 2177, tg = 34.04 t/s, tg_3s = 34.57 t/s
llama-server | 11122.07.007.524 I slot print_timing: id 0 | task 2822326 | n_gen = 2261, tg = 33.74 t/s, tg_3s = 27.41 t/s
llama-server | 11122.10.053.697 I slot print_timing: id 0 | task 2822326 | n_gen = 2367, tg = 33.78 t/s, tg_3s = 34.80 t/s
llama-server | 11122.13.119.231 I slot print_timing: id 0 | task 2822326 | n_gen = 2468, tg = 33.75 t/s, tg_3s = 32.95 t/s
llama-server | 11122.16.170.558 I slot print_timing: id 0 | task 2822326 | n_gen = 2566, tg = 33.68 t/s, tg_3s = 32.12 t/s
llama-server | 11122.19.213.362 I slot print_timing: id 0 | task 2822326 | n_gen = 2663, tg = 33.61 t/s, tg_3s = 31.88 t/s
llama-server | 11122.22.280.173 I slot print_timing: id 0 | task 2822326 | n_gen = 2792, tg = 33.93 t/s, tg_3s = 42.06 t/s
llama-server | 11122.25.330.428 I slot print_timing: id 0 | task 2822326 | n_gen = 2889, tg = 33.85 t/s, tg_3s = 31.80 t/s
llama-server | 11122.28.397.905 I slot print_timing: id 0 | task 2822326 | n_gen = 2985, tg = 33.76 t/s, tg_3s = 31.30 t/s
llama-server | 11122.31.450.164 I slot print_timing: id 0 | task 2822326 | n_gen = 3079, tg = 33.66 t/s, tg_3s = 30.80 t/s
llama-server | 11122.34.506.190 I slot print_timing: id 0 | task 2822326 | n_gen = 3183, tg = 33.68 t/s, tg_3s = 34.03 t/s
llama-server | 11122.37.584.913 I slot print_timing: id 0 | task 2822326 | n_gen = 3278, tg = 33.59 t/s, tg_3s = 30.86 t/s
llama-server | 11122.38.576.581 I slot print_timing: id 0 | task 2822326 | prompt eval time = 40657.17 ms / 39543 tokens ( 1.03 ms per token, 972.60 tokens per second)
llama-server | 11122.38.576.584 I slot print_timing: id 0 | task 2822326 | eval time = 98561.77 ms / 3313 tokens ( 29.76 ms per token, 33.60 tokens per second)
llama-server | 11122.38.576.585 I slot print_timing: id 0 | task 2822326 | total time = 139218.94 ms / 42856 tokens
llama-server | 11122.38.576.586 I slot print_timing: id 0 | task 2822326 | graphs reused = 2733606
llama-server | 11122.38.576.589 I slot print_timing: id 0 | task 2822326 | draft acceptance = 0.40054 ( 2209 accepted / 5515 generated), mean len = 3.00
llama-server | 11122.38.577.660 I slot release: id 0 | task 2822326 | stop processing: n_tokens = 42855, truncated = 0
llama-server | 11122.40.147.666 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 667232332733
llama-server | 11122.40.148.219 I slot launch_slot_: id 1 | task 2823452 | processing task, is_child = 0
llama-server | 11122.40.150.259 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1880.390 MiB)
llama-server | 11122.44.864.838 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 667374417712
llama-server | 11122.44.864.999 I slot launch_slot_: id 0 | task 2823455 | processing task, is_child = 0
llama-server | 11122.44.865.287 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.00 s / 1363.34 tokens per second
llama-server | 11122.46.846.495 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 5760, progress = 0.14, t = 5.05 s / 1140.43 tokens per second
llama-server | 11122.48.790.244 I slot print_timing: id 0 | task 2823455 | prompt processing, n_tokens = 566, progress = 0.63, t = 3.62 s / 156.29 tokens per second
llama-server | 11122.48.891.361 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 7626, progress = 0.19, t = 7.16 s / 1064.74 tokens per second
llama-server | 11122.50.878.436 I slot print_timing: id 0 | task 2823455 | prompt processing, n_tokens = 896, progress = 1.00, t = 5.53 s / 161.88 tokens per second
llama-server | 11122.50.971.361 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 9344, progress = 0.23, t = 9.08 s / 1029.54 tokens per second
llama-server | 11122.52.986.416 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 11388, progress = 0.28, t = 11.52 s / 988.92 tokens per second
llama-server | 11122.55.028.317 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 13430, progress = 0.33, t = 13.55 s / 991.07 tokens per second
llama-server | 11122.57.106.822 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 15472, progress = 0.38, t = 15.63 s / 989.59 tokens per second
llama-server | 11122.59.223.746 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 17514, progress = 0.44, t = 17.75 s / 986.60 tokens per second
llama-server | 11123.01.378.655 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 19556, progress = 0.49, t = 19.91 s / 982.39 tokens per second
llama-server | 11123.03.572.059 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 21598, progress = 0.54, t = 22.10 s / 977.26 tokens per second
llama-server | 11123.05.815.181 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 23640, progress = 0.59, t = 24.34 s / 971.10 tokens per second
llama-server | 11123.08.085.102 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 25682, progress = 0.64, t = 26.61 s / 965.00 tokens per second
llama-server | 11123.10.391.619 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 27724, progress = 0.69, t = 28.92 s / 958.64 tokens per second
llama-server | 11123.12.738.834 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 29766, progress = 0.74, t = 31.27 s / 951.98 tokens per second
llama-server | 11123.13.729.873 W srv stop: cancel task, id_task = 2823456
llama-server | 11123.15.157.751 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 31808, progress = 0.79, t = 33.68 s / 944.28 tokens per second
llama-server | 11123.17.578.328 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 33850, progress = 0.84, t = 36.11 s / 937.49 tokens per second
llama-server | 11123.20.037.070 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 35892, progress = 0.89, t = 38.56 s / 930.69 tokens per second
llama-server | 11123.22.527.657 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 37934, progress = 0.94, t = 41.06 s / 923.95 tokens per second
llama-server | 11123.24.790.032 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 39721, progress = 0.99, t = 43.33 s / 916.61 tokens per second
llama-server | 11123.25.584.347 I slot print_timing: id 1 | task 2823452 | prompt processing, n_tokens = 40233, progress = 1.00, t = 44.21 s / 910.05 tokens per second
llama-server | 11123.27.174.744 I slot print_timing: id 0 | task 2823455 | n_gen = 100, tg = 2.89 t/s, tg_3s = 2.92 t/s
llama-server | 11123.28.830.078 I slot print_timing: id 1 | task 2823452 | n_gen = 120, tg = 39.52 t/s, tg_3s = 39.85 t/s
llama-server | 11123.29.978.637 I slot print_timing: id 0 | task 2823455 | prompt eval time = 8110.48 ms / 900 tokens ( 9.01 ms per token, 110.97 tokens per second)
llama-server | 11123.29.978.641 I slot print_timing: id 0 | task 2823455 | eval time = 37002.82 ms / 198 tokens ( 187.83 ms per token, 5.32 tokens per second)
llama-server | 11123.29.978.642 I slot print_timing: id 0 | task 2823455 | total time = 45113.30 ms / 1098 tokens
llama-server | 11123.29.978.642 I slot print_timing: id 0 | task 2823455 | graphs reused = 2733650
llama-server | 11123.29.978.645 I slot print_timing: id 0 | task 2823455 | draft acceptance = 0.42540 ( 134 accepted / 315 generated), mean len = 3.13
llama-server | 11123.29.978.713 I slot release: id 0 | task 2823455 | stop processing: n_tokens = 1097, truncated = 0
llama-server | 11123.29.980.246 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 667425818765
llama-server | 11123.29.980.640 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1875.668 MiB)
llama-server | 11123.30.602.511 I slot launch_slot_: id 0 | task 2823471 | processing task, is_child = 0
llama-server | 11123.33.183.759 I slot print_timing: id 1 | task 2823452 | n_gen = 163, tg = 22.00 t/s, tg_3s = 9.88 t/s
llama-server | 11123.35.768.690 I slot print_timing: id 0 | task 2823471 | prompt processing, n_tokens = 4084, progress = 0.36, t = 5.01 s / 815.48 tokens per second
llama-server | 11123.38.372.604 I slot print_timing: id 1 | task 2823452 | n_gen = 166, tg = 13.14 t/s, tg_3s = 0.58 t/s
llama-server | 11123.38.387.289 I slot print_timing: id 0 | task 2823471 | prompt processing, n_tokens = 6126, progress = 0.53, t = 7.62 s / 803.64 tokens per second
llama-server | 11123.41.038.111 I slot print_timing: id 0 | task 2823471 | prompt processing, n_tokens = 8168, progress = 0.71, t = 10.28 s / 794.63 tokens per second
llama-server | 11123.43.738.659 I slot print_timing: id 1 | task 2823452 | n_gen = 168, tg = 9.32 t/s, tg_3s = 0.37 t/s
llama-server | 11123.43.747.401 I slot print_timing: id 0 | task 2823471 | prompt processing, n_tokens = 10210, progress = 0.89, t = 12.99 s / 786.05 tokens per second
llama-server | 11123.44.859.322 I slot print_timing: id 0 | task 2823471 | prompt processing, n_tokens = 10939, progress = 0.95, t = 14.18 s / 771.39 tokens per second
llama-server | 11123.45.390.611 I slot print_timing: id 0 | task 2823471 | prompt processing, n_tokens = 11121, progress = 0.97, t = 14.75 s / 753.82 tokens per second
llama-server | 11123.46.105.066 I slot print_timing: id 0 | task 2823471 | prompt processing, n_tokens = 11451, progress = 1.00, t = 15.46 s / 740.85 tokens per second
llama-server | 11123.46.763.575 I slot print_timing: id 1 | task 2823452 | n_gen = 189, tg = 8.98 t/s, tg_3s = 6.94 t/s
llama-server | 11123.49.371.498 I slot print_timing: id 0 | task 2823471 | n_gen = 127, tg = 41.95 t/s, tg_3s = 42.28 t/s
llama-server | 11123.49.834.135 I slot print_timing: id 1 | task 2823452 | n_gen = 274, tg = 11.37 t/s, tg_3s = 27.68 t/s
llama-server | 11123.52.271.281 I slot print_timing: id 1 | task 2823452 | prompt eval time = 44494.35 ms / 40237 tokens ( 1.11 ms per token, 904.32 tokens per second)
llama-server | 11123.52.271.284 I slot print_timing: id 1 | task 2823452 | eval time = 26452.56 ms / 364 tokens ( 72.87 ms per token, 13.72 tokens per second)
llama-server | 11123.52.271.285 I slot print_timing: id 1 | task 2823452 | total time = 70946.91 ms / 40601 tokens
llama-server | 11123.52.271.286 I slot print_timing: id 1 | task 2823452 | graphs reused = 2733711
llama-server | 11123.52.271.289 I slot print_timing: id 1 | task 2823452 | draft acceptance = 0.41008 ( 244 accepted / 595 generated), mean len = 3.05
llama-server | 11123.52.272.417 I slot release: id 1 | task 2823452 | stop processing: n_tokens = 40600, truncated = 0
llama-server | 11123.52.481.811 I slot print_timing: id 0 | task 2823471 | n_gen = 292, tg = 47.60 t/s, tg_3s = 53.05 t/s
llama-server | 11123.53.806.648 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 667448112469
llama-server | 11123.53.808.583 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1906.324 MiB)
llama-server | 11123.55.373.003 I slot launch_slot_: id 1 | task 2823614 | processing task, is_child = 0
llama-server | 11123.58.117.290 I slot print_timing: id 0 | task 2823471 | n_gen = 325, tg = 27.58 t/s, tg_3s = 5.86 t/s
llama-server | 11124.00.836.645 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.31 s / 769.78 tokens per second
llama-server | 11124.03.557.373 I slot print_timing: id 0 | task 2823471 | n_gen = 329, tg = 19.08 t/s, tg_3s = 0.74 t/s
llama-server | 11124.03.567.397 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.04 s / 762.11 tokens per second
llama-server | 11124.06.276.311 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 8168, progress = 0.20, t = 10.75 s / 760.05 tokens per second
llama-server | 11124.08.983.179 I slot print_timing: id 0 | task 2823471 | n_gen = 332, tg = 14.64 t/s, tg_3s = 0.55 t/s
llama-server | 11124.08.993.602 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 10210, progress = 0.25, t = 13.46 s / 758.72 tokens per second
llama-server | 11124.11.705.813 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.18 s / 757.42 tokens per second
llama-server | 11124.14.410.554 I slot print_timing: id 0 | task 2823471 | n_gen = 336, tg = 11.95 t/s, tg_3s = 0.74 t/s
llama-server | 11124.14.421.172 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 14294, progress = 0.35, t = 18.89 s / 756.68 tokens per second
llama-server | 11124.17.135.498 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 16336, progress = 0.40, t = 21.60 s / 756.14 tokens per second
llama-server | 11124.19.842.051 I slot print_timing: id 0 | task 2823471 | n_gen = 343, tg = 10.22 t/s, tg_3s = 1.29 t/s
llama-server | 11124.19.852.267 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 18378, progress = 0.45, t = 24.32 s / 755.58 tokens per second
llama-server | 11124.22.569.557 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 20420, progress = 0.50, t = 27.04 s / 755.18 tokens per second
llama-server | 11124.25.276.921 I slot print_timing: id 0 | task 2823471 | n_gen = 346, tg = 8.87 t/s, tg_3s = 0.55 t/s
llama-server | 11124.25.287.337 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 22462, progress = 0.55, t = 29.76 s / 754.84 tokens per second
llama-server | 11124.28.004.472 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 24504, progress = 0.60, t = 32.47 s / 754.56 tokens per second
llama-server | 11124.30.713.853 I slot print_timing: id 0 | task 2823471 | n_gen = 353, tg = 7.94 t/s, tg_3s = 1.29 t/s
llama-server | 11124.30.724.104 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 26546, progress = 0.65, t = 35.19 s / 754.29 tokens per second
llama-server | 11124.33.440.833 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 28588, progress = 0.70, t = 37.91 s / 754.07 tokens per second
llama-server | 11124.36.147.898 I slot print_timing: id 0 | task 2823471 | n_gen = 363, tg = 7.27 t/s, tg_3s = 1.84 t/s
llama-server | 11124.36.157.775 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 30630, progress = 0.75, t = 40.63 s / 753.89 tokens per second
llama-server | 11124.38.879.201 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 32672, progress = 0.80, t = 43.35 s / 753.72 tokens per second
llama-server | 11124.41.587.060 I slot print_timing: id 0 | task 2823471 | n_gen = 367, tg = 6.63 t/s, tg_3s = 0.74 t/s
llama-server | 11124.41.597.357 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 34714, progress = 0.85, t = 46.07 s / 753.55 tokens per second
llama-server | 11124.44.318.618 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 36756, progress = 0.89, t = 48.79 s / 753.36 tokens per second
llama-server | 11124.47.028.015 I slot print_timing: id 0 | task 2823471 | n_gen = 369, tg = 6.07 t/s, tg_3s = 0.37 t/s
llama-server | 11124.47.038.447 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 38798, progress = 0.94, t = 51.51 s / 753.23 tokens per second
llama-server | 11124.49.466.262 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 40553, progress = 0.99, t = 53.95 s / 751.65 tokens per second
llama-server | 11124.50.417.138 I slot print_timing: id 0 | task 2823471 | n_gen = 371, tg = 5.78 t/s, tg_3s = 0.59 t/s
llama-server | 11124.50.427.425 I slot print_timing: id 1 | task 2823614 | prompt processing, n_tokens = 41065, progress = 1.00, t = 54.99 s / 746.71 tokens per second
llama-server | 11124.53.427.464 I slot print_timing: id 0 | task 2823471 | n_gen = 444, tg = 6.61 t/s, tg_3s = 24.25 t/s
llama-server | 11124.53.803.078 I slot print_timing: id 1 | task 2823614 | prompt eval time = 55367.78 ms / 41069 tokens ( 1.35 ms per token, 741.75 tokens per second)
llama-server | 11124.53.803.082 I slot print_timing: id 1 | task 2823614 | eval time = 3052.39 ms / 115 tokens ( 26.78 ms per token, 37.35 tokens per second)
llama-server | 11124.53.803.083 I slot print_timing: id 1 | task 2823614 | total time = 58420.17 ms / 41184 tokens
llama-server | 11124.53.803.084 I slot print_timing: id 1 | task 2823614 | graphs reused = 2733796
llama-server | 11124.53.803.089 I slot print_timing: id 1 | task 2823614 | draft acceptance = 0.51875 ( 83 accepted / 160 generated), mean len = 3.59
llama-server | 11124.53.804.299 I slot release: id 1 | task 2823614 | stop processing: n_tokens = 41184, truncated = 0
llama-server | 11124.55.153.628 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 667509644351
llama-server | 11124.55.155.626 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1873.108 MiB)
llama-server | 11124.56.832.215 I slot launch_slot_: id 1 | task 2823683 | processing task, is_child = 0
llama-server | 11124.59.673.578 I slot print_timing: id 0 | task 2823471 | n_gen = 490, tg = 6.67 t/s, tg_3s = 7.36 t/s
llama-server | 11125.02.482.478 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.49 s / 743.48 tokens per second
llama-server | 11125.05.290.405 I slot print_timing: id 0 | task 2823471 | n_gen = 498, tg = 6.30 t/s, tg_3s = 1.42 t/s
llama-server | 11125.05.300.578 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.31 s / 736.98 tokens per second
llama-server | 11125.08.097.426 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.11 s / 735.38 tokens per second
llama-server | 11125.10.888.459 I slot print_timing: id 0 | task 2823471 | n_gen = 503, tg = 5.94 t/s, tg_3s = 0.89 t/s
llama-server | 11125.10.898.143 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 10210, progress = 0.25, t = 13.91 s / 734.05 tokens per second
llama-server | 11125.13.703.068 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.71 s / 733.07 tokens per second
llama-server | 11125.16.496.430 I slot print_timing: id 0 | task 2823471 | n_gen = 506, tg = 5.60 t/s, tg_3s = 0.53 t/s
llama-server | 11125.16.506.968 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.52 s / 732.36 tokens per second
llama-server | 11125.19.311.602 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.32 s / 731.81 tokens per second
llama-server | 11125.22.109.005 I slot print_timing: id 0 | task 2823471 | n_gen = 508, tg = 5.30 t/s, tg_3s = 0.36 t/s
llama-server | 11125.22.119.417 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 18378, progress = 0.45, t = 25.13 s / 731.39 tokens per second
llama-server | 11125.24.924.411 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 20420, progress = 0.50, t = 27.94 s / 730.96 tokens per second
llama-server | 11125.27.719.025 I slot print_timing: id 0 | task 2823471 | n_gen = 513, tg = 5.05 t/s, tg_3s = 0.89 t/s
llama-server | 11125.27.728.761 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 22462, progress = 0.55, t = 30.74 s / 730.68 tokens per second
llama-server | 11125.30.534.886 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 24504, progress = 0.60, t = 33.55 s / 730.46 tokens per second
llama-server | 11125.33.330.874 I slot print_timing: id 0 | task 2823471 | n_gen = 516, tg = 4.81 t/s, tg_3s = 0.53 t/s
llama-server | 11125.33.341.521 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 26546, progress = 0.65, t = 36.35 s / 730.24 tokens per second
llama-server | 11125.36.148.552 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 28588, progress = 0.70, t = 39.16 s / 730.05 tokens per second
llama-server | 11125.38.947.009 I slot print_timing: id 0 | task 2823471 | n_gen = 521, tg = 4.62 t/s, tg_3s = 0.89 t/s
llama-server | 11125.38.957.282 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 30630, progress = 0.75, t = 41.97 s / 729.86 tokens per second
llama-server | 11125.41.764.025 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 32672, progress = 0.80, t = 44.77 s / 729.69 tokens per second
llama-server | 11125.44.560.959 I slot print_timing: id 0 | task 2823471 | n_gen = 526, tg = 4.44 t/s, tg_3s = 0.89 t/s
llama-server | 11125.44.571.353 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 34714, progress = 0.85, t = 47.58 s / 729.55 tokens per second
llama-server | 11125.47.379.819 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 36756, progress = 0.90, t = 50.39 s / 729.42 tokens per second
llama-server | 11125.50.179.564 I slot print_timing: id 0 | task 2823471 | n_gen = 530, tg = 4.27 t/s, tg_3s = 0.71 t/s
llama-server | 11125.50.189.689 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 38798, progress = 0.95, t = 53.20 s / 729.27 tokens per second
llama-server | 11125.52.267.366 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 40238, progress = 0.99, t = 55.32 s / 727.42 tokens per second
llama-server | 11125.53.188.646 I slot print_timing: id 1 | task 2823683 | prompt processing, n_tokens = 40750, progress = 1.00, t = 56.29 s / 723.88 tokens per second
llama-server | 11125.53.549.419 I slot print_timing: id 0 | task 2823471 | n_gen = 538, tg = 4.22 t/s, tg_3s = 2.37 t/s
llama-server | 11125.56.562.280 I slot print_timing: id 0 | task 2823471 | n_gen = 622, tg = 4.77 t/s, tg_3s = 27.88 t/s
llama-server | 11125.56.563.678 I slot print_timing: id 1 | task 2823683 | n_gen = 107, tg = 35.15 t/s, tg_3s = 35.48 t/s
llama-server | 11125.58.433.262 I slot print_timing: id 1 | task 2823683 | prompt eval time = 56706.02 ms / 40754 tokens ( 1.39 ms per token, 718.69 tokens per second)
llama-server | 11125.58.433.265 I slot print_timing: id 1 | task 2823683 | eval time = 4885.10 ms / 200 tokens ( 24.55 ms per token, 40.74 tokens per second)
llama-server | 11125.58.433.266 I slot print_timing: id 1 | task 2823683 | total time = 61591.11 ms / 40954 tokens
llama-server | 11125.58.433.267 I slot print_timing: id 1 | task 2823683 | graphs reused = 2733899
llama-server | 11125.58.433.270 I slot print_timing: id 1 | task 2823683 | draft acceptance = 0.56538 ( 147 accepted / 260 generated), mean len = 3.83
llama-server | 11125.58.434.532 I slot release: id 1 | task 2823683 | stop processing: n_tokens = 40953, truncated = 0
llama-server | 11125.59.589.520 I slot print_timing: id 0 | task 2823471 | n_gen = 709, tg = 5.31 t/s, tg_3s = 28.74 t/s
llama-server | 11125.59.777.272 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 667574274583
llama-server | 11125.59.779.341 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1993.902 MiB)
llama-server | 11126.01.543.732 I slot launch_slot_: id 1 | task 2823772 | processing task, is_child = 0
llama-server | 11126.04.386.816 I slot print_timing: id 0 | task 2823471 | n_gen = 714, tg = 5.17 t/s, tg_3s = 1.04 t/s
llama-server | 11126.07.197.401 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.50 s / 743.04 tokens per second
llama-server | 11126.10.011.975 I slot print_timing: id 0 | task 2823471 | n_gen = 716, tg = 4.98 t/s, tg_3s = 0.36 t/s
llama-server | 11126.10.022.365 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.32 s / 736.13 tokens per second
llama-server | 11126.12.821.766 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.12 s / 734.40 tokens per second
llama-server | 11126.15.615.034 I slot print_timing: id 0 | task 2823471 | n_gen = 723, tg = 4.84 t/s, tg_3s = 1.25 t/s
llama-server | 11126.15.625.383 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 10210, progress = 0.25, t = 13.92 s / 733.26 tokens per second
llama-server | 11126.18.429.983 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 12252, progress = 0.30, t = 16.73 s / 732.37 tokens per second
llama-server | 11126.21.224.601 I slot print_timing: id 0 | task 2823471 | n_gen = 727, tg = 4.69 t/s, tg_3s = 0.71 t/s
llama-server | 11126.21.234.721 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 14294, progress = 0.35, t = 19.53 s / 731.71 tokens per second
llama-server | 11126.24.043.542 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 16336, progress = 0.40, t = 22.34 s / 731.24 tokens per second
llama-server | 11126.26.839.631 I slot print_timing: id 0 | task 2823471 | n_gen = 734, tg = 4.57 t/s, tg_3s = 1.25 t/s
llama-server | 11126.26.849.975 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 18378, progress = 0.44, t = 25.15 s / 730.75 tokens per second
llama-server | 11126.29.656.202 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 20420, progress = 0.49, t = 27.96 s / 730.42 tokens per second
llama-server | 11126.32.451.718 I slot print_timing: id 0 | task 2823471 | n_gen = 745, tg = 4.48 t/s, tg_3s = 1.96 t/s
llama-server | 11126.32.461.688 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 22462, progress = 0.54, t = 30.76 s / 730.19 tokens per second
llama-server | 11126.35.270.370 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 24504, progress = 0.59, t = 33.57 s / 729.97 tokens per second
llama-server | 11126.38.067.894 I slot print_timing: id 0 | task 2823471 | n_gen = 749, tg = 4.36 t/s, tg_3s = 0.71 t/s
llama-server | 11126.38.077.778 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 26546, progress = 0.64, t = 36.38 s / 729.73 tokens per second
llama-server | 11126.40.886.785 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 28588, progress = 0.69, t = 39.19 s / 729.53 tokens per second
llama-server | 11126.43.687.075 I slot print_timing: id 0 | task 2823471 | n_gen = 755, tg = 4.25 t/s, tg_3s = 1.07 t/s
llama-server | 11126.43.697.063 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 30630, progress = 0.74, t = 42.00 s / 729.35 tokens per second
llama-server | 11126.46.505.864 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 32672, progress = 0.79, t = 44.80 s / 729.21 tokens per second
llama-server | 11126.49.305.939 I slot print_timing: id 0 | task 2823471 | n_gen = 763, tg = 4.17 t/s, tg_3s = 1.42 t/s
llama-server | 11126.49.314.994 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 34714, progress = 0.84, t = 47.61 s / 729.06 tokens per second
llama-server | 11126.52.123.971 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 36756, progress = 0.89, t = 50.42 s / 728.95 tokens per second
llama-server | 11126.54.923.359 I slot print_timing: id 0 | task 2823471 | n_gen = 769, tg = 4.07 t/s, tg_3s = 1.07 t/s
llama-server | 11126.54.933.455 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 38798, progress = 0.94, t = 53.23 s / 728.82 tokens per second
llama-server | 11126.57.728.608 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 40790, progress = 0.99, t = 56.03 s / 727.99 tokens per second
llama-server | 11126.58.645.242 I slot print_timing: id 0 | task 2823471 | prompt eval time = 15755.73 ms / 11455 tokens ( 1.38 ms per token, 727.04 tokens per second)
llama-server | 11126.58.645.247 I slot print_timing: id 0 | task 2823471 | eval time = 192277.43 ms / 781 tokens ( 246.51 ms per token, 4.06 tokens per second)
llama-server | 11126.58.645.248 I slot print_timing: id 0 | task 2823471 | total time = 208033.16 ms / 12236 tokens
llama-server | 11126.58.645.249 I slot print_timing: id 0 | task 2823471 | graphs reused = 2733952
llama-server | 11126.58.645.253 I slot print_timing: id 0 | task 2823471 | draft acceptance = 0.40938 ( 524 accepted / 1280 generated), mean len = 3.05
llama-server | 11126.58.645.650 I slot release: id 0 | task 2823471 | stop processing: n_tokens = 12235, truncated = 0
llama-server | 11126.58.645.674 I slot print_timing: id 1 | task 2823772 | prompt processing, n_tokens = 41302, progress = 1.00, t = 57.05 s / 723.95 tokens per second
llama-server | 11126.58.942.632 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.936
llama-server | 11126.58.943.193 I slot launch_slot_: id 0 | task 2823795 | processing task, is_child = 0
llama-server | 11127.02.208.493 I slot print_timing: id 1 | task 2823772 | n_gen = 101, tg = 30.62 t/s, tg_3s = 30.93 t/s
llama-server | 11127.02.578.660 I slot print_timing: id 0 | task 2823795 | prompt eval time = 1625.24 ms / 616 tokens ( 2.64 ms per token, 379.02 tokens per second)
llama-server | 11127.02.578.663 I slot print_timing: id 0 | task 2823795 | eval time = 2001.64 ms / 75 tokens ( 27.05 ms per token, 36.97 tokens per second)
llama-server | 11127.02.578.663 I slot print_timing: id 0 | task 2823795 | total time = 3626.88 ms / 691 tokens
llama-server | 11127.02.578.664 I slot print_timing: id 0 | task 2823795 | graphs reused = 2733972
llama-server | 11127.02.578.667 I slot print_timing: id 0 | task 2823795 | draft acceptance = 0.50476 ( 53 accepted / 105 generated), mean len = 3.52
llama-server | 11127.02.579.142 I slot release: id 0 | task 2823795 | stop processing: n_tokens = 12141, truncated = 0
llama-server | 11127.02.794.492 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.949 (> 0.100 thold), f_keep = 0.994
llama-server | 11127.02.794.928 I slot launch_slot_: id 0 | task 2823822 | processing task, is_child = 0
llama-server | 11127.05.211.985 I slot print_timing: id 1 | task 2823772 | n_gen = 158, tg = 25.04 t/s, tg_3s = 18.98 t/s
llama-server | 11127.07.485.712 I slot print_timing: id 0 | task 2823822 | n_gen = 110, tg = 35.60 t/s, tg_3s = 35.92 t/s
llama-server | 11127.08.235.318 I slot print_timing: id 1 | task 2823772 | n_gen = 253, tg = 27.12 t/s, tg_3s = 31.42 t/s
llama-server | 11127.08.703.921 I slot print_timing: id 0 | task 2823822 | prompt eval time = 1620.51 ms / 652 tokens ( 2.49 ms per token, 402.34 tokens per second)
llama-server | 11127.08.703.924 I slot print_timing: id 0 | task 2823822 | eval time = 4279.90 ms / 166 tokens ( 25.94 ms per token, 38.55 tokens per second)
llama-server | 11127.08.703.924 I slot print_timing: id 0 | task 2823822 | total time = 5900.41 ms / 818 tokens
llama-server | 11127.08.703.925 I slot print_timing: id 0 | task 2823822 | graphs reused = 2734016
llama-server | 11127.08.703.928 I slot print_timing: id 0 | task 2823822 | draft acceptance = 0.53333 ( 120 accepted / 225 generated), mean len = 3.67
llama-server | 11127.08.704.387 I slot release: id 0 | task 2823822 | stop processing: n_tokens = 12880, truncated = 0
llama-server | 11127.08.919.577 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.942 (> 0.100 thold), f_keep = 0.987
llama-server | 11127.08.919.975 I slot launch_slot_: id 0 | task 2823873 | processing task, is_child = 0
llama-server | 11127.11.239.816 I slot print_timing: id 1 | task 2823772 | n_gen = 291, tg = 23.58 t/s, tg_3s = 12.65 t/s
llama-server | 11127.14.054.403 I slot print_timing: id 0 | task 2823873 | n_gen = 103, tg = 30.73 t/s, tg_3s = 31.02 t/s
llama-server | 11127.14.243.180 I slot print_timing: id 1 | task 2823772 | n_gen = 383, tg = 24.97 t/s, tg_3s = 30.63 t/s
llama-server | 11127.14.833.279 I slot print_timing: id 0 | task 2823873 | prompt eval time = 1806.21 ms / 779 tokens ( 2.32 ms per token, 431.29 tokens per second)
llama-server | 11127.14.833.283 I slot print_timing: id 0 | task 2823873 | eval time = 4098.59 ms / 139 tokens ( 29.70 ms per token, 33.67 tokens per second)
llama-server | 11127.14.833.283 I slot print_timing: id 0 | task 2823873 | total time = 5904.80 ms / 918 tokens
llama-server | 11127.14.833.284 I slot print_timing: id 0 | task 2823873 | graphs reused = 2734058
llama-server | 11127.14.833.287 I slot print_timing: id 0 | task 2823873 | draft acceptance = 0.44186 ( 95 accepted / 215 generated), mean len = 3.21
llama-server | 11127.14.833.764 I slot release: id 0 | task 2823873 | stop processing: n_tokens = 13628, truncated = 0
llama-server | 11127.15.049.590 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.953 (> 0.100 thold), f_keep = 0.990
llama-server | 11127.15.050.023 I slot launch_slot_: id 0 | task 2823922 | processing task, is_child = 0
llama-server | 11127.17.257.042 I slot print_timing: id 1 | task 2823772 | n_gen = 426, tg = 23.21 t/s, tg_3s = 14.27 t/s
llama-server | 11127.19.895.959 I slot print_timing: id 0 | task 2823922 | n_gen = 104, tg = 32.71 t/s, tg_3s = 33.02 t/s
llama-server | 11127.20.295.289 I slot print_timing: id 1 | task 2823772 | n_gen = 493, tg = 23.04 t/s, tg_3s = 22.05 t/s
llama-server | 11127.22.946.385 I slot print_timing: id 0 | task 2823922 | n_gen = 260, tg = 41.78 t/s, tg_3s = 51.14 t/s
llama-server | 11127.23.136.123 I slot print_timing: id 0 | task 2823922 | prompt eval time = 1688.29 ms / 663 tokens ( 2.55 ms per token, 392.71 tokens per second)
llama-server | 11127.23.136.126 I slot print_timing: id 0 | task 2823922 | eval time = 6389.24 ms / 271 tokens ( 23.66 ms per token, 42.26 tokens per second)
llama-server | 11127.23.136.127 I slot print_timing: id 0 | task 2823922 | total time = 8077.53 ms / 934 tokens
llama-server | 11127.23.136.127 I slot print_timing: id 0 | task 2823922 | graphs reused = 2734124
llama-server | 11127.23.136.130 I slot print_timing: id 0 | task 2823922 | draft acceptance = 0.60896 ( 204 accepted / 335 generated), mean len = 4.04
llama-server | 11127.23.136.615 I slot release: id 0 | task 2823922 | stop processing: n_tokens = 14420, truncated = 0
llama-server | 11127.23.353.097 I slot print_timing: id 1 | task 2823772 | n_gen = 581, tg = 23.76 t/s, tg_3s = 28.78 t/s
llama-server | 11127.23.353.111 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.983 (> 0.100 thold), f_keep = 0.981
llama-server | 11127.23.353.501 I slot launch_slot_: id 0 | task 2823995 | processing task, is_child = 0
llama-server | 11127.26.397.244 I slot print_timing: id 1 | task 2823772 | n_gen = 640, tg = 23.27 t/s, tg_3s = 19.38 t/s
llama-server | 11127.27.543.096 I slot print_timing: id 0 | task 2823995 | n_gen = 111, tg = 35.59 t/s, tg_3s = 35.91 t/s
llama-server | 11127.27.922.736 I slot print_timing: id 0 | task 2823995 | prompt eval time = 1090.12 ms / 250 tokens ( 4.36 ms per token, 229.33 tokens per second)
llama-server | 11127.27.922.739 I slot print_timing: id 0 | task 2823995 | eval time = 3470.83 ms / 129 tokens ( 27.12 ms per token, 36.88 tokens per second)
llama-server | 11127.27.922.740 I slot print_timing: id 0 | task 2823995 | total time = 4560.95 ms / 379 tokens
llama-server | 11127.27.922.741 I slot print_timing: id 0 | task 2823995 | graphs reused = 2734159
llama-server | 11127.27.922.743 I slot print_timing: id 0 | task 2823995 | draft acceptance = 0.51111 ( 92 accepted / 180 generated), mean len = 3.56
llama-server | 11127.27.923.255 I slot release: id 0 | task 2823995 | stop processing: n_tokens = 14523, truncated = 0
llama-server | 11127.28.233.639 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.957 (> 0.100 thold), f_keep = 0.991
llama-server | 11127.28.234.199 I slot launch_slot_: id 0 | task 2824037 | processing task, is_child = 0
llama-server | 11127.29.617.113 I slot print_timing: id 1 | task 2823772 | n_gen = 698, tg = 22.72 t/s, tg_3s = 18.01 t/s
llama-server | 11127.32.681.542 I slot print_timing: id 1 | task 2823772 | n_gen = 780, tg = 23.09 t/s, tg_3s = 26.76 t/s
llama-server | 11127.33.727.344 I slot print_timing: id 0 | task 2824037 | n_gen = 100, tg = 26.23 t/s, tg_3s = 26.50 t/s
llama-server | 11127.35.751.518 I slot print_timing: id 1 | task 2823772 | n_gen = 859, tg = 23.31 t/s, tg_3s = 25.73 t/s
llama-server | 11127.36.798.216 I slot print_timing: id 0 | task 2824037 | n_gen = 191, tg = 27.76 t/s, tg_3s = 29.63 t/s
llama-server | 11127.38.235.998 I slot print_timing: id 0 | task 2824037 | prompt eval time = 1710.58 ms / 650 tokens ( 2.63 ms per token, 379.99 tokens per second)
llama-server | 11127.38.236.001 I slot print_timing: id 0 | task 2824037 | eval time = 8282.40 ms / 249 tokens ( 33.40 ms per token, 29.94 tokens per second)
llama-server | 11127.38.236.001 I slot print_timing: id 0 | task 2824037 | total time = 9992.98 ms / 899 tokens
llama-server | 11127.38.236.002 I slot print_timing: id 0 | task 2824037 | graphs reused = 2734244
llama-server | 11127.38.236.005 I slot print_timing: id 0 | task 2824037 | draft acceptance = 0.37907 ( 163 accepted / 430 generated), mean len = 2.90
llama-server | 11127.38.236.502 I slot release: id 0 | task 2824037 | stop processing: n_tokens = 15290, truncated = 0
llama-server | 11127.38.455.351 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.994 (> 0.100 thold), f_keep = 0.984
llama-server | 11127.38.455.776 I slot launch_slot_: id 0 | task 2824129 | processing task, is_child = 0
llama-server | 11127.39.044.832 I slot print_timing: id 1 | task 2823772 | n_gen = 957, tg = 23.84 t/s, tg_3s = 29.76 t/s
llama-server | 11127.42.095.512 I slot print_timing: id 1 | task 2823772 | n_gen = 1064, tg = 24.63 t/s, tg_3s = 35.07 t/s
llama-server | 11127.42.594.661 I slot print_timing: id 0 | task 2824129 | n_gen = 103, tg = 31.78 t/s, tg_3s = 32.09 t/s
llama-server | 11127.45.176.448 I slot print_timing: id 1 | task 2823772 | n_gen = 1163, tg = 25.13 t/s, tg_3s = 32.13 t/s
llama-server | 11127.45.652.078 I slot print_timing: id 0 | task 2824129 | n_gen = 182, tg = 28.88 t/s, tg_3s = 25.84 t/s
llama-server | 11127.48.267.556 I slot print_timing: id 1 | task 2823772 | n_gen = 1281, tg = 25.95 t/s, tg_3s = 38.17 t/s
llama-server | 11127.48.745.633 I slot print_timing: id 0 | task 2824129 | n_gen = 267, tg = 28.42 t/s, tg_3s = 27.48 t/s
llama-server | 11127.51.284.841 I slot print_timing: id 1 | task 2823772 | n_gen = 1401, tg = 26.75 t/s, tg_3s = 39.77 t/s
llama-server | 11127.51.765.333 I slot print_timing: id 0 | task 2824129 | n_gen = 368, tg = 29.64 t/s, tg_3s = 33.45 t/s
llama-server | 11127.54.291.172 I slot print_timing: id 1 | task 2823772 | n_gen = 1486, tg = 26.83 t/s, tg_3s = 28.27 t/s
llama-server | 11127.54.771.085 I slot print_timing: id 0 | task 2824129 | n_gen = 505, tg = 32.76 t/s, tg_3s = 45.58 t/s
llama-server | 11127.57.398.587 I slot print_timing: id 1 | task 2823772 | n_gen = 1588, tg = 27.15 t/s, tg_3s = 32.82 t/s
llama-server | 11127.57.589.780 I slot print_timing: id 0 | task 2824129 | prompt eval time = 920.88 ms / 95 tokens ( 9.69 ms per token, 103.16 tokens per second)
llama-server | 11127.57.589.783 I slot print_timing: id 0 | task 2824129 | eval time = 18204.49 ms / 616 tokens ( 29.60 ms per token, 33.78 tokens per second)
llama-server | 11127.57.589.784 I slot print_timing: id 0 | task 2824129 | total time = 19125.37 ms / 711 tokens
llama-server | 11127.57.589.784 I slot print_timing: id 0 | task 2824129 | graphs reused = 2734427
llama-server | 11127.57.589.787 I slot print_timing: id 0 | task 2824129 | draft acceptance = 0.45426 ( 427 accepted / 940 generated), mean len = 3.27
llama-server | 11127.57.590.270 I slot release: id 0 | task 2824129 | stop processing: n_tokens = 15747, truncated = 0
llama-server | 11127.58.490.053 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.968 (> 0.100 thold), f_keep = 0.961
llama-server | 11127.58.490.690 I slot launch_slot_: id 0 | task 2824329 | processing task, is_child = 0
llama-server | 11128.00.440.326 I slot print_timing: id 1 | task 2823772 | n_gen = 1628, tg = 26.46 t/s, tg_3s = 13.15 t/s
llama-server | 11128.03.320.397 I slot print_timing: id 0 | task 2824329 | n_gen = 104, tg = 30.32 t/s, tg_3s = 30.61 t/s
llama-server | 11128.03.512.912 I slot print_timing: id 1 | task 2823772 | n_gen = 1720, tg = 26.62 t/s, tg_3s = 29.94 t/s
llama-server | 11128.06.414.483 I slot print_timing: id 0 | task 2824329 | n_gen = 179, tg = 27.42 t/s, tg_3s = 24.24 t/s
llama-server | 11128.06.608.363 I slot print_timing: id 1 | task 2823772 | n_gen = 1814, tg = 26.79 t/s, tg_3s = 30.37 t/s
llama-server | 11128.09.491.851 I slot print_timing: id 0 | task 2824329 | n_gen = 244, tg = 25.40 t/s, tg_3s = 21.12 t/s
llama-server | 11128.09.685.161 I slot print_timing: id 1 | task 2823772 | n_gen = 1902, tg = 26.87 t/s, tg_3s = 28.60 t/s
llama-server | 11128.12.510.684 I slot print_timing: id 0 | task 2824329 | n_gen = 367, tg = 29.08 t/s, tg_3s = 40.74 t/s
llama-server | 11128.12.707.551 I slot print_timing: id 1 | task 2823772 | n_gen = 2006, tg = 27.18 t/s, tg_3s = 34.41 t/s
llama-server | 11128.15.539.942 I slot print_timing: id 0 | task 2824329 | n_gen = 522, tg = 33.36 t/s, tg_3s = 51.17 t/s
llama-server | 11128.15.736.655 I slot print_timing: id 1 | task 2823772 | n_gen = 2097, tg = 27.29 t/s, tg_3s = 30.04 t/s
llama-server | 11128.17.790.003 I slot print_timing: id 0 | task 2824329 | prompt eval time = 1423.71 ms / 511 tokens ( 2.79 ms per token, 358.92 tokens per second)
llama-server | 11128.17.790.006 I slot print_timing: id 0 | task 2824329 | eval time = 17866.85 ms / 626 tokens ( 28.59 ms per token, 34.98 tokens per second)
llama-server | 11128.17.790.006 I slot print_timing: id 0 | task 2824329 | total time = 19290.56 ms / 1137 tokens
llama-server | 11128.17.790.007 I slot print_timing: id 0 | task 2824329 | graphs reused = 2734614
llama-server | 11128.17.790.010 I slot print_timing: id 0 | task 2824329 | draft acceptance = 0.47935 ( 441 accepted / 920 generated), mean len = 3.40
llama-server | 11128.17.790.520 I slot release: id 0 | task 2824329 | stop processing: n_tokens = 16264, truncated = 0
llama-server | 11128.18.795.153 I slot print_timing: id 1 | task 2823772 | n_gen = 2179, tg = 27.28 t/s, tg_3s = 26.81 t/s
llama-server | 11128.21.829.426 I slot print_timing: id 1 | task 2823772 | n_gen = 2255, tg = 27.19 t/s, tg_3s = 25.05 t/s
llama-server | 11128.24.887.342 I slot print_timing: id 1 | task 2823772 | n_gen = 2364, tg = 27.49 t/s, tg_3s = 35.65 t/s
llama-server | 11128.27.927.359 I slot print_timing: id 1 | task 2823772 | n_gen = 2462, tg = 27.66 t/s, tg_3s = 32.24 t/s
llama-server | 11128.28.025.291 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.966 (> 0.100 thold), f_keep = 0.962
llama-server | 11128.28.025.721 I slot launch_slot_: id 0 | task 2824620 | processing task, is_child = 0
llama-server | 11128.30.988.697 I slot print_timing: id 1 | task 2823772 | n_gen = 2505, tg = 27.20 t/s, tg_3s = 14.05 t/s
llama-server | 11128.33.207.469 I slot print_timing: id 0 | task 2824620 | n_gen = 105, tg = 31.32 t/s, tg_3s = 31.62 t/s
llama-server | 11128.34.004.043 I slot print_timing: id 1 | task 2823772 | n_gen = 2573, tg = 27.06 t/s, tg_3s = 22.55 t/s
llama-server | 11128.36.226.081 I slot print_timing: id 0 | task 2824620 | n_gen = 174, tg = 27.29 t/s, tg_3s = 22.86 t/s
llama-server | 11128.37.098.457 I slot print_timing: id 1 | task 2823772 | n_gen = 2663, tg = 27.12 t/s, tg_3s = 29.08 t/s
llama-server | 11128.39.260.353 I slot print_timing: id 0 | task 2824620 | n_gen = 291, tg = 30.94 t/s, tg_3s = 38.56 t/s
llama-server | 11128.40.143.291 I slot print_timing: id 1 | task 2823772 | n_gen = 2756, tg = 27.22 t/s, tg_3s = 30.54 t/s
llama-server | 11128.41.623.893 I slot print_timing: id 0 | task 2824620 | prompt eval time = 1852.67 ms / 550 tokens ( 3.37 ms per token, 296.87 tokens per second)
llama-server | 11128.41.623.896 I slot print_timing: id 0 | task 2824620 | eval time = 11736.69 ms / 383 tokens ( 30.72 ms per token, 32.55 tokens per second)
llama-server | 11128.41.623.896 I slot print_timing: id 0 | task 2824620 | total time = 13589.36 ms / 933 tokens
llama-server | 11128.41.623.897 I slot print_timing: id 0 | task 2824620 | graphs reused = 2734832
llama-server | 11128.41.623.900 I slot print_timing: id 0 | task 2824620 | draft acceptance = 0.43667 ( 262 accepted / 600 generated), mean len = 3.18
llama-server | 11128.41.624.434 I slot release: id 0 | task 2824620 | stop processing: n_tokens = 16567, truncated = 0
llama-server | 11128.41.844.130 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.984 (> 0.100 thold), f_keep = 0.977
llama-server | 11128.41.844.535 I slot launch_slot_: id 0 | task 2824746 | processing task, is_child = 0
llama-server | 11128.43.278.048 I slot print_timing: id 1 | task 2823772 | n_gen = 2826, tg = 27.08 t/s, tg_3s = 22.33 t/s
llama-server | 11128.46.325.717 I slot print_timing: id 1 | task 2823772 | n_gen = 2947, tg = 27.43 t/s, tg_3s = 39.70 t/s
llama-server | 11128.47.002.892 I slot print_timing: id 0 | task 2824746 | n_gen = 102, tg = 27.11 t/s, tg_3s = 27.38 t/s
llama-server | 11128.49.350.013 I slot print_timing: id 1 | task 2823772 | n_gen = 3015, tg = 27.30 t/s, tg_3s = 22.48 t/s
llama-server | 11128.50.027.918 I slot print_timing: id 0 | task 2824746 | n_gen = 196, tg = 28.89 t/s, tg_3s = 31.07 t/s
llama-server | 11128.52.368.368 I slot print_timing: id 1 | task 2823772 | n_gen = 3114, tg = 27.45 t/s, tg_3s = 32.80 t/s
llama-server | 11128.53.051.747 I slot print_timing: id 0 | task 2824746 | n_gen = 293, tg = 29.87 t/s, tg_3s = 32.08 t/s
llama-server | 11128.55.404.009 I slot print_timing: id 1 | task 2823772 | n_gen = 3191, tg = 27.39 t/s, tg_3s = 25.37 t/s
llama-server | 11128.56.082.111 I slot print_timing: id 0 | task 2824746 | n_gen = 360, tg = 28.04 t/s, tg_3s = 22.11 t/s
llama-server | 11128.58.443.914 I slot print_timing: id 1 | task 2823772 | n_gen = 3270, tg = 27.36 t/s, tg_3s = 25.99 t/s
llama-server | 11128.59.123.657 I slot print_timing: id 0 | task 2824746 | n_gen = 456, tg = 28.71 t/s, tg_3s = 31.56 t/s
llama-server | 11129.01.474.883 I slot print_timing: id 1 | task 2823772 | n_gen = 3347, tg = 27.31 t/s, tg_3s = 25.40 t/s
llama-server | 11129.02.156.325 I slot print_timing: id 0 | task 2824746 | n_gen = 539, tg = 28.50 t/s, tg_3s = 27.37 t/s
llama-server | 11129.04.526.197 I slot print_timing: id 1 | task 2823772 | n_gen = 3444, tg = 27.42 t/s, tg_3s = 31.79 t/s
llama-server | 11129.05.209.074 I slot print_timing: id 0 | task 2824746 | n_gen = 639, tg = 29.09 t/s, tg_3s = 32.76 t/s
llama-server | 11129.07.578.710 I slot print_timing: id 1 | task 2823772 | n_gen = 3511, tg = 27.29 t/s, tg_3s = 21.95 t/s
llama-server | 11129.08.262.494 I slot print_timing: id 0 | task 2824746 | n_gen = 729, tg = 29.14 t/s, tg_3s = 29.48 t/s
llama-server | 11129.10.614.892 I slot print_timing: id 1 | task 2823772 | n_gen = 3600, tg = 27.33 t/s, tg_3s = 29.31 t/s
llama-server | 11129.11.298.747 I slot print_timing: id 0 | task 2824746 | n_gen = 803, tg = 28.62 t/s, tg_3s = 24.37 t/s
llama-server | 11129.13.683.875 I slot print_timing: id 1 | task 2823772 | n_gen = 3673, tg = 27.25 t/s, tg_3s = 23.79 t/s
llama-server | 11129.14.373.015 I slot print_timing: id 0 | task 2824746 | n_gen = 946, tg = 30.39 t/s, tg_3s = 46.52 t/s
llama-server | 11129.16.580.544 I slot print_timing: id 0 | task 2824746 | prompt eval time = 1423.81 ms / 269 tokens ( 5.29 ms per token, 188.93 tokens per second)
llama-server | 11129.16.580.549 I slot print_timing: id 0 | task 2824746 | eval time = 33303.33 ms / 1069 tokens ( 31.18 ms per token, 32.07 tokens per second)
llama-server | 11129.16.580.550 I slot print_timing: id 0 | task 2824746 | total time = 34727.13 ms / 1338 tokens
llama-server | 11129.16.580.551 I slot print_timing: id 0 | task 2824746 | graphs reused = 2735164
llama-server | 11129.16.580.555 I slot print_timing: id 0 | task 2824746 | draft acceptance = 0.43009 ( 729 accepted / 1695 generated), mean len = 3.15
llama-server | 11129.16.581.189 I slot release: id 0 | task 2824746 | stop processing: n_tokens = 17518, truncated = 0
llama-server | 11129.16.684.505 I slot print_timing: id 1 | task 2823772 | n_gen = 3781, tg = 27.44 t/s, tg_3s = 35.99 t/s
llama-server | 11129.16.903.417 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.976 (> 0.100 thold), f_keep = 0.939
llama-server | 11129.16.903.824 I slot launch_slot_: id 0 | task 2825091 | processing task, is_child = 0
llama-server | 11129.19.703.856 I slot print_timing: id 1 | task 2823772 | n_gen = 3817, tg = 27.11 t/s, tg_3s = 11.92 t/s
llama-server | 11129.20.985.838 I slot print_timing: id 1 | task 2823772 | prompt eval time = 57389.56 ms / 41306 tokens ( 1.39 ms per token, 719.75 tokens per second)
llama-server | 11129.20.985.841 I slot print_timing: id 1 | task 2823772 | eval time = 142042.97 ms / 3869 tokens ( 36.72 ms per token, 27.23 tokens per second)
llama-server | 11129.20.985.842 I slot print_timing: id 1 | task 2823772 | total time = 199432.53 ms / 45175 tokens
llama-server | 11129.20.985.843 I slot print_timing: id 1 | task 2823772 | graphs reused = 2735190
llama-server | 11129.20.985.847 I slot print_timing: id 1 | task 2823772 | draft acceptance = 0.38919 ( 2555 accepted / 6565 generated), mean len = 2.95
llama-server | 11129.20.987.009 I slot release: id 1 | task 2823772 | stop processing: n_tokens = 45174, truncated = 0
llama-server | 11129.21.904.535 I slot print_timing: id 0 | task 2825091 | n_gen = 101, tg = 29.15 t/s, tg_3s = 29.44 t/s
llama-server | 11129.22.603.055 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 667776827061
llama-server | 11129.22.605.369 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 692.527 MiB)
llama-server | 11129.25.574.489 I slot launch_slot_: id 1 | task 2825135 | processing task, is_child = 0
llama-server | 11129.28.612.225 I slot print_timing: id 0 | task 2825091 | n_gen = 117, tg = 11.44 t/s, tg_3s = 2.39 t/s
llama-server | 11129.31.609.212 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.80 s / 704.59 tokens per second
llama-server | 11129.34.601.473 I slot print_timing: id 0 | task 2825091 | n_gen = 123, tg = 7.56 t/s, tg_3s = 1.00 t/s
llama-server | 11129.34.613.565 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.80 s / 696.08 tokens per second
llama-server | 11129.37.596.828 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.78 s / 693.13 tokens per second
llama-server | 11129.40.567.587 I slot print_timing: id 0 | task 2825091 | n_gen = 129, tg = 5.79 t/s, tg_3s = 1.01 t/s
llama-server | 11129.40.579.388 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.77 s / 691.38 tokens per second
llama-server | 11129.43.562.573 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 12252, progress = 0.30, t = 17.75 s / 690.22 tokens per second
llama-server | 11129.46.534.146 I slot print_timing: id 0 | task 2825091 | n_gen = 131, tg = 4.63 t/s, tg_3s = 0.34 t/s
llama-server | 11129.46.545.661 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 14294, progress = 0.35, t = 20.73 s / 689.37 tokens per second
llama-server | 11129.49.530.379 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 16336, progress = 0.40, t = 23.72 s / 688.75 tokens per second
llama-server | 11129.52.501.547 I slot print_timing: id 0 | task 2825091 | n_gen = 138, tg = 4.03 t/s, tg_3s = 1.17 t/s
llama-server | 11129.52.513.390 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 18378, progress = 0.45, t = 26.70 s / 688.28 tokens per second
llama-server | 11129.55.496.458 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 20420, progress = 0.50, t = 29.69 s / 687.87 tokens per second
llama-server | 11129.58.469.883 I slot print_timing: id 0 | task 2825091 | n_gen = 143, tg = 3.55 t/s, tg_3s = 0.84 t/s
llama-server | 11129.58.481.461 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 22462, progress = 0.55, t = 32.67 s / 687.53 tokens per second
llama-server | 11130.01.464.572 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 24504, progress = 0.60, t = 35.65 s / 687.26 tokens per second
llama-server | 11130.04.438.038 I slot print_timing: id 0 | task 2825091 | n_gen = 147, tg = 3.18 t/s, tg_3s = 0.67 t/s
llama-server | 11130.04.449.914 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 26546, progress = 0.65, t = 38.64 s / 687.04 tokens per second
llama-server | 11130.07.434.702 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 28588, progress = 0.70, t = 41.62 s / 686.80 tokens per second
llama-server | 11130.10.407.444 I slot print_timing: id 0 | task 2825091 | n_gen = 151, tg = 2.89 t/s, tg_3s = 0.67 t/s
llama-server | 11130.10.419.245 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 30630, progress = 0.75, t = 44.61 s / 686.64 tokens per second
llama-server | 11130.13.411.454 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 32672, progress = 0.80, t = 47.59 s / 686.47 tokens per second
llama-server | 11130.16.385.315 I slot print_timing: id 0 | task 2825091 | n_gen = 158, tg = 2.71 t/s, tg_3s = 1.17 t/s
llama-server | 11130.16.396.649 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 34714, progress = 0.85, t = 50.58 s / 686.26 tokens per second
llama-server | 11130.19.382.086 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 36756, progress = 0.89, t = 53.57 s / 686.14 tokens per second
llama-server | 11130.22.357.304 I slot print_timing: id 0 | task 2825091 | n_gen = 165, tg = 2.57 t/s, tg_3s = 1.17 t/s
llama-server | 11130.22.368.976 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 38798, progress = 0.94, t = 56.56 s / 685.99 tokens per second
llama-server | 11130.25.025.114 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 40560, progress = 0.99, t = 59.25 s / 684.59 tokens per second
llama-server | 11130.26.034.299 I slot print_timing: id 0 | task 2825091 | n_gen = 172, tg = 2.53 t/s, tg_3s = 1.90 t/s
llama-server | 11130.26.046.998 I slot print_timing: id 1 | task 2825135 | prompt processing, n_tokens = 41072, progress = 1.00, t = 60.39 s / 680.11 tokens per second
llama-server | 11130.28.529.739 I slot print_timing: id 0 | task 2825091 | prompt eval time = 1561.93 ms / 411 tokens ( 3.80 ms per token, 263.14 tokens per second)
llama-server | 11130.28.529.742 I slot print_timing: id 0 | task 2825091 | eval time = 70055.32 ms / 297 tokens ( 236.67 ms per token, 4.23 tokens per second)
llama-server | 11130.28.529.742 I slot print_timing: id 0 | task 2825091 | total time = 71617.26 ms / 708 tokens
llama-server | 11130.28.529.743 I slot print_timing: id 0 | task 2825091 | graphs reused = 2735265
llama-server | 11130.28.529.746 I slot print_timing: id 0 | task 2825091 | draft acceptance = 0.50476 ( 212 accepted / 420 generated), mean len = 3.52
llama-server | 11130.28.530.313 I slot release: id 0 | task 2825091 | stop processing: n_tokens = 17153, truncated = 0
llama-server | 11130.28.849.931 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.983 (> 0.100 thold), f_keep = 0.983
llama-server | 11130.28.850.375 I slot launch_slot_: id 0 | task 2825182 | processing task, is_child = 0
llama-server | 11130.31.141.400 I slot print_timing: id 1 | task 2825135 | n_gen = 100, tg = 20.99 t/s, tg_3s = 21.20 t/s
llama-server | 11130.34.152.679 I slot print_timing: id 1 | task 2825135 | n_gen = 176, tg = 22.64 t/s, tg_3s = 25.24 t/s
llama-server | 11130.34.250.417 I slot print_timing: id 0 | task 2825182 | n_gen = 102, tg = 23.97 t/s, tg_3s = 24.20 t/s
llama-server | 11130.37.161.973 I slot print_timing: id 1 | task 2825135 | n_gen = 247, tg = 22.91 t/s, tg_3s = 23.59 t/s
llama-server | 11130.37.257.634 I slot print_timing: id 0 | task 2825182 | n_gen = 177, tg = 24.37 t/s, tg_3s = 24.94 t/s
llama-server | 11130.40.181.741 I slot print_timing: id 1 | task 2825135 | n_gen = 310, tg = 22.46 t/s, tg_3s = 20.86 t/s
llama-server | 11130.40.278.459 I slot print_timing: id 0 | task 2825182 | n_gen = 330, tg = 32.12 t/s, tg_3s = 50.65 t/s
llama-server | 11130.43.205.632 I slot print_timing: id 1 | task 2825135 | n_gen = 379, tg = 22.53 t/s, tg_3s = 22.82 t/s
llama-server | 11130.43.302.359 I slot print_timing: id 0 | task 2825182 | n_gen = 492, tg = 37.01 t/s, tg_3s = 53.57 t/s
llama-server | 11130.46.247.212 I slot print_timing: id 1 | task 2825135 | n_gen = 473, tg = 23.81 t/s, tg_3s = 30.91 t/s
llama-server | 11130.46.344.050 I slot print_timing: id 0 | task 2825182 | n_gen = 617, tg = 37.77 t/s, tg_3s = 41.10 t/s
llama-server | 11130.49.276.531 I slot print_timing: id 1 | task 2825135 | n_gen = 580, tg = 25.34 t/s, tg_3s = 35.32 t/s
llama-server | 11130.49.372.429 I slot print_timing: id 0 | task 2825182 | n_gen = 718, tg = 37.08 t/s, tg_3s = 33.35 t/s
llama-server | 11130.52.303.191 I slot print_timing: id 1 | task 2825135 | n_gen = 653, tg = 25.19 t/s, tg_3s = 24.12 t/s
llama-server | 11130.52.400.209 I slot print_timing: id 0 | task 2825182 | n_gen = 844, tg = 37.69 t/s, tg_3s = 41.61 t/s
llama-server | 11130.52.498.009 I slot print_timing: id 0 | task 2825182 | prompt eval time = 1176.88 ms / 295 tokens ( 3.99 ms per token, 250.66 tokens per second)
llama-server | 11130.52.498.013 I slot print_timing: id 0 | task 2825182 | eval time = 22462.03 ms / 848 tokens ( 26.52 ms per token, 37.71 tokens per second)
llama-server | 11130.52.498.014 I slot print_timing: id 0 | task 2825182 | total time = 23638.92 ms / 1143 tokens
llama-server | 11130.52.498.014 I slot print_timing: id 0 | task 2825182 | graphs reused = 2735496
llama-server | 11130.52.498.019 I slot print_timing: id 0 | task 2825182 | draft acceptance = 0.53652 ( 617 accepted / 1150 generated), mean len = 3.68
llama-server | 11130.52.498.686 I slot release: id 0 | task 2825182 | stop processing: n_tokens = 17995, truncated = 0
llama-server | 11130.55.379.769 I slot print_timing: id 1 | task 2825135 | n_gen = 723, tg = 24.94 t/s, tg_3s = 22.75 t/s
llama-server | 11130.55.379.784 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.940 (> 0.100 thold), f_keep = 0.953
llama-server | 11130.55.380.318 I slot launch_slot_: id 0 | task 2825444 | processing task, is_child = 0
llama-server | 11130.58.406.459 I slot print_timing: id 1 | task 2825135 | n_gen = 730, tg = 22.79 t/s, tg_3s = 2.31 t/s
llama-server | 11131.01.415.271 I slot print_timing: id 1 | task 2825135 | n_gen = 808, tg = 23.06 t/s, tg_3s = 25.92 t/s
llama-server | 11131.02.483.661 I slot print_timing: id 0 | task 2825444 | n_gen = 100, tg = 22.45 t/s, tg_3s = 22.67 t/s
llama-server | 11131.04.430.152 I slot print_timing: id 1 | task 2825135 | n_gen = 890, tg = 23.39 t/s, tg_3s = 27.20 t/s
llama-server | 11131.05.499.503 I slot print_timing: id 0 | task 2825444 | n_gen = 161, tg = 21.54 t/s, tg_3s = 20.23 t/s
llama-server | 11131.07.479.200 I slot print_timing: id 1 | task 2825135 | n_gen = 962, tg = 23.41 t/s, tg_3s = 23.61 t/s
llama-server | 11131.08.551.579 I slot print_timing: id 0 | task 2825444 | n_gen = 220, tg = 20.90 t/s, tg_3s = 19.33 t/s
llama-server | 11131.10.012.851 I slot print_timing: id 0 | task 2825444 | prompt eval time = 2684.21 ms / 1099 tokens ( 2.44 ms per token, 409.43 tokens per second)
llama-server | 11131.10.012.854 I slot print_timing: id 0 | task 2825444 | eval time = 11939.75 ms / 272 tokens ( 44.06 ms per token, 22.70 tokens per second)
llama-server | 11131.10.012.855 I slot print_timing: id 0 | task 2825444 | total time = 14623.96 ms / 1371 tokens
llama-server | 11131.10.012.855 I slot print_timing: id 0 | task 2825444 | graphs reused = 2735643
llama-server | 11131.10.012.858 I slot print_timing: id 0 | task 2825444 | draft acceptance = 0.25167 ( 151 accepted / 600 generated), mean len = 2.26
llama-server | 11131.10.013.427 I slot release: id 0 | task 2825444 | stop processing: n_tokens = 18514, truncated = 0
llama-server | 11131.10.333.906 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.977 (> 0.100 thold), f_keep = 0.985
llama-server | 11131.10.334.483 I slot launch_slot_: id 0 | task 2825571 | processing task, is_child = 0
llama-server | 11131.11.504.270 I slot print_timing: id 1 | task 2825135 | n_gen = 1050, tg = 23.27 t/s, tg_3s = 21.86 t/s
llama-server | 11131.14.586.507 I slot print_timing: id 1 | task 2825135 | n_gen = 1122, tg = 23.28 t/s, tg_3s = 23.36 t/s
llama-server | 11131.15.846.825 I slot print_timing: id 0 | task 2825571 | n_gen = 104, tg = 26.25 t/s, tg_3s = 26.50 t/s
llama-server | 11131.17.677.409 I slot print_timing: id 1 | task 2825135 | n_gen = 1175, tg = 22.91 t/s, tg_3s = 17.15 t/s
llama-server | 11131.18.848.840 I slot print_timing: id 0 | task 2825571 | n_gen = 234, tg = 33.64 t/s, tg_3s = 43.30 t/s
llama-server | 11131.20.705.481 I slot print_timing: id 1 | task 2825135 | n_gen = 1260, tg = 23.19 t/s, tg_3s = 28.07 t/s
llama-server | 11131.21.875.681 I slot print_timing: id 0 | task 2825571 | prompt eval time = 1579.52 ms / 430 tokens ( 3.67 ms per token, 272.23 tokens per second)
llama-server | 11131.21.875.683 I slot print_timing: id 0 | task 2825571 | eval time = 9952.93 ms / 365 tokens ( 27.34 ms per token, 36.57 tokens per second)
llama-server | 11131.21.875.684 I slot print_timing: id 0 | task 2825571 | total time = 11532.45 ms / 795 tokens
llama-server | 11131.21.875.685 I slot print_timing: id 0 | task 2825571 | graphs reused = 2735740
llama-server | 11131.21.875.687 I slot print_timing: id 0 | task 2825571 | draft acceptance = 0.56042 ( 269 accepted / 480 generated), mean len = 3.80
llama-server | 11131.21.876.266 I slot release: id 0 | task 2825571 | stop processing: n_tokens = 19034, truncated = 0
llama-server | 11131.22.097.114 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.971 (> 0.100 thold), f_keep = 0.981
llama-server | 11131.22.097.527 I slot launch_slot_: id 0 | task 2825672 | processing task, is_child = 0
llama-server | 11131.24.017.938 I slot print_timing: id 1 | task 2825135 | n_gen = 1317, tg = 22.85 t/s, tg_3s = 17.21 t/s
llama-server | 11131.26.501.311 I slot print_timing: id 1 | task 2825135 | prompt eval time = 60838.68 ms / 41076 tokens ( 1.48 ms per token, 675.16 tokens per second)
llama-server | 11131.26.501.327 I slot print_timing: id 1 | task 2825135 | eval time = 60076.60 ms / 1407 tokens ( 42.73 ms per token, 23.40 tokens per second)
llama-server | 11131.26.501.328 I slot print_timing: id 1 | task 2825135 | total time = 120915.28 ms / 42483 tokens
llama-server | 11131.26.501.329 I slot print_timing: id 1 | task 2825135 | graphs reused = 2735763
llama-server | 11131.26.501.333 I slot print_timing: id 1 | task 2825135 | draft acceptance = 0.32268 ( 868 accepted / 2690 generated), mean len = 2.61
llama-server | 11131.26.503.060 I slot release: id 1 | task 2825135 | stop processing: n_tokens = 42482, truncated = 0
llama-server | 11131.28.596.632 I slot print_timing: id 0 | task 2825672 | n_gen = 101, tg = 21.83 t/s, tg_3s = 22.05 t/s
llama-server | 11131.28.596.640 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 667902343111
llama-server | 11131.28.598.836 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1918.925 MiB)
llama-server | 11131.31.604.070 I slot launch_slot_: id 1 | task 2825721 | processing task, is_child = 0
llama-server | 11131.34.629.947 I slot print_timing: id 0 | task 2825672 | n_gen = 107, tg = 9.99 t/s, tg_3s = 0.99 t/s
llama-server | 11131.37.623.800 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 4084, progress = 0.10, t = 5.78 s / 706.49 tokens per second
llama-server | 11131.40.618.209 I slot print_timing: id 0 | task 2825672 | n_gen = 117, tg = 6.99 t/s, tg_3s = 1.67 t/s
llama-server | 11131.40.630.040 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 6126, progress = 0.15, t = 8.79 s / 697.14 tokens per second
llama-server | 11131.43.599.202 W srv stop: cancel task, id_task = 2825672
llama-server | 11131.43.610.651 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 8168, progress = 0.20, t = 11.77 s / 693.99 tokens per second
llama-server | 11131.46.577.984 I slot print_timing: id 0 | task 2825672 | n_gen = 120, tg = 5.27 t/s, tg_3s = 0.50 t/s
llama-server | 11131.46.577.990 I slot release: id 0 | task 2825672 | stop processing: n_tokens = 19343, truncated = 0
llama-server | 11131.46.578.035 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 10210, progress = 0.25, t = 14.75 s / 692.26 tokens per second
llama-server | 11131.49.474.231 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 12258, progress = 0.30, t = 16.99 s / 721.55 tokens per second
llama-server | 11131.52.347.876 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 14306, progress = 0.35, t = 19.86 s / 720.20 tokens per second
llama-server | 11131.55.224.679 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 16354, progress = 0.40, t = 22.74 s / 719.20 tokens per second
llama-server | 11131.58.431.364 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 18402, progress = 0.45, t = 25.61 s / 718.44 tokens per second
llama-server | 11132.01.322.339 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 20450, progress = 0.50, t = 28.84 s / 709.14 tokens per second
llama-server | 11132.04.199.925 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 22498, progress = 0.55, t = 31.71 s / 709.41 tokens per second
llama-server | 11132.07.078.320 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 24546, progress = 0.60, t = 34.59 s / 709.58 tokens per second
llama-server | 11132.09.955.927 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 26594, progress = 0.65, t = 37.47 s / 709.76 tokens per second
llama-server | 11132.12.833.264 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 28642, progress = 0.70, t = 40.35 s / 709.89 tokens per second
llama-server | 11132.15.710.400 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 30690, progress = 0.75, t = 43.22 s / 710.01 tokens per second
llama-server | 11132.18.606.279 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 32738, progress = 0.80, t = 46.10 s / 710.12 tokens per second
llama-server | 11132.21.477.424 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 34786, progress = 0.85, t = 49.00 s / 709.95 tokens per second
llama-server | 11132.24.351.730 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 36834, progress = 0.90, t = 51.87 s / 710.13 tokens per second
llama-server | 11132.27.228.363 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 38882, progress = 0.95, t = 54.75 s / 710.22 tokens per second
llama-server | 11132.29.611.731 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 40503, progress = 0.99, t = 57.63 s / 702.87 tokens per second
llama-server | 11132.30.529.574 I slot print_timing: id 1 | task 2825721 | prompt processing, n_tokens = 41015, progress = 1.00, t = 58.20 s / 704.67 tokens per second
llama-server | 11132.33.846.038 I slot print_timing: id 1 | task 2825721 | n_gen = 104, tg = 33.51 t/s, tg_3s = 33.84 t/s
llama-server | 11132.36.902.328 I slot print_timing: id 1 | task 2825721 | n_gen = 199, tg = 32.30 t/s, tg_3s = 31.08 t/s
llama-server | 11132.39.960.066 I slot print_timing: id 1 | task 2825721 | n_gen = 290, tg = 31.46 t/s, tg_3s = 29.76 t/s
llama-server | 11132.43.017.625 I slot print_timing: id 1 | task 2825721 | n_gen = 381, tg = 31.03 t/s, tg_3s = 29.76 t/s
llama-server | 11132.46.071.438 I slot print_timing: id 1 | task 2825721 | n_gen = 468, tg = 30.53 t/s, tg_3s = 28.49 t/s
llama-server | 11132.49.125.809 I slot print_timing: id 1 | task 2825721 | n_gen = 551, tg = 29.97 t/s, tg_3s = 27.17 t/s
llama-server | 11132.52.178.665 I slot print_timing: id 1 | task 2825721 | n_gen = 629, tg = 29.34 t/s, tg_3s = 25.55 t/s
llama-server | 11132.55.237.544 I slot print_timing: id 1 | task 2825721 | n_gen = 723, tg = 29.51 t/s, tg_3s = 30.73 t/s
llama-server | 11132.58.305.406 I slot print_timing: id 1 | task 2825721 | n_gen = 837, tg = 30.36 t/s, tg_3s = 37.16 t/s
llama-server | 11133.01.370.036 I slot print_timing: id 1 | task 2825721 | n_gen = 930, tg = 30.36 t/s, tg_3s = 30.35 t/s
llama-server | 11133.04.438.434 I slot print_timing: id 1 | task 2825721 | n_gen = 1037, tg = 30.77 t/s, tg_3s = 34.87 t/s
llama-server | 11133.07.505.906 I slot print_timing: id 1 | task 2825721 | n_gen = 1116, tg = 30.35 t/s, tg_3s = 25.75 t/s
llama-server | 11133.10.575.807 I slot print_timing: id 1 | task 2825721 | n_gen = 1201, tg = 30.15 t/s, tg_3s = 27.69 t/s
llama-server | 11133.13.637.471 I slot print_timing: id 1 | task 2825721 | n_gen = 1295, tg = 30.19 t/s, tg_3s = 30.70 t/s
llama-server | 11133.16.698.700 I slot print_timing: id 1 | task 2825721 | n_gen = 1373, tg = 29.87 t/s, tg_3s = 25.48 t/s
llama-server | 11133.19.767.935 I slot print_timing: id 1 | task 2825721 | n_gen = 1473, tg = 30.04 t/s, tg_3s = 32.58 t/s
llama-server | 11133.22.829.231 I slot print_timing: id 1 | task 2825721 | n_gen = 1555, tg = 29.85 t/s, tg_3s = 26.79 t/s
llama-server | 11133.25.912.231 I slot print_timing: id 1 | task 2825721 | n_gen = 1639, tg = 29.71 t/s, tg_3s = 27.25 t/s
llama-server | 11133.28.982.263 I slot print_timing: id 1 | task 2825721 | n_gen = 1728, tg = 29.67 t/s, tg_3s = 28.99 t/s
llama-server | 11133.32.052.528 I slot print_timing: id 1 | task 2825721 | n_gen = 1817, tg = 29.63 t/s, tg_3s = 28.99 t/s
llama-server | 11133.35.138.109 I slot print_timing: id 1 | task 2825721 | n_gen = 1913, tg = 29.71 t/s, tg_3s = 31.11 t/s
llama-server | 11133.38.209.096 I slot print_timing: id 1 | task 2825721 | n_gen = 1998, tg = 29.61 t/s, tg_3s = 27.68 t/s
llama-server | 11133.41.274.039 I slot print_timing: id 1 | task 2825721 | n_gen = 2066, tg = 29.29 t/s, tg_3s = 22.19 t/s
llama-server | 11133.44.364.532 I slot print_timing: id 1 | task 2825721 | n_gen = 2154, tg = 29.26 t/s, tg_3s = 28.47 t/s
llama-server | 11133.47.438.844 I slot print_timing: id 1 | task 2825721 | n_gen = 2231, tg = 29.09 t/s, tg_3s = 25.05 t/s
llama-server | 11133.50.521.925 I slot print_timing: id 1 | task 2825721 | n_gen = 2346, tg = 29.40 t/s, tg_3s = 37.30 t/s
llama-server | 11133.53.525.063 I slot print_timing: id 1 | task 2825721 | n_gen = 2457, tg = 29.68 t/s, tg_3s = 36.96 t/s
llama-server | 11133.56.617.129 I slot print_timing: id 1 | task 2825721 | n_gen = 2586, tg = 30.11 t/s, tg_3s = 41.72 t/s
llama-server | 11133.59.427.616 I slot print_timing: id 1 | task 2825721 | prompt eval time = 59156.60 ms / 41019 tokens ( 1.44 ms per token, 693.40 tokens per second)
llama-server | 11133.59.427.619 I slot print_timing: id 1 | task 2825721 | eval time = 88654.91 ms / 2695 tokens ( 32.91 ms per token, 30.39 tokens per second)
llama-server | 11133.59.427.620 I slot print_timing: id 1 | task 2825721 | total time = 147811.51 ms / 43714 tokens
llama-server | 11133.59.427.620 I slot print_timing: id 1 | task 2825721 | graphs reused = 2736740
llama-server | 11133.59.427.623 I slot print_timing: id 1 | task 2825721 | draft acceptance = 0.40201 ( 1799 accepted / 4475 generated), mean len = 3.01
llama-server | 11133.59.428.938 I slot release: id 1 | task 2825721 | stop processing: n_tokens = 43713, truncated = 0
llama-server | 11134.01.049.183 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 667922418041
llama-server | 11134.01.050.685 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1938.343 MiB)
llama-server | 11134.01.253.153 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1930.662 MiB)
llama-server | 11134.01.429.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2071.006 MiB)
llama-server | 11134.08.041.046 I slot launch_slot_: id 0 | task 2826640 | processing task, is_child = 0
llama-server | 11134.08.043.236 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1981.500 MiB)
llama-server | 11134.15.131.820 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 4096, progress = 0.10, t = 3.71 s / 1103.09 tokens per second
llama-server | 11134.16.932.605 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 6144, progress = 0.15, t = 5.51 s / 1116.03 tokens per second
llama-server | 11134.18.771.100 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 8192, progress = 0.20, t = 7.33 s / 1117.14 tokens per second
llama-server | 11134.20.645.422 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 10240, progress = 0.25, t = 9.20 s / 1113.16 tokens per second
llama-server | 11134.22.557.185 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 12288, progress = 0.30, t = 11.10 s / 1106.85 tokens per second
llama-server | 11134.24.508.876 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 14336, progress = 0.35, t = 13.04 s / 1099.11 tokens per second
llama-server | 11134.26.502.595 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 16384, progress = 0.40, t = 15.02 s / 1090.52 tokens per second
llama-server | 11134.28.532.861 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 18432, progress = 0.45, t = 17.05 s / 1081.19 tokens per second
llama-server | 11134.30.602.191 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 20480, progress = 0.50, t = 19.11 s / 1071.90 tokens per second
llama-server | 11134.32.712.768 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 22528, progress = 0.55, t = 21.20 s / 1062.40 tokens per second
llama-server | 11134.34.877.395 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 24576, progress = 0.60, t = 23.35 s / 1052.59 tokens per second
llama-server | 11134.37.066.084 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 26624, progress = 0.65, t = 25.54 s / 1042.47 tokens per second
llama-server | 11134.39.293.762 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 28672, progress = 0.70, t = 27.76 s / 1033.00 tokens per second
llama-server | 11134.41.555.705 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 30720, progress = 0.75, t = 30.01 s / 1023.63 tokens per second
llama-server | 11134.43.888.026 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 32768, progress = 0.80, t = 32.30 s / 1014.53 tokens per second
llama-server | 11134.46.222.599 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 34816, progress = 0.85, t = 34.66 s / 1004.53 tokens per second
llama-server | 11134.48.592.884 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 36864, progress = 0.90, t = 37.02 s / 995.82 tokens per second
llama-server | 11134.51.001.662 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 38912, progress = 0.95, t = 39.42 s / 987.15 tokens per second
llama-server | 11134.52.823.037 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 40438, progress = 0.99, t = 41.28 s / 979.66 tokens per second
llama-server | 11134.53.556.065 I slot print_timing: id 0 | task 2826640 | prompt processing, n_tokens = 40950, progress = 1.00, t = 42.04 s / 974.10 tokens per second
llama-server | 11134.57.278.233 I slot print_timing: id 0 | task 2826640 | n_gen = 102, tg = 28.31 t/s, tg_3s = 28.59 t/s
llama-server | 11135.00.295.839 I slot print_timing: id 0 | task 2826640 | n_gen = 200, tg = 30.22 t/s, tg_3s = 32.48 t/s
llama-server | 11135.03.337.703 I slot print_timing: id 0 | task 2826640 | n_gen = 316, tg = 32.72 t/s, tg_3s = 38.13 t/s
llama-server | 11135.04.230.087 I slot print_timing: id 0 | task 2826640 | prompt eval time = 42826.12 ms / 40954 tokens ( 1.05 ms per token, 956.29 tokens per second)
llama-server | 11135.04.230.090 I slot print_timing: id 0 | task 2826640 | eval time = 10519.03 ms / 358 tokens ( 29.47 ms per token, 33.94 tokens per second)
llama-server | 11135.04.230.090 I slot print_timing: id 0 | task 2826640 | total time = 53345.16 ms / 41312 tokens
llama-server | 11135.04.230.091 I slot print_timing: id 0 | task 2826640 | graphs reused = 2736855
llama-server | 11135.04.230.094 I slot print_timing: id 0 | task 2826640 | draft acceptance = 0.40508 ( 239 accepted / 590 generated), mean len = 3.03
llama-server | 11135.04.231.353 I slot release: id 0 | task 2826640 | stop processing: n_tokens = 41311, truncated = 0
llama-server | 11135.21.559.956 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 668055268990
llama-server | 11135.21.560.613 I slot launch_slot_: id 1 | task 2826781 | processing task, is_child = 0
llama-server | 11135.21.563.386 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 5764.192 MiB)
llama-server | 11135.28.286.902 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 6144, progress = 0.15, t = 4.75 s / 1294.60 tokens per second
llama-server | 11135.30.114.155 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 8192, progress = 0.20, t = 6.56 s / 1248.19 tokens per second
llama-server | 11135.31.976.559 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 10240, progress = 0.25, t = 8.42 s / 1216.37 tokens per second
llama-server | 11135.33.878.816 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 12288, progress = 0.30, t = 10.31 s / 1191.81 tokens per second
llama-server | 11135.35.820.491 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 14336, progress = 0.35, t = 12.24 s / 1171.04 tokens per second
llama-server | 11135.37.802.502 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 16384, progress = 0.40, t = 14.21 s / 1152.82 tokens per second
llama-server | 11135.39.823.457 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 18432, progress = 0.45, t = 16.22 s / 1136.03 tokens per second
llama-server | 11135.41.886.402 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 20480, progress = 0.50, t = 18.28 s / 1120.57 tokens per second
llama-server | 11135.44.016.987 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 22528, progress = 0.55, t = 20.37 s / 1105.98 tokens per second
llama-server | 11135.46.175.823 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 24576, progress = 0.60, t = 22.53 s / 1090.64 tokens per second
llama-server | 11135.48.362.649 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 26624, progress = 0.65, t = 24.72 s / 1076.97 tokens per second
llama-server | 11135.50.588.275 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 28672, progress = 0.70, t = 26.93 s / 1064.54 tokens per second
llama-server | 11135.52.847.202 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 30720, progress = 0.75, t = 29.19 s / 1052.54 tokens per second
llama-server | 11135.55.177.717 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 32768, progress = 0.80, t = 31.47 s / 1041.18 tokens per second
llama-server | 11135.57.510.560 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 34816, progress = 0.85, t = 33.83 s / 1029.12 tokens per second
llama-server | 11135.59.881.702 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 36864, progress = 0.90, t = 36.19 s / 1018.59 tokens per second
llama-server | 11136.02.286.205 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 38912, progress = 0.95, t = 38.59 s / 1008.33 tokens per second
llama-server | 11136.04.401.439 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 40614, progress = 0.99, t = 41.02 s / 990.13 tokens per second
llama-server | 11136.05.107.386 I slot print_timing: id 1 | task 2826781 | prompt processing, n_tokens = 41126, progress = 1.00, t = 41.50 s / 990.87 tokens per second
llama-server | 11136.08.321.439 I slot print_timing: id 1 | task 2826781 | n_gen = 113, tg = 36.62 t/s, tg_3s = 36.95 t/s
llama-server | 11136.11.335.422 I slot print_timing: id 1 | task 2826781 | n_gen = 236, tg = 38.70 t/s, tg_3s = 40.81 t/s
llama-server | 11136.14.196.405 I slot print_timing: id 1 | task 2826781 | prompt eval time = 42264.44 ms / 41130 tokens ( 1.03 ms per token, 973.16 tokens per second)
llama-server | 11136.14.196.408 I slot print_timing: id 1 | task 2826781 | eval time = 8933.22 ms / 370 tokens ( 24.21 ms per token, 41.31 tokens per second)
llama-server | 11136.14.196.408 I slot print_timing: id 1 | task 2826781 | total time = 51197.66 ms / 41500 tokens
llama-server | 11136.14.196.409 I slot print_timing: id 1 | task 2826781 | graphs reused = 2736952
llama-server | 11136.14.196.412 I slot print_timing: id 1 | task 2826781 | draft acceptance = 0.53800 ( 269 accepted / 500 generated), mean len = 3.69
llama-server | 11136.14.197.693 I slot release: id 1 | task 2826781 | stop processing: n_tokens = 41499, truncated = 0
llama-server | 11136.31.933.337 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 668120071405
llama-server | 11136.31.934.206 I slot launch_slot_: id 0 | task 2826904 | processing task, is_child = 0
llama-server | 11136.38.627.733 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.74 s / 1295.83 tokens per second
llama-server | 11136.40.455.152 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 8192, progress = 0.17, t = 6.56 s / 1248.56 tokens per second
llama-server | 11136.42.315.126 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 10240, progress = 0.21, t = 8.42 s / 1216.78 tokens per second
llama-server | 11136.44.213.737 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 12288, progress = 0.26, t = 10.30 s / 1192.47 tokens per second
llama-server | 11136.46.151.650 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 14336, progress = 0.30, t = 12.23 s / 1171.98 tokens per second
llama-server | 11136.48.133.015 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 16384, progress = 0.34, t = 14.20 s / 1153.84 tokens per second
llama-server | 11136.50.154.055 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 18432, progress = 0.39, t = 16.21 s / 1136.79 tokens per second
llama-server | 11136.52.214.901 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 20480, progress = 0.43, t = 18.26 s / 1121.37 tokens per second
llama-server | 11136.54.317.340 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 22528, progress = 0.47, t = 20.35 s / 1106.82 tokens per second
llama-server | 11136.56.476.302 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 24576, progress = 0.52, t = 22.49 s / 1092.67 tokens per second
llama-server | 11136.58.660.475 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 26624, progress = 0.56, t = 24.68 s / 1078.92 tokens per second
llama-server | 11137.00.882.882 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 28672, progress = 0.60, t = 26.89 s / 1066.33 tokens per second
llama-server | 11137.03.141.102 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 30720, progress = 0.64, t = 29.14 s / 1054.25 tokens per second
llama-server | 11137.05.470.168 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 32768, progress = 0.69, t = 31.42 s / 1042.82 tokens per second
llama-server | 11137.07.799.195 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 34816, progress = 0.73, t = 33.78 s / 1030.69 tokens per second
llama-server | 11137.10.169.912 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 36864, progress = 0.77, t = 36.14 s / 1020.15 tokens per second
llama-server | 11137.12.573.193 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 38912, progress = 0.82, t = 38.53 s / 1009.79 tokens per second
llama-server | 11137.15.029.069 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 40960, progress = 0.86, t = 40.96 s / 999.93 tokens per second
llama-server | 11137.17.503.501 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 43008, progress = 0.90, t = 43.45 s / 989.92 tokens per second
llama-server | 11137.20.014.849 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 45056, progress = 0.94, t = 45.95 s / 980.58 tokens per second
llama-server | 11137.22.563.326 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 47104, progress = 0.99, t = 48.49 s / 971.49 tokens per second
llama-server | 11137.22.720.775 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 47168, progress = 0.99, t = 49.23 s / 958.06 tokens per second
llama-server | 11137.23.454.804 I slot print_timing: id 0 | task 2826904 | prompt processing, n_tokens = 47680, progress = 1.00, t = 49.48 s / 963.60 tokens per second
llama-server | 11137.26.663.949 I slot print_timing: id 0 | task 2826904 | n_gen = 120, tg = 39.01 t/s, tg_3s = 39.34 t/s
llama-server | 11137.29.686.091 I slot print_timing: id 0 | task 2826904 | n_gen = 183, tg = 29.97 t/s, tg_3s = 20.85 t/s
llama-server | 11137.32.736.738 I slot print_timing: id 0 | task 2826904 | n_gen = 254, tg = 27.73 t/s, tg_3s = 23.27 t/s
llama-server | 11137.35.776.029 I slot print_timing: id 0 | task 2826904 | n_gen = 364, tg = 29.85 t/s, tg_3s = 36.19 t/s
llama-server | 11137.38.832.269 I slot print_timing: id 0 | task 2826904 | n_gen = 493, tg = 32.33 t/s, tg_3s = 42.21 t/s
llama-server | 11137.41.507.652 I slot print_timing: id 0 | task 2826904 | prompt eval time = 50272.56 ms / 47684 tokens ( 1.05 ms per token, 948.51 tokens per second)
llama-server | 11137.41.507.655 I slot print_timing: id 0 | task 2826904 | eval time = 17894.01 ms / 600 tokens ( 29.87 ms per token, 33.47 tokens per second)
llama-server | 11137.41.507.655 I slot print_timing: id 0 | task 2826904 | total time = 68166.57 ms / 48284 tokens
llama-server | 11137.41.507.656 I slot print_timing: id 0 | task 2826904 | graphs reused = 2737143
llama-server | 11137.41.507.659 I slot print_timing: id 0 | task 2826904 | draft acceptance = 0.41753 ( 405 accepted / 970 generated), mean len = 3.09
llama-server | 11137.41.508.946 I slot release: id 0 | task 2826904 | stop processing: n_tokens = 48283, truncated = 0
llama-server | 11137.42.883.666 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 668190037745
llama-server | 11137.42.884.332 I slot launch_slot_: id 1 | task 2827125 | processing task, is_child = 0
llama-server | 11137.47.722.501 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 4096, progress = 0.09, t = 3.00 s / 1365.28 tokens per second
llama-server | 11137.49.539.498 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.81 s / 1277.82 tokens per second
llama-server | 11137.51.395.051 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 8192, progress = 0.17, t = 6.65 s / 1231.42 tokens per second
llama-server | 11137.53.284.228 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 10240, progress = 0.21, t = 8.53 s / 1199.78 tokens per second
llama-server | 11137.55.214.603 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 12288, progress = 0.26, t = 10.45 s / 1175.57 tokens per second
llama-server | 11137.57.194.578 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 14336, progress = 0.30, t = 12.42 s / 1153.90 tokens per second
llama-server | 11137.59.196.537 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 16384, progress = 0.34, t = 14.42 s / 1136.54 tokens per second
llama-server | 11138.01.235.837 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 18432, progress = 0.38, t = 16.45 s / 1120.54 tokens per second
llama-server | 11138.03.313.821 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 20480, progress = 0.43, t = 18.52 s / 1106.06 tokens per second
llama-server | 11138.05.432.747 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 22528, progress = 0.47, t = 20.62 s / 1092.37 tokens per second
llama-server | 11138.07.605.494 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 24576, progress = 0.51, t = 22.78 s / 1079.07 tokens per second
llama-server | 11138.09.801.476 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 26624, progress = 0.55, t = 24.97 s / 1066.11 tokens per second
llama-server | 11138.12.032.869 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 28672, progress = 0.60, t = 27.19 s / 1054.33 tokens per second
llama-server | 11138.14.298.758 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 30720, progress = 0.64, t = 29.45 s / 1043.02 tokens per second
llama-server | 11138.16.636.996 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 32768, progress = 0.68, t = 31.74 s / 1032.29 tokens per second
llama-server | 11138.18.973.309 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 34816, progress = 0.72, t = 34.11 s / 1020.74 tokens per second
llama-server | 11138.21.346.871 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 36864, progress = 0.77, t = 36.47 s / 1010.75 tokens per second
llama-server | 11138.23.753.169 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 38912, progress = 0.81, t = 38.87 s / 1001.02 tokens per second
llama-server | 11138.26.210.912 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 40960, progress = 0.85, t = 41.30 s / 991.69 tokens per second
llama-server | 11138.28.686.503 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 43008, progress = 0.90, t = 43.79 s / 982.21 tokens per second
llama-server | 11138.31.199.119 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 45056, progress = 0.94, t = 46.29 s / 973.36 tokens per second
llama-server | 11138.33.746.717 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 47104, progress = 0.98, t = 48.83 s / 964.69 tokens per second
llama-server | 11138.34.338.978 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 47517, progress = 0.99, t = 49.58 s / 958.44 tokens per second
llama-server | 11138.35.076.374 I slot print_timing: id 1 | task 2827125 | prompt processing, n_tokens = 48029, progress = 1.00, t = 50.26 s / 955.67 tokens per second
llama-server | 11138.38.761.481 I slot print_timing: id 1 | task 2827125 | n_gen = 100, tg = 28.08 t/s, tg_3s = 28.36 t/s
llama-server | 11138.41.800.421 I slot print_timing: id 1 | task 2827125 | n_gen = 189, tg = 28.64 t/s, tg_3s = 29.29 t/s
llama-server | 11138.44.833.851 I slot print_timing: id 1 | task 2827125 | n_gen = 264, tg = 27.40 t/s, tg_3s = 24.72 t/s
llama-server | 11138.47.886.545 I slot print_timing: id 1 | task 2827125 | n_gen = 373, tg = 29.40 t/s, tg_3s = 35.71 t/s
llama-server | 11138.50.751.497 I slot print_timing: id 1 | task 2827125 | prompt eval time = 51050.25 ms / 48033 tokens ( 1.06 ms per token, 940.90 tokens per second)
llama-server | 11138.50.751.501 I slot print_timing: id 1 | task 2827125 | eval time = 15516.08 ms / 499 tokens ( 31.16 ms per token, 32.10 tokens per second)
llama-server | 11138.50.751.501 I slot print_timing: id 1 | task 2827125 | total time = 66566.33 ms / 48532 tokens
llama-server | 11138.50.751.502 I slot print_timing: id 1 | task 2827125 | graphs reused = 2737308
llama-server | 11138.50.751.505 I slot print_timing: id 1 | task 2827125 | draft acceptance = 0.39405 ( 331 accepted / 840 generated), mean len = 2.97
llama-server | 11138.50.752.813 I slot release: id 1 | task 2827125 | stop processing: n_tokens = 48532, truncated = 0
llama-server | 11138.52.164.773 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 668277348998
llama-server | 11138.52.165.443 I slot launch_slot_: id 0 | task 2827320 | processing task, is_child = 0
llama-server | 11138.52.168.586 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2022.429 MiB)
llama-server | 11138.52.378.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1942.565 MiB)
llama-server | 11138.59.039.624 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 6144, progress = 0.13, t = 4.80 s / 1280.24 tokens per second
llama-server | 11139.00.896.226 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 8192, progress = 0.17, t = 6.64 s / 1233.92 tokens per second
llama-server | 11139.02.781.073 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 10240, progress = 0.21, t = 8.52 s / 1201.56 tokens per second
llama-server | 11139.04.719.382 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 12288, progress = 0.25, t = 10.45 s / 1176.09 tokens per second
llama-server | 11139.06.681.326 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 14336, progress = 0.30, t = 12.40 s / 1155.77 tokens per second
llama-server | 11139.08.684.232 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 16384, progress = 0.34, t = 14.39 s / 1138.26 tokens per second
llama-server | 11139.10.725.783 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 18432, progress = 0.38, t = 16.43 s / 1122.10 tokens per second
llama-server | 11139.12.801.804 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 20480, progress = 0.42, t = 18.50 s / 1107.32 tokens per second
llama-server | 11139.14.928.484 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 22528, progress = 0.46, t = 20.60 s / 1093.57 tokens per second
llama-server | 11139.17.100.280 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 24576, progress = 0.51, t = 22.76 s / 1079.72 tokens per second
llama-server | 11139.19.295.592 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 26624, progress = 0.55, t = 24.96 s / 1066.78 tokens per second
llama-server | 11139.21.527.603 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 28672, progress = 0.59, t = 27.18 s / 1054.91 tokens per second
llama-server | 11139.23.795.261 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 30720, progress = 0.63, t = 29.44 s / 1043.54 tokens per second
llama-server | 11139.26.132.022 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 32768, progress = 0.68, t = 31.73 s / 1032.61 tokens per second
llama-server | 11139.28.468.109 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 34816, progress = 0.72, t = 34.09 s / 1021.18 tokens per second
llama-server | 11139.30.839.486 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 36864, progress = 0.76, t = 36.46 s / 1011.17 tokens per second
llama-server | 11139.33.245.620 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 38912, progress = 0.80, t = 38.85 s / 1001.48 tokens per second
llama-server | 11139.35.711.023 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 40960, progress = 0.84, t = 41.29 s / 992.08 tokens per second
llama-server | 11139.38.188.177 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 43008, progress = 0.89, t = 43.78 s / 982.38 tokens per second
llama-server | 11139.40.702.549 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 45056, progress = 0.93, t = 46.28 s / 973.49 tokens per second
llama-server | 11139.43.253.015 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 47104, progress = 0.97, t = 48.82 s / 964.75 tokens per second
llama-server | 11139.44.428.768 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 47977, progress = 0.99, t = 50.18 s / 956.05 tokens per second
llama-server | 11139.45.168.073 I slot print_timing: id 0 | task 2827320 | prompt processing, n_tokens = 48489, progress = 1.00, t = 50.84 s / 953.82 tokens per second
llama-server | 11139.49.031.685 I slot print_timing: id 0 | task 2827320 | n_gen = 100, tg = 26.72 t/s, tg_3s = 26.99 t/s
llama-server | 11139.52.092.434 I slot print_timing: id 0 | task 2827320 | n_gen = 185, tg = 27.20 t/s, tg_3s = 27.77 t/s
llama-server | 11139.55.136.057 I slot print_timing: id 0 | task 2827320 | n_gen = 269, tg = 27.32 t/s, tg_3s = 27.60 t/s
llama-server | 11139.58.193.593 I slot print_timing: id 0 | task 2827320 | n_gen = 382, tg = 29.61 t/s, tg_3s = 36.96 t/s
llama-server | 11140.01.265.420 I slot print_timing: id 0 | task 2827320 | n_gen = 518, tg = 32.44 t/s, tg_3s = 44.27 t/s
llama-server | 11140.04.318.305 I slot print_timing: id 0 | task 2827320 | n_gen = 628, tg = 33.01 t/s, tg_3s = 36.03 t/s
llama-server | 11140.07.403.989 I slot print_timing: id 0 | task 2827320 | n_gen = 762, tg = 34.47 t/s, tg_3s = 43.43 t/s
llama-server | 11140.10.469.090 I slot print_timing: id 0 | task 2827320 | n_gen = 867, tg = 34.44 t/s, tg_3s = 34.26 t/s
llama-server | 11140.13.548.900 I slot print_timing: id 0 | task 2827320 | n_gen = 951, tg = 33.66 t/s, tg_3s = 27.27 t/s
llama-server | 11140.15.033.397 I slot print_timing: id 0 | task 2827320 | prompt eval time = 51632.42 ms / 48493 tokens ( 1.06 ms per token, 939.20 tokens per second)
llama-server | 11140.15.033.400 I slot print_timing: id 0 | task 2827320 | eval time = 29706.52 ms / 993 tokens ( 29.95 ms per token, 33.39 tokens per second)
llama-server | 11140.15.033.401 I slot print_timing: id 0 | task 2827320 | total time = 81338.94 ms / 49486 tokens
llama-server | 11140.15.033.402 I slot print_timing: id 0 | task 2827320 | graphs reused = 2737623
llama-server | 11140.15.033.404 I slot print_timing: id 0 | task 2827320 | draft acceptance = 0.42000 ( 672 accepted / 1600 generated), mean len = 3.10
llama-server | 11140.15.034.896 I slot release: id 0 | task 2827320 | stop processing: n_tokens = 49485, truncated = 0
llama-server | 11360.40.176.464 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 668346592865
llama-server | 11360.40.176.895 I slot launch_slot_: id 1 | task 2827667 | processing task, is_child = 0
llama-server | 11360.40.179.703 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1948.816 MiB)
llama-server | 11360.45.626.134 I slot print_timing: id 1 | task 2827667 | prompt processing, n_tokens = 4246, progress = 0.89, t = 3.32 s / 1280.05 tokens per second
llama-server | 11360.46.156.772 I slot print_timing: id 1 | task 2827667 | prompt processing, n_tokens = 4758, progress = 1.00, t = 3.83 s / 1242.33 tokens per second
llama-server | 11360.49.352.078 I slot print_timing: id 1 | task 2827667 | n_gen = 172, tg = 56.23 t/s, tg_3s = 56.55 t/s
llama-server | 11360.52.367.751 I slot print_timing: id 1 | task 2827667 | n_gen = 349, tg = 57.46 t/s, tg_3s = 58.69 t/s
llama-server | 11360.55.407.529 I slot print_timing: id 1 | task 2827667 | n_gen = 496, tg = 54.42 t/s, tg_3s = 48.36 t/s
llama-server | 11360.58.459.881 I slot print_timing: id 1 | task 2827667 | n_gen = 650, tg = 53.42 t/s, tg_3s = 50.45 t/s
llama-server | 11361.01.509.362 I slot print_timing: id 1 | task 2827667 | n_gen = 808, tg = 53.10 t/s, tg_3s = 51.81 t/s
llama-server | 11361.04.513.868 I slot print_timing: id 1 | task 2827667 | n_gen = 975, tg = 53.51 t/s, tg_3s = 55.58 t/s
llama-server | 11361.07.535.683 I slot print_timing: id 1 | task 2827667 | n_gen = 1155, tg = 54.37 t/s, tg_3s = 59.57 t/s
llama-server | 11361.10.178.708 W srv stop: cancel task, id_task = 2827667
llama-server | 11361.10.197.914 I slot get_availabl: id 0 | task -1 | selected slot by LRU, t_last = 668430874948
llama-server | 11361.10.198.295 I slot launch_slot_: id 0 | task 2828009 | processing task, is_child = 0
llama-server | 11361.10.198.298 I slot release: id 1 | task 2827667 | stop processing: n_tokens = 6109, truncated = 0
llama-server | 11361.14.229.923 I slot print_timing: id 0 | task 2828009 | prompt processing, n_tokens = 4246, progress = 0.89, t = 3.59 s / 1182.50 tokens per second
llama-server | 11361.14.796.166 I slot print_timing: id 0 | task 2828009 | prompt processing, n_tokens = 4758, progress = 1.00, t = 4.13 s / 1151.96 tokens per second
llama-server | 11361.17.933.832 I slot print_timing: id 0 | task 2828009 | n_gen = 178, tg = 58.93 t/s, tg_3s = 59.26 t/s
llama-server | 11361.20.987.519 I slot print_timing: id 0 | task 2828009 | n_gen = 350, tg = 57.62 t/s, tg_3s = 56.33 t/s
llama-server | 11361.23.994.518 I slot print_timing: id 0 | task 2828009 | n_gen = 492, tg = 54.17 t/s, tg_3s = 47.22 t/s
llama-server | 11361.27.059.029 I slot print_timing: id 0 | task 2828009 | n_gen = 640, tg = 52.68 t/s, tg_3s = 48.29 t/s
llama-server | 11361.30.066.164 I slot print_timing: id 0 | task 2828009 | n_gen = 785, tg = 51.80 t/s, tg_3s = 48.22 t/s
llama-server | 11361.33.077.632 I slot print_timing: id 0 | task 2828009 | n_gen = 914, tg = 50.31 t/s, tg_3s = 42.84 t/s
llama-server | 11361.36.151.614 I slot print_timing: id 0 | task 2828009 | n_gen = 1063, tg = 50.04 t/s, tg_3s = 48.47 t/s
llama-server | 11361.39.175.049 I slot print_timing: id 0 | task 2828009 | n_gen = 1227, tg = 50.57 t/s, tg_3s = 54.24 t/s
llama-server | 11361.42.178.728 I slot print_timing: id 0 | task 2828009 | n_gen = 1367, tg = 50.13 t/s, tg_3s = 46.61 t/s
llama-server | 11361.45.207.746 I slot print_timing: id 0 | task 2828009 | n_gen = 1545, tg = 51.00 t/s, tg_3s = 58.76 t/s
llama-server | 11361.48.236.001 I slot print_timing: id 0 | task 2828009 | n_gen = 1729, tg = 51.88 t/s, tg_3s = 60.76 t/s
llama-server | 11361.51.246.885 I slot print_timing: id 0 | task 2828009 | n_gen = 1890, tg = 52.01 t/s, tg_3s = 53.47 t/s
llama-server | 11361.54.289.632 I slot print_timing: id 0 | task 2828009 | n_gen = 2059, tg = 52.29 t/s, tg_3s = 55.54 t/s
llama-server | 11361.57.188.929 I slot print_timing: id 0 | task 2828009 | prompt eval time = 4731.72 ms / 4762 tokens ( 0.99 ms per token, 1006.40 tokens per second)
llama-server | 11361.57.188.933 I slot print_timing: id 0 | task 2828009 | eval time = 42258.66 ms / 2273 tokens ( 18.60 ms per token, 53.76 tokens per second)
llama-server | 11361.57.188.933 I slot print_timing: id 0 | task 2828009 | total time = 46990.38 ms / 7035 tokens
llama-server | 11361.57.188.934 I slot print_timing: id 0 | task 2828009 | graphs reused = 2738504
llama-server | 11361.57.188.937 I slot print_timing: id 0 | task 2828009 | draft acceptance = 0.60998 ( 1711 accepted / 2805 generated), mean len = 4.05
llama-server | 11361.57.189.127 I slot release: id 0 | task 2828009 | stop processing: n_tokens = 7034, truncated = 0
llama-server | 11361.57.335.473 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.839 (> 0.100 thold), f_keep = 0.184
llama-server | 11361.57.776.606 I slot launch_slot_: id 0 | task 2828577 | processing task, is_child = 0
llama-server | 11361.57.777.175 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2174.377 MiB)
llama-server | 11362.02.378.718 I slot print_timing: id 0 | task 2828577 | n_gen = 166, tg = 54.85 t/s, tg_3s = 55.17 t/s
llama-server | 11362.05.446.150 I slot print_timing: id 0 | task 2828577 | n_gen = 353, tg = 57.93 t/s, tg_3s = 60.96 t/s
llama-server | 11362.07.791.651 I slot print_timing: id 0 | task 2828577 | prompt eval time = 534.00 ms / 254 tokens ( 2.10 ms per token, 475.66 tokens per second)
llama-server | 11362.07.791.656 I slot print_timing: id 0 | task 2828577 | eval time = 8421.39 ms / 543 tokens ( 15.54 ms per token, 64.36 tokens per second)
llama-server | 11362.07.791.656 I slot print_timing: id 0 | task 2828577 | total time = 8955.39 ms / 797 tokens
llama-server | 11362.07.791.657 I slot print_timing: id 0 | task 2828577 | graphs reused = 2738618
llama-server | 11362.07.791.662 I slot print_timing: id 0 | task 2828577 | draft acceptance = 0.74261 ( 427 accepted / 575 generated), mean len = 4.71
llama-server | 11362.07.791.757 I slot release: id 0 | task 2828577 | stop processing: n_tokens = 2088, truncated = 0
llama-server | 11362.16.999.116 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.238 (> 0.100 thold), f_keep = 0.621
llama-server | 11362.16.999.641 I slot launch_slot_: id 0 | task 2828695 | processing task, is_child = 0
llama-server | 11362.20.433.247 I slot print_timing: id 0 | task 2828695 | prompt processing, n_tokens = 3636, progress = 0.91, t = 3.25 s / 1117.33 tokens per second
llama-server | 11362.21.004.598 I slot print_timing: id 0 | task 2828695 | prompt processing, n_tokens = 4148, progress = 1.00, t = 3.55 s / 1167.93 tokens per second
llama-server | 11362.24.198.796 I slot print_timing: id 0 | task 2828695 | n_gen = 161, tg = 53.30 t/s, tg_3s = 53.63 t/s
llama-server | 11362.27.249.669 I slot print_timing: id 0 | task 2828695 | n_gen = 317, tg = 52.21 t/s, tg_3s = 51.13 t/s
llama-server | 11362.30.302.159 I slot print_timing: id 0 | task 2828695 | n_gen = 471, tg = 51.62 t/s, tg_3s = 50.45 t/s
llama-server | 11362.33.374.371 I slot print_timing: id 0 | task 2828695 | n_gen = 636, tg = 52.15 t/s, tg_3s = 53.71 t/s
llama-server | 11362.36.441.815 I slot print_timing: id 0 | task 2828695 | n_gen = 780, tg = 51.10 t/s, tg_3s = 46.94 t/s
llama-server | 11362.39.510.257 I slot print_timing: id 0 | task 2828695 | n_gen = 956, tg = 52.15 t/s, tg_3s = 57.36 t/s
llama-server | 11362.42.511.014 I slot print_timing: id 0 | task 2828695 | n_gen = 1142, tg = 53.53 t/s, tg_3s = 61.98 t/s
llama-server | 11362.45.518.074 I slot print_timing: id 0 | task 2828695 | n_gen = 1297, tg = 53.29 t/s, tg_3s = 51.55 t/s
llama-server | 11362.47.003.590 W srv stop: cancel task, id_task = 2828695
llama-server | 11362.47.059.457 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 681686038349
llama-server | 11362.47.059.917 I slot launch_slot_: id 1 | task 2829054 | processing task, is_child = 0
llama-server | 11362.47.059.920 I slot release: id 0 | task 2828695 | stop processing: n_tokens = 6850, truncated = 0
llama-server | 11362.51.790.897 I slot print_timing: id 1 | task 2829054 | prompt processing, n_tokens = 4928, progress = 0.91, t = 4.55 s / 1084.04 tokens per second
llama-server | 11362.52.387.941 I slot print_timing: id 1 | task 2829054 | prompt processing, n_tokens = 5440, progress = 1.00, t = 4.85 s / 1122.61 tokens per second
llama-server | 11362.55.573.594 I slot print_timing: id 1 | task 2829054 | n_gen = 145, tg = 47.59 t/s, tg_3s = 47.91 t/s
llama-server | 11362.58.604.014 I slot print_timing: id 1 | task 2829054 | n_gen = 305, tg = 50.19 t/s, tg_3s = 52.80 t/s
llama-server | 11363.01.616.572 I slot print_timing: id 1 | task 2829054 | n_gen = 441, tg = 48.52 t/s, tg_3s = 45.14 t/s
llama-server | 11363.04.644.200 I slot print_timing: id 1 | task 2829054 | n_gen = 570, tg = 47.04 t/s, tg_3s = 42.61 t/s
llama-server | 11363.07.679.532 I slot print_timing: id 1 | task 2829054 | n_gen = 735, tg = 48.51 t/s, tg_3s = 54.36 t/s
llama-server | 11363.10.726.813 I slot print_timing: id 1 | task 2829054 | n_gen = 863, tg = 47.42 t/s, tg_3s = 42.00 t/s
llama-server | 11363.13.753.051 I slot print_timing: id 1 | task 2829054 | n_gen = 987, tg = 46.50 t/s, tg_3s = 40.97 t/s
llama-server | 11363.16.799.448 I slot print_timing: id 1 | task 2829054 | n_gen = 1090, tg = 44.90 t/s, tg_3s = 33.81 t/s
llama-server | 11363.19.842.016 I slot print_timing: id 1 | task 2829054 | n_gen = 1239, tg = 45.36 t/s, tg_3s = 48.97 t/s
llama-server | 11363.22.896.408 I slot print_timing: id 1 | task 2829054 | n_gen = 1349, tg = 44.42 t/s, tg_3s = 36.01 t/s
llama-server | 11363.25.943.878 I slot print_timing: id 1 | task 2829054 | n_gen = 1492, tg = 44.65 t/s, tg_3s = 46.92 t/s
llama-server | 11363.29.007.779 I slot print_timing: id 1 | task 2829054 | n_gen = 1632, tg = 44.73 t/s, tg_3s = 45.69 t/s
llama-server | 11363.32.058.199 I slot print_timing: id 1 | task 2829054 | n_gen = 1782, tg = 45.08 t/s, tg_3s = 49.17 t/s
llama-server | 11363.35.060.642 I slot print_timing: id 1 | task 2829054 | n_gen = 1944, tg = 45.70 t/s, tg_3s = 53.96 t/s
llama-server | 11363.38.063.679 I slot print_timing: id 1 | task 2829054 | n_gen = 2106, tg = 46.25 t/s, tg_3s = 53.95 t/s
llama-server | 11363.41.124.100 I slot print_timing: id 1 | task 2829054 | n_gen = 2256, tg = 46.42 t/s, tg_3s = 49.01 t/s
llama-server | 11363.44.128.984 I slot print_timing: id 1 | task 2829054 | n_gen = 2392, tg = 46.35 t/s, tg_3s = 45.26 t/s
llama-server | 11363.47.194.739 I slot print_timing: id 1 | task 2829054 | n_gen = 2528, tg = 46.24 t/s, tg_3s = 44.36 t/s
llama-server | 11363.50.196.333 I slot print_timing: id 1 | task 2829054 | n_gen = 2641, tg = 45.79 t/s, tg_3s = 37.65 t/s
llama-server | 11363.53.261.515 I slot print_timing: id 1 | task 2829054 | n_gen = 2777, tg = 45.72 t/s, tg_3s = 44.37 t/s
llama-server | 11363.56.276.453 I slot print_timing: id 1 | task 2829054 | n_gen = 2902, tg = 45.52 t/s, tg_3s = 41.46 t/s
llama-server | 11363.59.346.571 I slot print_timing: id 1 | task 2829054 | n_gen = 3033, tg = 45.39 t/s, tg_3s = 42.67 t/s
llama-server | 11364.02.359.354 I slot print_timing: id 1 | task 2829054 | n_gen = 3138, tg = 44.94 t/s, tg_3s = 34.85 t/s
llama-server | 11364.05.430.725 I slot print_timing: id 1 | task 2829054 | n_gen = 3252, tg = 44.61 t/s, tg_3s = 37.12 t/s
llama-server | 11364.08.454.136 I slot print_timing: id 1 | task 2829054 | n_gen = 3385, tg = 44.58 t/s, tg_3s = 43.99 t/s
llama-server | 11364.11.463.518 I slot print_timing: id 1 | task 2829054 | n_gen = 3551, tg = 44.98 t/s, tg_3s = 55.16 t/s
llama-server | 11364.14.504.658 I slot print_timing: id 1 | task 2829054 | n_gen = 3760, tg = 45.87 t/s, tg_3s = 68.72 t/s
llama-server | 11364.17.533.053 I slot print_timing: id 1 | task 2829054 | n_gen = 3890, tg = 45.76 t/s, tg_3s = 42.93 t/s
llama-server | 11364.20.559.060 I slot print_timing: id 1 | task 2829054 | n_gen = 4051, tg = 46.02 t/s, tg_3s = 53.21 t/s
llama-server | 11364.23.609.336 I slot print_timing: id 1 | task 2829054 | n_gen = 4284, tg = 47.03 t/s, tg_3s = 76.39 t/s
llama-server | 11364.23.919.387 I slot print_timing: id 1 | task 2829054 | prompt eval time = 5487.41 ms / 5444 tokens ( 1.01 ms per token, 992.09 tokens per second)
llama-server | 11364.23.919.390 I slot print_timing: id 1 | task 2829054 | eval time = 91371.80 ms / 4305 tokens ( 21.23 ms per token, 47.10 tokens per second)
llama-server | 11364.23.919.391 I slot print_timing: id 1 | task 2829054 | total time = 96859.21 ms / 9749 tokens
llama-server | 11364.23.919.391 I slot print_timing: id 1 | task 2829054 | graphs reused = 2740152
llama-server | 11364.23.919.395 I slot print_timing: id 1 | task 2829054 | draft acceptance = 0.52215 ( 3112 accepted / 5960 generated), mean len = 3.61
llama-server | 11364.23.919.590 I slot release: id 1 | task 2829054 | stop processing: n_tokens = 9748, truncated = 0
llama-server | 11364.24.089.586 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.839 (> 0.100 thold), f_keep = 0.189
llama-server | 11364.24.530.991 I slot launch_slot_: id 0 | task 2830253 | processing task, is_child = 0
llama-server | 11364.24.531.693 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2182.656 MiB)
llama-server | 11364.28.863.192 I slot print_timing: id 0 | task 2830253 | n_gen = 183, tg = 60.06 t/s, tg_3s = 60.39 t/s
llama-server | 11364.31.876.396 I slot print_timing: id 0 | task 2830253 | n_gen = 393, tg = 64.86 t/s, tg_3s = 69.69 t/s
llama-server | 11364.34.751.693 I slot print_timing: id 0 | task 2830253 | prompt eval time = 543.68 ms / 254 tokens ( 2.14 ms per token, 467.19 tokens per second)
llama-server | 11364.34.751.697 I slot print_timing: id 0 | task 2830253 | eval time = 8918.71 ms / 623 tokens ( 14.34 ms per token, 69.74 tokens per second)
llama-server | 11364.34.751.697 I slot print_timing: id 0 | task 2830253 | total time = 9462.39 ms / 877 tokens
llama-server | 11364.34.751.698 I slot print_timing: id 0 | task 2830253 | graphs reused = 2740272
llama-server | 11364.34.751.710 I slot print_timing: id 0 | task 2830253 | draft acceptance = 0.82810 ( 501 accepted / 605 generated), mean len = 5.14
llama-server | 11364.34.751.789 I slot release: id 0 | task 2830253 | stop processing: n_tokens = 2168, truncated = 0
llama-server | 11364.42.074.451 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.240 (> 0.100 thold), f_keep = 0.598
llama-server | 11364.42.075.163 I slot launch_slot_: id 0 | task 2830377 | processing task, is_child = 0
llama-server | 11364.45.477.697 I slot print_timing: id 0 | task 2830377 | prompt processing, n_tokens = 3600, progress = 0.90, t = 3.25 s / 1106.20 tokens per second
llama-server | 11364.46.024.965 I slot print_timing: id 0 | task 2830377 | prompt processing, n_tokens = 4112, progress = 1.00, t = 3.50 s / 1175.30 tokens per second
llama-server | 11364.49.236.899 I slot print_timing: id 0 | task 2830377 | n_gen = 164, tg = 53.08 t/s, tg_3s = 53.40 t/s
llama-server | 11364.52.294.162 I slot print_timing: id 0 | task 2830377 | n_gen = 313, tg = 50.91 t/s, tg_3s = 48.74 t/s
llama-server | 11364.55.355.403 I slot print_timing: id 0 | task 2830377 | n_gen = 460, tg = 49.95 t/s, tg_3s = 48.02 t/s
llama-server | 11364.58.355.671 I slot print_timing: id 0 | task 2830377 | n_gen = 602, tg = 49.30 t/s, tg_3s = 47.33 t/s
llama-server | 11365.01.358.067 I slot print_timing: id 0 | task 2830377 | n_gen = 764, tg = 50.22 t/s, tg_3s = 53.96 t/s
llama-server | 11365.04.429.441 I slot print_timing: id 0 | task 2830377 | n_gen = 926, tg = 50.65 t/s, tg_3s = 52.75 t/s
llama-server | 11365.07.439.293 I slot print_timing: id 0 | task 2830377 | n_gen = 1132, tg = 53.17 t/s, tg_3s = 68.44 t/s
llama-server | 11365.10.453.600 I slot print_timing: id 0 | task 2830377 | n_gen = 1303, tg = 53.61 t/s, tg_3s = 56.73 t/s
llama-server | 11365.12.072.545 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 681879759643
llama-server | 11365.12.073.011 I slot launch_slot_: id 1 | task 2830736 | processing task, is_child = 0
llama-server | 11365.12.076.970 W srv stop: cancel task, id_task = 2830377
llama-server | 11365.13.368.138 I slot release: id 0 | task 2830377 | stop processing: n_tokens = 6845, truncated = 0
llama-server | 11365.16.840.530 I slot print_timing: id 1 | task 2830736 | prompt processing, n_tokens = 4892, progress = 0.90, t = 4.61 s / 1061.39 tokens per second
llama-server | 11365.17.417.483 I slot print_timing: id 1 | task 2830736 | prompt processing, n_tokens = 5404, progress = 1.00, t = 4.86 s / 1112.72 tokens per second
llama-server | 11365.20.610.381 I slot print_timing: id 1 | task 2830736 | n_gen = 156, tg = 50.81 t/s, tg_3s = 51.13 t/s
llama-server | 11365.23.649.614 I slot print_timing: id 1 | task 2830736 | n_gen = 320, tg = 52.38 t/s, tg_3s = 53.96 t/s
llama-server | 11365.26.677.689 I slot print_timing: id 1 | task 2830736 | n_gen = 488, tg = 53.41 t/s, tg_3s = 55.48 t/s
llama-server | 11365.29.717.856 I slot print_timing: id 1 | task 2830736 | n_gen = 622, tg = 51.08 t/s, tg_3s = 44.08 t/s
llama-server | 11365.32.747.350 I slot print_timing: id 1 | task 2830736 | n_gen = 759, tg = 49.91 t/s, tg_3s = 45.22 t/s
llama-server | 11365.35.803.292 I slot print_timing: id 1 | task 2830736 | n_gen = 933, tg = 51.09 t/s, tg_3s = 56.94 t/s
llama-server | 11365.38.862.653 I slot print_timing: id 1 | task 2830736 | n_gen = 1093, tg = 51.26 t/s, tg_3s = 52.30 t/s
llama-server | 11365.41.910.533 I slot print_timing: id 1 | task 2830736 | n_gen = 1237, tg = 50.76 t/s, tg_3s = 47.25 t/s
llama-server | 11365.44.982.848 I slot print_timing: id 1 | task 2830736 | n_gen = 1443, tg = 52.58 t/s, tg_3s = 67.05 t/s
llama-server | 11365.47.984.747 I slot print_timing: id 1 | task 2830736 | n_gen = 1675, tg = 55.02 t/s, tg_3s = 77.28 t/s
llama-server | 11365.48.596.382 I slot print_timing: id 1 | task 2830736 | prompt eval time = 5477.94 ms / 5408 tokens ( 1.01 ms per token, 987.23 tokens per second)
llama-server | 11365.48.596.385 I slot print_timing: id 1 | task 2830736 | eval time = 31036.79 ms / 1719 tokens ( 18.07 ms per token, 55.35 tokens per second)
llama-server | 11365.48.596.386 I slot print_timing: id 1 | task 2830736 | total time = 36514.73 ms / 7127 tokens
llama-server | 11365.48.596.386 I slot print_timing: id 1 | task 2830736 | graphs reused = 2741030
llama-server | 11365.48.596.390 I slot print_timing: id 1 | task 2830736 | draft acceptance = 0.64423 ( 1311 accepted / 2035 generated), mean len = 4.22
llama-server | 11365.48.596.566 I slot release: id 1 | task 2830736 | stop processing: n_tokens = 7126, truncated = 0
llama-server | 11365.48.742.526 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.828 (> 0.100 thold), f_keep = 0.189
llama-server | 11365.49.290.419 I slot launch_slot_: id 0 | task 2831150 | processing task, is_child = 0
llama-server | 11365.53.805.546 I slot print_timing: id 0 | task 2831150 | n_gen = 183, tg = 60.23 t/s, tg_3s = 60.56 t/s
llama-server | 11365.56.819.826 I slot print_timing: id 0 | task 2831150 | n_gen = 382, tg = 63.12 t/s, tg_3s = 66.02 t/s
llama-server | 11365.59.833.732 I slot print_timing: id 0 | task 2831150 | n_gen = 615, tg = 67.85 t/s, tg_3s = 77.31 t/s
llama-server | 11366.01.082.868 I slot print_timing: id 0 | task 2831150 | prompt eval time = 914.21 ms / 274 tokens ( 3.34 ms per token, 299.71 tokens per second)
llama-server | 11366.01.082.871 I slot print_timing: id 0 | task 2831150 | eval time = 10299.01 ms / 715 tokens ( 14.42 ms per token, 69.33 tokens per second)
llama-server | 11366.01.082.872 I slot print_timing: id 0 | task 2831150 | total time = 11213.22 ms / 989 tokens
llama-server | 11366.01.082.872 I slot print_timing: id 0 | task 2831150 | graphs reused = 2741169
llama-server | 11366.01.082.875 I slot print_timing: id 0 | task 2831150 | draft acceptance = 0.82000 ( 574 accepted / 700 generated), mean len = 5.10
llama-server | 11366.01.082.966 I slot release: id 0 | task 2831150 | stop processing: n_tokens = 2280, truncated = 0
llama-server | 11366.07.231.141 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.569
llama-server | 11366.07.231.931 I slot launch_slot_: id 0 | task 2831293 | processing task, is_child = 0
llama-server | 11366.11.178.119 I slot print_timing: id 0 | task 2831293 | prompt processing, n_tokens = 4063, progress = 0.91, t = 3.33 s / 1221.12 tokens per second
llama-server | 11366.11.729.945 I slot print_timing: id 0 | task 2831293 | prompt processing, n_tokens = 4575, progress = 1.00, t = 4.04 s / 1131.60 tokens per second
llama-server | 11366.14.871.296 I slot print_timing: id 0 | task 2831293 | n_gen = 171, tg = 56.47 t/s, tg_3s = 56.80 t/s
llama-server | 11366.17.934.014 I slot print_timing: id 0 | task 2831293 | n_gen = 320, tg = 52.53 t/s, tg_3s = 48.65 t/s
llama-server | 11366.21.001.467 I slot print_timing: id 0 | task 2831293 | n_gen = 469, tg = 51.20 t/s, tg_3s = 48.57 t/s
llama-server | 11366.24.014.374 I slot print_timing: id 0 | task 2831293 | n_gen = 648, tg = 53.24 t/s, tg_3s = 59.41 t/s
llama-server | 11366.27.018.619 I slot print_timing: id 0 | task 2831293 | n_gen = 845, tg = 55.68 t/s, tg_3s = 65.57 t/s
llama-server | 11366.29.884.143 I slot print_timing: id 0 | task 2831293 | prompt eval time = 4628.36 ms / 4579 tokens ( 1.01 ms per token, 989.33 tokens per second)
llama-server | 11366.29.884.147 I slot print_timing: id 0 | task 2831293 | eval time = 18023.07 ms / 1067 tokens ( 16.91 ms per token, 59.15 tokens per second)
llama-server | 11366.29.884.147 I slot print_timing: id 0 | task 2831293 | total time = 22651.43 ms / 5646 tokens
llama-server | 11366.29.884.148 I slot print_timing: id 0 | task 2831293 | graphs reused = 2741420
llama-server | 11366.29.884.152 I slot print_timing: id 0 | task 2831293 | draft acceptance = 0.66667 ( 820 accepted / 1230 generated), mean len = 4.33
llama-server | 11366.29.884.354 I slot release: id 0 | task 2831293 | stop processing: n_tokens = 6937, truncated = 0
llama-server | 11366.30.003.597 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.831 (> 0.100 thold), f_keep = 0.187
llama-server | 11366.30.004.470 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 2214.342 MiB)
llama-server | 11366.30.808.885 I slot launch_slot_: id 0 | task 2831544 | processing task, is_child = 0
llama-server | 11366.34.420.262 I slot print_timing: id 0 | task 2831544 | n_gen = 217, tg = 71.41 t/s, tg_3s = 71.74 t/s
llama-server | 11366.37.427.229 I slot print_timing: id 0 | task 2831544 | n_gen = 399, tg = 65.99 t/s, tg_3s = 60.53 t/s
llama-server | 11366.40.436.224 I slot print_timing: id 0 | task 2831544 | n_gen = 578, tg = 63.82 t/s, tg_3s = 59.49 t/s
llama-server | 11366.43.449.995 I slot print_timing: id 0 | task 2831544 | n_gen = 764, tg = 63.30 t/s, tg_3s = 61.72 t/s
llama-server | 11366.46.465.141 I slot print_timing: id 0 | task 2831544 | n_gen = 946, tg = 62.71 t/s, tg_3s = 60.36 t/s
llama-server | 11366.49.480.150 I slot print_timing: id 0 | task 2831544 | n_gen = 1143, tg = 63.15 t/s, tg_3s = 65.34 t/s
llama-server | 11366.52.487.748 I slot print_timing: id 0 | task 2831544 | n_gen = 1288, tg = 61.02 t/s, tg_3s = 48.21 t/s
llama-server | 11366.55.513.314 I slot print_timing: id 0 | task 2831544 | n_gen = 1518, tg = 62.90 t/s, tg_3s = 76.02 t/s
llama-server | 11366.56.474.826 I slot print_timing: id 0 | task 2831544 | prompt eval time = 585.95 ms / 269 tokens ( 2.18 ms per token, 459.08 tokens per second)
llama-server | 11366.56.474.829 I slot print_timing: id 0 | task 2831544 | eval time = 25079.21 ms / 1594 tokens ( 15.74 ms per token, 63.52 tokens per second)
llama-server | 11366.56.474.830 I slot print_timing: id 0 | task 2831544 | total time = 25665.16 ms / 1863 tokens
llama-server | 11366.56.474.831 I slot print_timing: id 0 | task 2831544 | graphs reused = 2741760
llama-server | 11366.56.474.833 I slot print_timing: id 0 | task 2831544 | draft acceptance = 0.73431 ( 1252 accepted / 1705 generated), mean len = 4.67
llama-server | 11366.56.474.919 I slot release: id 0 | task 2831544 | stop processing: n_tokens = 3154, truncated = 0
llama-server | 11367.02.483.253 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.221 (> 0.100 thold), f_keep = 0.411
llama-server | 11367.02.933.057 I slot launch_slot_: id 0 | task 2831888 | processing task, is_child = 0
llama-server | 11367.06.899.398 I slot print_timing: id 0 | task 2831888 | prompt processing, n_tokens = 4063, progress = 0.91, t = 3.35 s / 1213.88 tokens per second
llama-server | 11367.07.507.115 I slot print_timing: id 0 | task 2831888 | prompt processing, n_tokens = 4575, progress = 1.00, t = 4.10 s / 1115.50 tokens per second
llama-server | 11367.10.656.068 I slot print_timing: id 0 | task 2831888 | n_gen = 166, tg = 54.94 t/s, tg_3s = 55.27 t/s
llama-server | 11367.13.721.430 I slot print_timing: id 0 | task 2831888 | n_gen = 340, tg = 55.86 t/s, tg_3s = 56.76 t/s
llama-server | 11367.16.725.035 I slot print_timing: id 0 | task 2831888 | n_gen = 555, tg = 61.07 t/s, tg_3s = 71.58 t/s
llama-server | 11367.18.999.464 I slot print_timing: id 0 | task 2831888 | prompt eval time = 4719.04 ms / 4579 tokens ( 1.03 ms per token, 970.33 tokens per second)
llama-server | 11367.18.999.468 I slot print_timing: id 0 | task 2831888 | eval time = 11346.57 ms / 730 tokens ( 15.56 ms per token, 64.25 tokens per second)
llama-server | 11367.18.999.468 I slot print_timing: id 0 | task 2831888 | total time = 16065.60 ms / 5309 tokens
llama-server | 11367.18.999.469 I slot print_timing: id 0 | task 2831888 | graphs reused = 2741920
llama-server | 11367.18.999.472 I slot print_timing: id 0 | task 2831888 | draft acceptance = 0.74065 ( 574 accepted / 775 generated), mean len = 4.70
llama-server | 11367.18.999.673 I slot release: id 0 | task 2831888 | stop processing: n_tokens = 6600, truncated = 0
llama-server | 11367.19.126.208 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.197
llama-server | 11367.19.127.079 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 977.783 MiB)
llama-server | 11367.19.818.788 I slot launch_slot_: id 0 | task 2832048 | processing task, is_child = 0
llama-server | 11367.23.484.616 I slot print_timing: id 0 | task 2832048 | n_gen = 181, tg = 59.69 t/s, tg_3s = 60.02 t/s
llama-server | 11367.26.501.763 I slot print_timing: id 0 | task 2832048 | n_gen = 410, tg = 67.80 t/s, tg_3s = 75.90 t/s
llama-server | 11367.28.371.254 I slot print_timing: id 0 | task 2832048 | prompt eval time = 649.95 ms / 263 tokens ( 2.47 ms per token, 404.65 tokens per second)
llama-server | 11367.28.371.258 I slot print_timing: id 0 | task 2832048 | eval time = 7902.02 ms / 561 tokens ( 14.11 ms per token, 70.87 tokens per second)
llama-server | 11367.28.371.258 I slot print_timing: id 0 | task 2832048 | total time = 8551.96 ms / 824 tokens
llama-server | 11367.28.371.259 I slot print_timing: id 0 | task 2832048 | graphs reused = 2742029
llama-server | 11367.28.371.262 I slot print_timing: id 0 | task 2832048 | draft acceptance = 0.81818 ( 450 accepted / 550 generated), mean len = 5.09
llama-server | 11367.28.371.347 I slot release: id 0 | task 2832048 | stop processing: n_tokens = 2115, truncated = 0
llama-server | 11367.37.761.209 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.613
llama-server | 11367.37.762.316 I slot launch_slot_: id 0 | task 2832161 | processing task, is_child = 0
llama-server | 11367.41.575.280 I slot print_timing: id 0 | task 2832161 | prompt processing, n_tokens = 4017, progress = 0.91, t = 3.24 s / 1238.66 tokens per second
llama-server | 11367.42.136.182 I slot print_timing: id 0 | task 2832161 | prompt processing, n_tokens = 4529, progress = 1.00, t = 3.93 s / 1153.80 tokens per second
llama-server | 11367.45.363.218 I slot print_timing: id 0 | task 2832161 | n_gen = 154, tg = 49.99 t/s, tg_3s = 50.31 t/s
llama-server | 11367.48.418.162 I slot print_timing: id 0 | task 2832161 | n_gen = 328, tg = 53.47 t/s, tg_3s = 56.96 t/s
llama-server | 11367.51.460.442 I slot print_timing: id 0 | task 2832161 | n_gen = 476, tg = 51.87 t/s, tg_3s = 48.65 t/s
llama-server | 11367.54.530.309 I slot print_timing: id 0 | task 2832161 | n_gen = 613, tg = 50.05 t/s, tg_3s = 44.63 t/s
llama-server | 11367.57.587.417 I slot print_timing: id 0 | task 2832161 | n_gen = 759, tg = 49.59 t/s, tg_3s = 47.76 t/s
llama-server | 11368.00.596.071 I slot print_timing: id 0 | task 2832161 | n_gen = 928, tg = 50.67 t/s, tg_3s = 56.17 t/s
llama-server | 11368.03.617.131 I slot print_timing: id 0 | task 2832161 | n_gen = 1122, tg = 52.59 t/s, tg_3s = 64.22 t/s
llama-server | 11368.06.642.966 I slot print_timing: id 0 | task 2832161 | n_gen = 1353, tg = 55.55 t/s, tg_3s = 76.34 t/s
llama-server | 11368.07.764.281 W srv stop: cancel task, id_task = 2832161
llama-server | 11368.07.823.774 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 681964436618
llama-server | 11368.07.824.233 I slot launch_slot_: id 1 | task 2832515 | processing task, is_child = 0
llama-server | 11368.07.824.236 I slot release: id 0 | task 2832161 | stop processing: n_tokens = 7267, truncated = 0
llama-server | 11368.13.139.036 I slot print_timing: id 1 | task 2832515 | prompt processing, n_tokens = 5309, progress = 0.91, t = 4.69 s / 1130.88 tokens per second
llama-server | 11368.13.812.518 I slot print_timing: id 1 | task 2832515 | prompt processing, n_tokens = 5821, progress = 1.00, t = 5.51 s / 1057.40 tokens per second
llama-server | 11368.17.044.909 I slot print_timing: id 1 | task 2832515 | n_gen = 156, tg = 50.94 t/s, tg_3s = 51.27 t/s
llama-server | 11368.20.104.289 I slot print_timing: id 1 | task 2832515 | n_gen = 319, tg = 52.11 t/s, tg_3s = 53.28 t/s
llama-server | 11368.23.180.134 I slot print_timing: id 1 | task 2832515 | n_gen = 484, tg = 52.63 t/s, tg_3s = 53.64 t/s
llama-server | 11368.26.236.676 I slot print_timing: id 1 | task 2832515 | n_gen = 616, tg = 50.27 t/s, tg_3s = 43.19 t/s
llama-server | 11368.29.243.427 I slot print_timing: id 1 | task 2832515 | n_gen = 765, tg = 50.13 t/s, tg_3s = 49.56 t/s
llama-server | 11368.32.243.779 I slot print_timing: id 1 | task 2832515 | n_gen = 956, tg = 52.35 t/s, tg_3s = 63.66 t/s
llama-server | 11368.35.266.772 I slot print_timing: id 1 | task 2832515 | n_gen = 1184, tg = 55.63 t/s, tg_3s = 75.42 t/s
llama-server | 11368.36.286.283 I slot print_timing: id 1 | task 2832515 | prompt eval time = 6177.76 ms / 5825 tokens ( 1.06 ms per token, 942.90 tokens per second)
llama-server | 11368.36.286.287 I slot print_timing: id 1 | task 2832515 | eval time = 22284.01 ms / 1254 tokens ( 17.78 ms per token, 56.23 tokens per second)
llama-server | 11368.36.286.288 I slot print_timing: id 1 | task 2832515 | total time = 28461.77 ms / 7079 tokens
llama-server | 11368.36.286.288 I slot print_timing: id 1 | task 2832515 | graphs reused = 2742657
llama-server | 11368.36.286.291 I slot print_timing: id 1 | task 2832515 | draft acceptance = 0.66414 ( 963 accepted / 1450 generated), mean len = 4.32
llama-server | 11368.36.286.497 I slot release: id 1 | task 2832515 | stop processing: n_tokens = 7078, truncated = 0
llama-server | 11368.36.436.472 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.178
llama-server | 11368.37.033.394 I slot launch_slot_: id 0 | task 2832812 | processing task, is_child = 0
llama-server | 11368.37.034.638 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 947.008 MiB)
llama-server | 11368.41.347.115 I slot print_timing: id 0 | task 2832812 | n_gen = 195, tg = 63.91 t/s, tg_3s = 64.24 t/s
llama-server | 11368.44.368.254 I slot print_timing: id 0 | task 2832812 | n_gen = 430, tg = 70.83 t/s, tg_3s = 77.79 t/s
llama-server | 11368.45.808.232 I slot print_timing: id 0 | task 2832812 | prompt eval time = 582.43 ms / 266 tokens ( 2.19 ms per token, 456.71 tokens per second)
llama-server | 11368.45.808.236 I slot print_timing: id 0 | task 2832812 | eval time = 7496.44 ms / 547 tokens ( 13.73 ms per token, 72.83 tokens per second)
llama-server | 11368.45.808.236 I slot print_timing: id 0 | task 2832812 | total time = 8078.87 ms / 813 tokens
llama-server | 11368.45.808.237 I slot print_timing: id 0 | task 2832812 | graphs reused = 2742760
llama-server | 11368.45.808.240 I slot print_timing: id 0 | task 2832812 | draft acceptance = 0.85000 ( 442 accepted / 520 generated), mean len = 5.25
llama-server | 11368.45.808.324 I slot release: id 0 | task 2832812 | stop processing: n_tokens = 2104, truncated = 0
llama-server | 11368.52.591.803 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.223 (> 0.100 thold), f_keep = 0.616
llama-server | 11368.52.592.403 I slot launch_slot_: id 0 | task 2832919 | processing task, is_child = 0
llama-server | 11368.56.422.552 I slot print_timing: id 0 | task 2832919 | prompt processing, n_tokens = 4017, progress = 0.91, t = 3.25 s / 1234.88 tokens per second
llama-server | 11368.56.996.964 I slot print_timing: id 0 | task 2832919 | prompt processing, n_tokens = 4529, progress = 1.00, t = 3.94 s / 1149.80 tokens per second
llama-server | 11369.00.236.897 I slot print_timing: id 0 | task 2832919 | n_gen = 143, tg = 46.25 t/s, tg_3s = 46.57 t/s
llama-server | 11369.03.295.471 I slot print_timing: id 0 | task 2832919 | n_gen = 327, tg = 53.19 t/s, tg_3s = 60.16 t/s
llama-server | 11369.06.343.502 I slot print_timing: id 0 | task 2832919 | n_gen = 469, tg = 51.00 t/s, tg_3s = 46.59 t/s
llama-server | 11369.09.415.855 I slot print_timing: id 0 | task 2832919 | n_gen = 592, tg = 48.25 t/s, tg_3s = 40.03 t/s
llama-server | 11369.12.473.105 I slot print_timing: id 0 | task 2832919 | n_gen = 744, tg = 48.54 t/s, tg_3s = 49.72 t/s
llama-server | 11369.15.479.957 I slot print_timing: id 0 | task 2832919 | n_gen = 877, tg = 47.83 t/s, tg_3s = 44.23 t/s
llama-server | 11369.18.551.968 I slot print_timing: id 0 | task 2832919 | n_gen = 1039, tg = 48.54 t/s, tg_3s = 52.73 t/s
llama-server | 11369.21.580.054 I slot print_timing: id 0 | task 2832919 | n_gen = 1215, tg = 49.73 t/s, tg_3s = 58.12 t/s
llama-server | 11369.22.594.764 W srv stop: cancel task, id_task = 2832919
llama-server | 11369.22.607.065 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 682132126549
llama-server | 11369.22.607.447 I slot launch_slot_: id 1 | task 2833272 | processing task, is_child = 0
llama-server | 11369.22.607.450 I slot release: id 0 | task 2832919 | stop processing: n_tokens = 7105, truncated = 0
llama-server | 11369.27.943.940 I slot print_timing: id 1 | task 2833272 | prompt processing, n_tokens = 5309, progress = 0.91, t = 4.73 s / 1121.26 tokens per second
llama-server | 11369.28.614.532 I slot print_timing: id 1 | task 2833272 | prompt processing, n_tokens = 5821, progress = 1.00, t = 5.51 s / 1056.85 tokens per second
llama-server | 11369.31.840.947 I slot print_timing: id 1 | task 2833272 | n_gen = 149, tg = 48.28 t/s, tg_3s = 48.61 t/s
llama-server | 11369.34.876.968 I slot print_timing: id 1 | task 2833272 | n_gen = 310, tg = 50.65 t/s, tg_3s = 53.03 t/s
llama-server | 11369.37.937.051 I slot print_timing: id 1 | task 2833272 | n_gen = 461, tg = 50.21 t/s, tg_3s = 49.35 t/s
llama-server | 11369.40.976.967 I slot print_timing: id 1 | task 2833272 | n_gen = 589, tg = 48.19 t/s, tg_3s = 42.11 t/s
llama-server | 11369.44.036.517 I slot print_timing: id 1 | task 2833272 | n_gen = 726, tg = 47.51 t/s, tg_3s = 44.78 t/s
llama-server | 11369.47.086.418 I slot print_timing: id 1 | task 2833272 | n_gen = 893, tg = 48.71 t/s, tg_3s = 54.76 t/s
llama-server | 11369.50.150.529 I slot print_timing: id 1 | task 2833272 | n_gen = 1009, tg = 47.16 t/s, tg_3s = 37.86 t/s
llama-server | 11369.53.156.518 I slot print_timing: id 1 | task 2833272 | n_gen = 1194, tg = 48.93 t/s, tg_3s = 61.54 t/s
llama-server | 11369.56.227.356 I slot print_timing: id 1 | task 2833272 | n_gen = 1405, tg = 51.14 t/s, tg_3s = 68.71 t/s
llama-server | 11369.59.233.862 I slot print_timing: id 1 | task 2833272 | n_gen = 1537, tg = 50.43 t/s, tg_3s = 43.90 t/s
llama-server | 11370.02.255.649 I slot print_timing: id 1 | task 2833272 | n_gen = 1744, tg = 52.06 t/s, tg_3s = 68.50 t/s
llama-server | 11370.03.873.869 I slot print_timing: id 1 | task 2833272 | prompt eval time = 6168.00 ms / 5825 tokens ( 1.06 ms per token, 944.39 tokens per second)
llama-server | 11370.03.873.873 I slot print_timing: id 1 | task 2833272 | eval time = 35098.16 ms / 1868 tokens ( 18.80 ms per token, 53.19 tokens per second)
llama-server | 11370.03.873.873 I slot print_timing: id 1 | task 2833272 | total time = 41266.16 ms / 7693 tokens
llama-server | 11370.03.873.874 I slot print_timing: id 1 | task 2833272 | graphs reused = 2743554
llama-server | 11370.03.873.877 I slot print_timing: id 1 | task 2833272 | draft acceptance = 0.61528 ( 1409 accepted / 2290 generated), mean len = 4.08
llama-server | 11370.03.874.096 I slot release: id 1 | task 2833272 | stop processing: n_tokens = 7692, truncated = 0
llama-server | 11370.03.991.111 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.837 (> 0.100 thold), f_keep = 0.183
llama-server | 11370.03.991.884 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 971.645 MiB)
llama-server | 11370.04.559.401 I slot launch_slot_: id 0 | task 2833737 | processing task, is_child = 0
llama-server | 11370.04.560.195 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1068.020 MiB)
llama-server | 11370.08.757.124 I slot print_timing: id 0 | task 2833737 | n_gen = 181, tg = 59.31 t/s, tg_3s = 59.64 t/s
llama-server | 11370.11.776.656 I slot print_timing: id 0 | task 2833737 | n_gen = 346, tg = 56.98 t/s, tg_3s = 54.64 t/s
llama-server | 11370.14.807.603 I slot print_timing: id 0 | task 2833737 | n_gen = 548, tg = 60.21 t/s, tg_3s = 66.65 t/s
llama-server | 11370.17.835.623 I slot print_timing: id 0 | task 2833737 | n_gen = 792, tg = 65.30 t/s, tg_3s = 80.58 t/s
llama-server | 11370.18.700.040 I slot print_timing: id 0 | task 2833737 | prompt eval time = 534.72 ms / 258 tokens ( 2.07 ms per token, 482.49 tokens per second)
llama-server | 11370.18.700.044 I slot print_timing: id 0 | task 2833737 | eval time = 12977.71 ms / 864 tokens ( 15.04 ms per token, 66.50 tokens per second)
llama-server | 11370.18.700.045 I slot print_timing: id 0 | task 2833737 | total time = 13512.43 ms / 1122 tokens
llama-server | 11370.18.700.045 I slot print_timing: id 0 | task 2833737 | graphs reused = 2743733
llama-server | 11370.18.700.048 I slot print_timing: id 0 | task 2833737 | draft acceptance = 0.75889 ( 683 accepted / 900 generated), mean len = 4.79
llama-server | 11370.18.700.138 I slot release: id 0 | task 2833737 | stop processing: n_tokens = 2413, truncated = 0
llama-server | 11370.27.634.804 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.313 (> 0.100 thold), f_keep = 0.538
llama-server | 11370.27.635.470 I slot launch_slot_: id 0 | task 2833920 | processing task, is_child = 0
llama-server | 11370.33.732.924 I slot print_timing: id 0 | task 2833920 | n_gen = 173, tg = 56.80 t/s, tg_3s = 57.13 t/s
llama-server | 11370.36.758.122 I slot print_timing: id 0 | task 2833920 | n_gen = 358, tg = 58.98 t/s, tg_3s = 61.15 t/s
llama-server | 11370.39.780.210 I slot print_timing: id 0 | task 2833920 | n_gen = 521, tg = 57.30 t/s, tg_3s = 53.94 t/s
llama-server | 11370.42.803.238 I slot print_timing: id 0 | task 2833920 | n_gen = 673, tg = 55.54 t/s, tg_3s = 50.28 t/s
llama-server | 11370.45.852.140 I slot print_timing: id 0 | task 2833920 | n_gen = 806, tg = 53.14 t/s, tg_3s = 43.62 t/s
llama-server | 11370.48.881.469 I slot print_timing: id 0 | task 2833920 | n_gen = 954, tg = 52.43 t/s, tg_3s = 48.86 t/s
llama-server | 11370.51.943.743 I slot print_timing: id 0 | task 2833920 | n_gen = 1107, tg = 52.07 t/s, tg_3s = 49.96 t/s
llama-server | 11370.54.945.441 I slot print_timing: id 0 | task 2833920 | n_gen = 1282, tg = 52.85 t/s, tg_3s = 58.30 t/s
llama-server | 11370.57.638.326 W srv stop: cancel task, id_task = 2833920
llama-server | 11370.57.640.634 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 682219714148
llama-server | 11370.57.641.032 I slot launch_slot_: id 1 | task 2834297 | processing task, is_child = 0
llama-server | 11370.57.641.035 I slot release: id 0 | task 2833920 | stop processing: n_tokens = 5617, truncated = 0
llama-server | 11371.01.270.325 I slot print_timing: id 1 | task 2834297 | prompt processing, n_tokens = 3625, progress = 0.88, t = 3.33 s / 1088.14 tokens per second
llama-server | 11371.01.935.802 I slot print_timing: id 1 | task 2834297 | prompt processing, n_tokens = 4137, progress = 1.00, t = 3.81 s / 1085.24 tokens per second
llama-server | 11371.05.094.609 I slot print_timing: id 1 | task 2834297 | n_gen = 194, tg = 64.22 t/s, tg_3s = 64.55 t/s
llama-server | 11371.08.169.113 I slot print_timing: id 1 | task 2834297 | n_gen = 360, tg = 59.05 t/s, tg_3s = 53.99 t/s
llama-server | 11371.11.177.271 I slot print_timing: id 1 | task 2834297 | n_gen = 532, tg = 58.43 t/s, tg_3s = 57.18 t/s
llama-server | 11371.14.243.703 I slot print_timing: id 1 | task 2834297 | n_gen = 682, tg = 56.03 t/s, tg_3s = 48.92 t/s
llama-server | 11371.17.256.936 I slot print_timing: id 1 | task 2834297 | n_gen = 844, tg = 55.58 t/s, tg_3s = 53.76 t/s
llama-server | 11371.20.323.366 I slot print_timing: id 1 | task 2834297 | n_gen = 985, tg = 53.96 t/s, tg_3s = 45.98 t/s
llama-server | 11371.23.341.636 I slot print_timing: id 1 | task 2834297 | n_gen = 1153, tg = 54.21 t/s, tg_3s = 55.66 t/s
llama-server | 11371.26.360.866 I slot print_timing: id 1 | task 2834297 | n_gen = 1275, tg = 52.49 t/s, tg_3s = 40.41 t/s
llama-server | 11371.29.362.507 I slot print_timing: id 1 | task 2834297 | n_gen = 1423, tg = 52.14 t/s, tg_3s = 49.31 t/s
llama-server | 11371.32.392.209 I slot print_timing: id 1 | task 2834297 | n_gen = 1579, tg = 52.07 t/s, tg_3s = 51.49 t/s
llama-server | 11371.35.406.072 I slot print_timing: id 1 | task 2834297 | n_gen = 1721, tg = 51.63 t/s, tg_3s = 47.12 t/s
llama-server | 11371.38.439.811 I slot print_timing: id 1 | task 2834297 | n_gen = 1876, tg = 51.58 t/s, tg_3s = 51.09 t/s
llama-server | 11371.41.453.338 I slot print_timing: id 1 | task 2834297 | n_gen = 2022, tg = 51.34 t/s, tg_3s = 48.45 t/s
llama-server | 11371.44.489.870 I slot print_timing: id 1 | task 2834297 | n_gen = 2154, tg = 50.78 t/s, tg_3s = 43.47 t/s
llama-server | 11371.47.527.848 I slot print_timing: id 1 | task 2834297 | n_gen = 2282, tg = 50.20 t/s, tg_3s = 42.13 t/s
llama-server | 11371.50.552.805 I slot print_timing: id 1 | task 2834297 | n_gen = 2443, tg = 50.39 t/s, tg_3s = 53.22 t/s
llama-server | 11371.53.604.596 I slot print_timing: id 1 | task 2834297 | n_gen = 2623, tg = 50.90 t/s, tg_3s = 58.98 t/s
llama-server | 11371.56.634.519 I slot print_timing: id 1 | task 2834297 | n_gen = 2741, tg = 50.23 t/s, tg_3s = 38.94 t/s
llama-server | 11371.59.686.944 I slot print_timing: id 1 | task 2834297 | n_gen = 2907, tg = 50.45 t/s, tg_3s = 54.38 t/s
llama-server | 11372.02.755.180 I slot print_timing: id 1 | task 2834297 | n_gen = 3102, tg = 51.12 t/s, tg_3s = 63.55 t/s
llama-server | 11372.05.808.083 I slot print_timing: id 1 | task 2834297 | n_gen = 3296, tg = 51.71 t/s, tg_3s = 63.55 t/s
llama-server | 11372.08.871.603 I slot print_timing: id 1 | task 2834297 | n_gen = 3457, tg = 51.75 t/s, tg_3s = 52.55 t/s
llama-server | 11372.11.877.115 I slot print_timing: id 1 | task 2834297 | n_gen = 3690, tg = 52.86 t/s, tg_3s = 77.52 t/s
llama-server | 11372.12.030.606 I slot print_timing: id 1 | task 2834297 | prompt eval time = 4447.93 ms / 4141 tokens ( 1.07 ms per token, 930.99 tokens per second)
llama-server | 11372.12.030.609 I slot print_timing: id 1 | task 2834297 | eval time = 69941.38 ms / 3701 tokens ( 18.90 ms per token, 52.90 tokens per second)
llama-server | 11372.12.030.609 I slot print_timing: id 1 | task 2834297 | total time = 74389.32 ms / 7842 tokens
llama-server | 11372.12.030.610 I slot print_timing: id 1 | task 2834297 | graphs reused = 2745010
llama-server | 11372.12.030.613 I slot print_timing: id 1 | task 2834297 | draft acceptance = 0.60108 ( 2777 accepted / 4620 generated), mean len = 4.01
llama-server | 11372.12.030.779 I slot release: id 1 | task 2834297 | stop processing: n_tokens = 7842, truncated = 0
llama-server | 11372.12.179.985 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.231
llama-server | 11372.12.180.702 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 971.479 MiB)
llama-server | 11372.12.771.640 I slot launch_slot_: id 0 | task 2835228 | processing task, is_child = 0
llama-server | 11372.12.772.983 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 980.842 MiB)
llama-server | 11372.16.987.453 I slot print_timing: id 0 | task 2835228 | n_gen = 202, tg = 66.19 t/s, tg_3s = 66.51 t/s
llama-server | 11372.20.006.514 I slot print_timing: id 0 | task 2835228 | n_gen = 386, tg = 63.58 t/s, tg_3s = 60.95 t/s
llama-server | 11372.22.171.226 I slot print_timing: id 0 | task 2835228 | prompt eval time = 537.25 ms / 260 tokens ( 2.07 ms per token, 483.95 tokens per second)
llama-server | 11372.22.171.229 I slot print_timing: id 0 | task 2835228 | eval time = 8220.45 ms / 564 tokens ( 14.60 ms per token, 68.49 tokens per second)
llama-server | 11372.22.171.230 I slot print_timing: id 0 | task 2835228 | total time = 8757.70 ms / 824 tokens
llama-server | 11372.22.171.230 I slot print_timing: id 0 | task 2835228 | graphs reused = 2745123
llama-server | 11372.22.171.233 I slot print_timing: id 0 | task 2835228 | draft acceptance = 0.78947 ( 450 accepted / 570 generated), mean len = 4.95
llama-server | 11372.22.171.320 I slot release: id 0 | task 2835228 | stop processing: n_tokens = 2116, truncated = 0
llama-server | 11372.27.943.106 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.225 (> 0.100 thold), f_keep = 0.613
llama-server | 11372.27.943.699 I slot launch_slot_: id 0 | task 2835345 | processing task, is_child = 0
llama-server | 11372.31.689.426 I slot print_timing: id 0 | task 2835345 | prompt processing, n_tokens = 3951, progress = 0.91, t = 3.24 s / 1219.04 tokens per second
llama-server | 11372.32.231.058 I slot print_timing: id 0 | task 2835345 | prompt processing, n_tokens = 4463, progress = 1.00, t = 3.84 s / 1162.13 tokens per second
llama-server | 11372.35.410.028 I slot print_timing: id 0 | task 2835345 | n_gen = 167, tg = 55.25 t/s, tg_3s = 55.58 t/s
llama-server | 11372.38.456.902 I slot print_timing: id 0 | task 2835345 | n_gen = 328, tg = 54.04 t/s, tg_3s = 52.84 t/s
llama-server | 11372.41.523.398 I slot print_timing: id 0 | task 2835345 | n_gen = 470, tg = 51.44 t/s, tg_3s = 46.31 t/s
llama-server | 11372.44.583.191 I slot print_timing: id 0 | task 2835345 | n_gen = 614, tg = 50.34 t/s, tg_3s = 47.06 t/s
llama-server | 11372.47.591.542 I slot print_timing: id 0 | task 2835345 | n_gen = 770, tg = 50.64 t/s, tg_3s = 51.86 t/s
llama-server | 11372.50.611.943 I slot print_timing: id 0 | task 2835345 | n_gen = 940, tg = 51.58 t/s, tg_3s = 56.28 t/s
llama-server | 11372.53.618.312 I slot print_timing: id 0 | task 2835345 | n_gen = 1104, tg = 52.00 t/s, tg_3s = 54.55 t/s
llama-server | 11372.56.646.422 I slot print_timing: id 0 | task 2835345 | n_gen = 1279, tg = 52.72 t/s, tg_3s = 57.79 t/s
llama-server | 11372.57.945.424 W srv stop: cancel task, id_task = 2835345
llama-server | 11372.57.962.527 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 682347870831
llama-server | 11372.57.962.884 I slot launch_slot_: id 1 | task 2835699 | processing task, is_child = 0
llama-server | 11372.57.962.887 I slot release: id 0 | task 2835345 | stop processing: n_tokens = 7085, truncated = 0
llama-server | 11373.03.204.510 I slot print_timing: id 1 | task 2835699 | prompt processing, n_tokens = 5243, progress = 0.91, t = 4.71 s / 1113.40 tokens per second
llama-server | 11373.03.867.655 I slot print_timing: id 1 | task 2835699 | prompt processing, n_tokens = 5755, progress = 1.00, t = 5.43 s / 1060.79 tokens per second
llama-server | 11373.07.109.525 I slot print_timing: id 1 | task 2835699 | n_gen = 160, tg = 52.02 t/s, tg_3s = 52.35 t/s
llama-server | 11373.10.168.711 I slot print_timing: id 1 | task 2835699 | n_gen = 315, tg = 51.35 t/s, tg_3s = 50.67 t/s
llama-server | 11373.13.204.176 I slot print_timing: id 1 | task 2835699 | n_gen = 435, tg = 47.43 t/s, tg_3s = 39.53 t/s
llama-server | 11373.16.267.571 I slot print_timing: id 1 | task 2835699 | n_gen = 574, tg = 46.91 t/s, tg_3s = 45.37 t/s
llama-server | 11373.19.309.854 I slot print_timing: id 1 | task 2835699 | n_gen = 714, tg = 46.73 t/s, tg_3s = 46.02 t/s
llama-server | 11373.22.378.898 I slot print_timing: id 1 | task 2835699 | n_gen = 882, tg = 48.07 t/s, tg_3s = 54.74 t/s
llama-server | 11373.25.454.978 I slot print_timing: id 1 | task 2835699 | n_gen = 1061, tg = 49.53 t/s, tg_3s = 58.19 t/s
llama-server | 11373.28.512.696 I slot print_timing: id 1 | task 2835699 | n_gen = 1201, tg = 49.06 t/s, tg_3s = 45.79 t/s
llama-server | 11373.31.517.649 I slot print_timing: id 1 | task 2835699 | n_gen = 1338, tg = 48.68 t/s, tg_3s = 45.59 t/s
llama-server | 11373.34.578.496 I slot print_timing: id 1 | task 2835699 | n_gen = 1482, tg = 48.52 t/s, tg_3s = 47.05 t/s
llama-server | 11373.37.598.664 I slot print_timing: id 1 | task 2835699 | n_gen = 1676, tg = 49.93 t/s, tg_3s = 64.23 t/s
llama-server | 11373.39.931.136 I slot print_timing: id 1 | task 2835699 | prompt eval time = 6090.13 ms / 5759 tokens ( 1.06 ms per token, 945.63 tokens per second)
llama-server | 11373.39.931.139 I slot print_timing: id 1 | task 2835699 | eval time = 35877.86 ms / 1851 tokens ( 19.39 ms per token, 51.56 tokens per second)
llama-server | 11373.39.931.140 I slot print_timing: id 1 | task 2835699 | total time = 41967.99 ms / 7610 tokens
llama-server | 11373.39.931.140 I slot print_timing: id 1 | task 2835699 | graphs reused = 2745928
llama-server | 11373.39.931.144 I slot print_timing: id 1 | task 2835699 | draft acceptance = 0.59060 ( 1382 accepted / 2340 generated), mean len = 3.95
llama-server | 11373.39.931.332 I slot release: id 1 | task 2835699 | stop processing: n_tokens = 7609, truncated = 0
llama-server | 11373.40.073.010 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.183
llama-server | 11373.40.073.791 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 974.558 MiB)
llama-server | 11373.40.750.358 I slot launch_slot_: id 0 | task 2836174 | processing task, is_child = 0
llama-server | 11373.40.751.374 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 963.353 MiB)
llama-server | 11373.45.045.101 I slot print_timing: id 0 | task 2836174 | n_gen = 192, tg = 63.01 t/s, tg_3s = 63.33 t/s
llama-server | 11373.48.072.954 I slot print_timing: id 0 | task 2836174 | n_gen = 436, tg = 71.79 t/s, tg_3s = 80.59 t/s
llama-server | 11373.50.450.842 I slot print_timing: id 0 | task 2836174 | prompt eval time = 560.91 ms / 263 tokens ( 2.13 ms per token, 468.88 tokens per second)
llama-server | 11373.50.450.845 I slot print_timing: id 0 | task 2836174 | eval time = 8437.13 ms / 632 tokens ( 13.37 ms per token, 74.79 tokens per second)
llama-server | 11373.50.450.846 I slot print_timing: id 0 | task 2836174 | total time = 8998.04 ms / 895 tokens
llama-server | 11373.50.450.846 I slot print_timing: id 0 | task 2836174 | graphs reused = 2746044
llama-server | 11373.50.450.857 I slot print_timing: id 0 | task 2836174 | draft acceptance = 0.87863 ( 514 accepted / 585 generated), mean len = 5.39
llama-server | 11373.50.450.937 I slot release: id 0 | task 2836174 | stop processing: n_tokens = 2186, truncated = 0
llama-server | 11373.57.998.191 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.239 (> 0.100 thold), f_keep = 0.593
llama-server | 11373.57.999.091 I slot launch_slot_: id 0 | task 2836294 | processing task, is_child = 0
llama-server | 11374.01.501.624 I slot print_timing: id 0 | task 2836294 | prompt processing, n_tokens = 3629, progress = 0.91, t = 3.26 s / 1111.64 tokens per second
llama-server | 11374.02.058.048 I slot print_timing: id 0 | task 2836294 | prompt processing, n_tokens = 4141, progress = 1.00, t = 3.60 s / 1151.32 tokens per second
llama-server | 11374.05.324.050 I slot print_timing: id 0 | task 2836294 | n_gen = 159, tg = 52.00 t/s, tg_3s = 52.32 t/s
llama-server | 11374.08.370.835 I slot print_timing: id 0 | task 2836294 | n_gen = 294, tg = 48.15 t/s, tg_3s = 44.31 t/s
llama-server | 11374.11.405.374 I slot print_timing: id 0 | task 2836294 | n_gen = 431, tg = 47.15 t/s, tg_3s = 45.15 t/s
llama-server | 11374.14.472.447 I slot print_timing: id 0 | task 2836294 | n_gen = 561, tg = 45.95 t/s, tg_3s = 42.39 t/s
llama-server | 11374.17.539.014 I slot print_timing: id 0 | task 2836294 | n_gen = 718, tg = 47.01 t/s, tg_3s = 51.20 t/s
llama-server | 11374.20.592.237 I slot print_timing: id 0 | task 2836294 | n_gen = 844, tg = 46.05 t/s, tg_3s = 41.27 t/s
llama-server | 11374.23.596.644 I slot print_timing: id 0 | task 2836294 | n_gen = 978, tg = 45.84 t/s, tg_3s = 44.60 t/s
llama-server | 11374.26.664.195 I slot print_timing: id 0 | task 2836294 | n_gen = 1121, tg = 45.94 t/s, tg_3s = 46.62 t/s
llama-server | 11374.28.001.693 W srv stop: cancel task, id_task = 2836294
llama-server | 11374.28.053.024 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 682435771384
llama-server | 11374.28.053.453 I slot launch_slot_: id 1 | task 2836653 | processing task, is_child = 0
llama-server | 11374.28.053.456 I slot release: id 0 | task 2836294 | stop processing: n_tokens = 6625, truncated = 0
llama-server | 11374.32.994.329 I slot print_timing: id 1 | task 2836653 | prompt processing, n_tokens = 4921, progress = 0.91, t = 4.70 s / 1046.34 tokens per second
llama-server | 11374.33.631.573 I slot print_timing: id 1 | task 2836653 | prompt processing, n_tokens = 5433, progress = 1.00, t = 5.08 s / 1069.24 tokens per second
llama-server | 11374.36.822.092 I slot print_timing: id 1 | task 2836653 | n_gen = 142, tg = 46.63 t/s, tg_3s = 46.95 t/s
llama-server | 11374.39.855.584 I slot print_timing: id 1 | task 2836653 | n_gen = 296, tg = 48.70 t/s, tg_3s = 50.77 t/s
llama-server | 11374.42.873.739 I slot print_timing: id 1 | task 2836653 | n_gen = 412, tg = 45.29 t/s, tg_3s = 38.43 t/s
llama-server | 11374.45.906.498 I slot print_timing: id 1 | task 2836653 | n_gen = 532, tg = 43.85 t/s, tg_3s = 39.57 t/s
llama-server | 11374.48.923.230 I slot print_timing: id 1 | task 2836653 | n_gen = 650, tg = 42.91 t/s, tg_3s = 39.12 t/s
llama-server | 11374.51.967.678 I slot print_timing: id 1 | task 2836653 | n_gen = 785, tg = 43.15 t/s, tg_3s = 44.34 t/s
llama-server | 11374.55.003.695 I slot print_timing: id 1 | task 2836653 | n_gen = 914, tg = 43.05 t/s, tg_3s = 42.49 t/s
llama-server | 11374.58.059.626 I slot print_timing: id 1 | task 2836653 | n_gen = 1038, tg = 42.74 t/s, tg_3s = 40.58 t/s
llama-server | 11375.01.100.565 I slot print_timing: id 1 | task 2836653 | n_gen = 1174, tg = 42.96 t/s, tg_3s = 44.72 t/s
llama-server | 11375.04.163.183 I slot print_timing: id 1 | task 2836653 | n_gen = 1291, tg = 42.48 t/s, tg_3s = 38.20 t/s
llama-server | 11375.07.211.320 I slot print_timing: id 1 | task 2836653 | n_gen = 1427, tg = 42.68 t/s, tg_3s = 44.62 t/s
llama-server | 11375.10.274.845 I slot print_timing: id 1 | task 2836653 | n_gen = 1572, tg = 43.07 t/s, tg_3s = 47.33 t/s
llama-server | 11375.13.322.610 I slot print_timing: id 1 | task 2836653 | n_gen = 1706, tg = 43.14 t/s, tg_3s = 43.97 t/s
llama-server | 11375.16.324.217 I slot print_timing: id 1 | task 2836653 | n_gen = 1838, tg = 43.20 t/s, tg_3s = 43.98 t/s
llama-server | 11375.19.377.628 I slot print_timing: id 1 | task 2836653 | n_gen = 1947, tg = 42.69 t/s, tg_3s = 35.70 t/s
llama-server | 11375.22.378.169 I slot print_timing: id 1 | task 2836653 | n_gen = 2087, tg = 42.94 t/s, tg_3s = 46.66 t/s
llama-server | 11375.25.439.455 I slot print_timing: id 1 | task 2836653 | n_gen = 2217, tg = 42.91 t/s, tg_3s = 42.47 t/s
llama-server | 11375.28.447.104 I slot print_timing: id 1 | task 2836653 | n_gen = 2349, tg = 42.97 t/s, tg_3s = 43.89 t/s
llama-server | 11375.31.521.250 I slot print_timing: id 1 | task 2836653 | n_gen = 2513, tg = 43.52 t/s, tg_3s = 53.35 t/s
llama-server | 11375.34.523.120 I slot print_timing: id 1 | task 2836653 | n_gen = 2625, tg = 43.21 t/s, tg_3s = 37.31 t/s
llama-server | 11375.37.597.659 I slot print_timing: id 1 | task 2836653 | n_gen = 2766, tg = 43.34 t/s, tg_3s = 45.86 t/s
llama-server | 11375.40.611.281 I slot print_timing: id 1 | task 2836653 | n_gen = 2884, tg = 43.15 t/s, tg_3s = 39.16 t/s
llama-server | 11375.43.682.685 I slot print_timing: id 1 | task 2836653 | n_gen = 2990, tg = 42.77 t/s, tg_3s = 34.51 t/s
llama-server | 11375.46.699.152 I slot print_timing: id 1 | task 2836653 | n_gen = 3111, tg = 42.66 t/s, tg_3s = 40.11 t/s
llama-server | 11375.49.701.290 I slot print_timing: id 1 | task 2836653 | n_gen = 3263, tg = 42.98 t/s, tg_3s = 50.63 t/s
llama-server | 11375.52.717.066 I slot print_timing: id 1 | task 2836653 | n_gen = 3373, tg = 42.73 t/s, tg_3s = 36.47 t/s
llama-server | 11375.55.721.227 I slot print_timing: id 1 | task 2836653 | n_gen = 3489, tg = 42.58 t/s, tg_3s = 38.61 t/s
llama-server | 11375.58.747.203 I slot print_timing: id 1 | task 2836653 | n_gen = 3619, tg = 42.59 t/s, tg_3s = 42.96 t/s
llama-server | 11376.01.759.473 I slot print_timing: id 1 | task 2836653 | n_gen = 3750, tg = 42.62 t/s, tg_3s = 43.49 t/s
llama-server | 11376.04.793.507 I slot print_timing: id 1 | task 2836653 | n_gen = 3894, tg = 42.78 t/s, tg_3s = 47.46 t/s
llama-server | 11376.07.817.014 I slot print_timing: id 1 | task 2836653 | n_gen = 4018, tg = 42.73 t/s, tg_3s = 41.01 t/s
llama-server | 11376.10.850.110 I slot print_timing: id 1 | task 2836653 | n_gen = 4141, tg = 42.66 t/s, tg_3s = 40.55 t/s
llama-server | 11376.13.868.651 I slot print_timing: id 1 | task 2836653 | n_gen = 4275, tg = 42.71 t/s, tg_3s = 44.39 t/s
llama-server | 11376.16.910.042 I slot print_timing: id 1 | task 2836653 | n_gen = 4392, tg = 42.58 t/s, tg_3s = 38.47 t/s
llama-server | 11376.19.933.903 I slot print_timing: id 1 | task 2836653 | n_gen = 4514, tg = 42.52 t/s, tg_3s = 40.35 t/s
llama-server | 11376.22.971.310 I slot print_timing: id 1 | task 2836653 | n_gen = 4617, tg = 42.28 t/s, tg_3s = 33.91 t/s
llama-server | 11376.25.998.827 I slot print_timing: id 1 | task 2836653 | n_gen = 4751, tg = 42.33 t/s, tg_3s = 44.26 t/s
llama-server | 11376.29.062.177 I slot print_timing: id 1 | task 2836653 | n_gen = 4896, tg = 42.47 t/s, tg_3s = 47.33 t/s
llama-server | 11376.32.115.567 I slot print_timing: id 1 | task 2836653 | n_gen = 5017, tg = 42.39 t/s, tg_3s = 39.63 t/s
llama-server | 11376.35.189.820 I slot print_timing: id 1 | task 2836653 | n_gen = 5148, tg = 42.40 t/s, tg_3s = 42.61 t/s
llama-server | 11376.38.247.672 I slot print_timing: id 1 | task 2836653 | n_gen = 5274, tg = 42.37 t/s, tg_3s = 41.21 t/s
llama-server | 11376.41.248.039 I slot print_timing: id 1 | task 2836653 | n_gen = 5389, tg = 42.28 t/s, tg_3s = 38.33 t/s
llama-server | 11376.44.307.694 I slot print_timing: id 1 | task 2836653 | n_gen = 5518, tg = 42.27 t/s, tg_3s = 42.16 t/s
llama-server | 11376.47.318.914 I slot print_timing: id 1 | task 2836653 | n_gen = 5687, tg = 42.59 t/s, tg_3s = 56.12 t/s
llama-server | 11376.50.385.580 I slot print_timing: id 1 | task 2836653 | n_gen = 5827, tg = 42.65 t/s, tg_3s = 45.65 t/s
llama-server | 11376.53.392.892 I slot print_timing: id 1 | task 2836653 | n_gen = 5935, tg = 42.51 t/s, tg_3s = 35.91 t/s
llama-server | 11376.56.462.373 I slot print_timing: id 1 | task 2836653 | n_gen = 6028, tg = 42.25 t/s, tg_3s = 30.30 t/s
llama-server | 11376.59.484.800 I slot print_timing: id 1 | task 2836653 | n_gen = 6200, tg = 42.55 t/s, tg_3s = 56.91 t/s
llama-server | 11377.01.701.843 I slot print_timing: id 1 | task 2836653 | prompt eval time = 5744.37 ms / 5437 tokens ( 1.06 ms per token, 946.49 tokens per second)
llama-server | 11377.01.701.847 I slot print_timing: id 1 | task 2836653 | eval time = 147903.75 ms / 6364 tokens ( 23.24 ms per token, 43.02 tokens per second)
llama-server | 11377.01.701.847 I slot print_timing: id 1 | task 2836653 | total time = 153648.12 ms / 11801 tokens
llama-server | 11377.01.701.848 I slot print_timing: id 1 | task 2836653 | graphs reused = 2748284
llama-server | 11377.01.701.851 I slot print_timing: id 1 | task 2836653 | draft acceptance = 0.46489 ( 4449 accepted / 9570 generated), mean len = 3.32
llama-server | 11377.01.702.039 I slot release: id 1 | task 2836653 | stop processing: n_tokens = 11800, truncated = 0
llama-server | 11377.01.844.213 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.829 (> 0.100 thold), f_keep = 0.196
llama-server | 11377.01.845.072 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 985.510 MiB)
llama-server | 11377.02.425.225 I slot launch_slot_: id 0 | task 2838574 | processing task, is_child = 0
llama-server | 11377.02.426.907 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 979.246 MiB)
llama-server | 11377.06.849.144 I slot print_timing: id 0 | task 2838574 | n_gen = 205, tg = 66.64 t/s, tg_3s = 66.97 t/s
llama-server | 11377.09.897.658 I slot print_timing: id 0 | task 2838574 | n_gen = 390, tg = 63.67 t/s, tg_3s = 60.69 t/s
llama-server | 11377.12.954.010 I slot print_timing: id 0 | task 2838574 | n_gen = 621, tg = 67.64 t/s, tg_3s = 75.58 t/s
llama-server | 11377.14.847.726 I slot print_timing: id 0 | task 2838574 | prompt eval time = 566.41 ms / 273 tokens ( 2.07 ms per token, 481.98 tokens per second)
llama-server | 11377.14.847.730 I slot print_timing: id 0 | task 2838574 | eval time = 11059.61 ms / 773 tokens ( 14.33 ms per token, 69.80 tokens per second)
llama-server | 11377.14.847.731 I slot print_timing: id 0 | task 2838574 | total time = 11626.02 ms / 1046 tokens
llama-server | 11377.14.847.732 I slot print_timing: id 0 | task 2838574 | graphs reused = 2748435
llama-server | 11377.14.847.735 I slot print_timing: id 0 | task 2838574 | draft acceptance = 0.81579 ( 620 accepted / 760 generated), mean len = 5.08
llama-server | 11377.14.847.839 I slot release: id 0 | task 2838574 | stop processing: n_tokens = 2337, truncated = 0
llama-server | 11377.23.217.546 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.555
llama-server | 11377.23.218.696 I slot launch_slot_: id 0 | task 2838729 | processing task, is_child = 0
llama-server | 11377.27.119.162 I slot print_timing: id 0 | task 2838729 | prompt processing, n_tokens = 4096, progress = 0.88, t = 3.27 s / 1251.51 tokens per second
llama-server | 11377.27.379.110 I slot print_timing: id 0 | task 2838729 | prompt processing, n_tokens = 4345, progress = 0.92, t = 3.91 s / 1111.31 tokens per second
llama-server | 11377.27.949.228 I slot print_timing: id 0 | task 2838729 | prompt processing, n_tokens = 4857, progress = 1.00, t = 4.26 s / 1139.18 tokens per second
llama-server | 11377.31.197.065 I slot print_timing: id 0 | task 2838729 | n_gen = 174, tg = 56.45 t/s, tg_3s = 56.77 t/s
llama-server | 11377.34.209.393 I slot print_timing: id 0 | task 2838729 | n_gen = 350, tg = 57.43 t/s, tg_3s = 58.43 t/s
llama-server | 11377.37.210.890 I slot print_timing: id 0 | task 2838729 | n_gen = 502, tg = 55.19 t/s, tg_3s = 50.64 t/s
llama-server | 11377.40.244.460 I slot print_timing: id 0 | task 2838729 | n_gen = 666, tg = 54.90 t/s, tg_3s = 54.06 t/s
llama-server | 11377.43.278.228 I slot print_timing: id 0 | task 2838729 | n_gen = 839, tg = 55.33 t/s, tg_3s = 57.02 t/s
llama-server | 11377.46.297.205 I slot print_timing: id 0 | task 2838729 | n_gen = 988, tg = 54.34 t/s, tg_3s = 49.35 t/s
llama-server | 11377.49.356.026 I slot print_timing: id 0 | task 2838729 | n_gen = 1171, tg = 55.13 t/s, tg_3s = 59.83 t/s
llama-server | 11377.52.411.971 I slot print_timing: id 0 | task 2838729 | n_gen = 1347, tg = 55.44 t/s, tg_3s = 57.59 t/s
llama-server | 11377.53.219.877 W srv stop: cancel task, id_task = 2838729
llama-server | 11377.53.231.060 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 682637542091
llama-server | 11377.53.231.480 I slot launch_slot_: id 1 | task 2839075 | processing task, is_child = 0
llama-server | 11377.53.231.484 I slot release: id 0 | task 2838729 | stop processing: n_tokens = 7554, truncated = 0
llama-server | 11377.58.633.273 I slot print_timing: id 1 | task 2839075 | prompt processing, n_tokens = 5388, progress = 0.88, t = 4.75 s / 1135.27 tokens per second
llama-server | 11377.58.919.798 I slot print_timing: id 1 | task 2839075 | prompt processing, n_tokens = 5637, progress = 0.92, t = 5.41 s / 1041.41 tokens per second
llama-server | 11377.59.532.660 I slot print_timing: id 1 | task 2839075 | prompt processing, n_tokens = 6149, progress = 1.00, t = 5.80 s / 1060.24 tokens per second
llama-server | 11378.02.732.827 I slot print_timing: id 1 | task 2839075 | n_gen = 151, tg = 49.01 t/s, tg_3s = 49.34 t/s
llama-server | 11378.05.810.460 I slot print_timing: id 1 | task 2839075 | n_gen = 310, tg = 50.34 t/s, tg_3s = 51.66 t/s
llama-server | 11378.08.824.965 I slot print_timing: id 1 | task 2839075 | n_gen = 451, tg = 49.17 t/s, tg_3s = 46.77 t/s
llama-server | 11378.11.901.185 I slot print_timing: id 1 | task 2839075 | n_gen = 597, tg = 48.74 t/s, tg_3s = 47.46 t/s
llama-server | 11378.14.933.190 I slot print_timing: id 1 | task 2839075 | n_gen = 765, tg = 50.06 t/s, tg_3s = 55.41 t/s
llama-server | 11378.17.971.243 I slot print_timing: id 1 | task 2839075 | n_gen = 941, tg = 51.37 t/s, tg_3s = 57.93 t/s
llama-server | 11378.20.982.675 I slot print_timing: id 1 | task 2839075 | n_gen = 1102, tg = 51.67 t/s, tg_3s = 53.46 t/s
llama-server | 11378.24.024.667 I slot print_timing: id 1 | task 2839075 | n_gen = 1270, tg = 52.11 t/s, tg_3s = 55.23 t/s
llama-server | 11378.27.074.902 I slot print_timing: id 1 | task 2839075 | n_gen = 1470, tg = 53.61 t/s, tg_3s = 65.57 t/s
llama-server | 11378.30.122.454 I slot print_timing: id 1 | task 2839075 | n_gen = 1669, tg = 54.78 t/s, tg_3s = 65.30 t/s
llama-server | 11378.33.123.408 I slot print_timing: id 1 | task 2839075 | n_gen = 1806, tg = 53.96 t/s, tg_3s = 45.65 t/s
llama-server | 11378.36.177.444 I slot print_timing: id 1 | task 2839075 | n_gen = 2028, tg = 55.53 t/s, tg_3s = 72.69 t/s
llama-server | 11378.39.003.471 I slot print_timing: id 1 | task 2839075 | prompt eval time = 6440.73 ms / 6153 tokens ( 1.05 ms per token, 955.33 tokens per second)
llama-server | 11378.39.003.474 I slot print_timing: id 1 | task 2839075 | eval time = 39330.99 ms / 2242 tokens ( 17.55 ms per token, 56.98 tokens per second)
llama-server | 11378.39.003.475 I slot print_timing: id 1 | task 2839075 | total time = 45771.72 ms / 8395 tokens
llama-server | 11378.39.003.475 I slot print_timing: id 1 | task 2839075 | graphs reused = 2749265
llama-server | 11378.39.003.480 I slot print_timing: id 1 | task 2839075 | draft acceptance = 0.68968 ( 1738 accepted / 2520 generated), mean len = 4.45
llama-server | 11378.39.003.671 I slot release: id 1 | task 2839075 | stop processing: n_tokens = 8395, truncated = 0
llama-server | 11378.39.117.857 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.830 (> 0.100 thold), f_keep = 0.172
llama-server | 11378.39.118.667 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 980.124 MiB)
llama-server | 11378.39.709.142 I slot launch_slot_: id 0 | task 2839587 | processing task, is_child = 0
llama-server | 11378.39.710.489 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 999.661 MiB)
llama-server | 11378.43.964.220 I slot print_timing: id 0 | task 2839587 | n_gen = 223, tg = 72.84 t/s, tg_3s = 73.16 t/s
llama-server | 11378.46.796.812 I slot print_timing: id 0 | task 2839587 | prompt eval time = 578.45 ms / 271 tokens ( 2.13 ms per token, 468.49 tokens per second)
llama-server | 11378.46.796.816 I slot print_timing: id 0 | task 2839587 | eval time = 5880.40 ms / 453 tokens ( 13.01 ms per token, 76.87 tokens per second)
llama-server | 11378.46.796.817 I slot print_timing: id 0 | task 2839587 | total time = 6458.85 ms / 724 tokens
llama-server | 11378.46.796.818 I slot print_timing: id 0 | task 2839587 | graphs reused = 2749345
llama-server | 11378.46.796.821 I slot print_timing: id 0 | task 2839587 | draft acceptance = 0.91605 ( 371 accepted / 405 generated), mean len = 5.58
llama-server | 11378.46.796.913 I slot release: id 0 | task 2839587 | stop processing: n_tokens = 2015, truncated = 0
llama-server | 11378.53.512.143 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.644
llama-server | 11378.53.512.897 I slot launch_slot_: id 0 | task 2839671 | processing task, is_child = 0
llama-server | 11378.57.400.500 I slot print_timing: id 0 | task 2839671 | prompt processing, n_tokens = 4096, progress = 0.88, t = 3.26 s / 1255.30 tokens per second
llama-server | 11378.57.658.393 I slot print_timing: id 0 | task 2839671 | prompt processing, n_tokens = 4331, progress = 0.92, t = 3.90 s / 1111.16 tokens per second
llama-server | 11378.58.217.475 I slot print_timing: id 0 | task 2839671 | prompt processing, n_tokens = 4843, progress = 1.00, t = 4.24 s / 1142.05 tokens per second
llama-server | 11379.01.409.697 I slot print_timing: id 0 | task 2839671 | n_gen = 162, tg = 53.42 t/s, tg_3s = 53.75 t/s
llama-server | 11379.04.429.995 I slot print_timing: id 0 | task 2839671 | n_gen = 344, tg = 56.84 t/s, tg_3s = 60.26 t/s
llama-server | 11379.07.456.749 I slot print_timing: id 0 | task 2839671 | n_gen = 521, tg = 57.39 t/s, tg_3s = 58.48 t/s
llama-server | 11379.10.481.797 I slot print_timing: id 0 | task 2839671 | n_gen = 679, tg = 56.10 t/s, tg_3s = 52.23 t/s
llama-server | 11379.13.519.171 I slot print_timing: id 0 | task 2839671 | n_gen = 834, tg = 55.08 t/s, tg_3s = 51.03 t/s
llama-server | 11379.16.542.272 I slot print_timing: id 0 | task 2839671 | n_gen = 981, tg = 54.01 t/s, tg_3s = 48.63 t/s
llama-server | 11379.19.594.582 I slot print_timing: id 0 | task 2839671 | n_gen = 1160, tg = 54.67 t/s, tg_3s = 58.64 t/s
llama-server | 11379.22.656.827 I slot print_timing: id 0 | task 2839671 | n_gen = 1346, tg = 55.44 t/s, tg_3s = 60.74 t/s
llama-server | 11379.23.515.419 W srv stop: cancel task, id_task = 2839671
llama-server | 11379.23.547.875 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 682734843724
llama-server | 11379.23.548.283 I slot launch_slot_: id 1 | task 2840017 | processing task, is_child = 0
llama-server | 11379.23.548.287 I slot release: id 0 | task 2839671 | stop processing: n_tokens = 7533, truncated = 0
llama-server | 11379.28.942.103 I slot print_timing: id 1 | task 2840017 | prompt processing, n_tokens = 5388, progress = 0.88, t = 4.74 s / 1137.06 tokens per second
llama-server | 11379.29.226.526 I slot print_timing: id 1 | task 2840017 | prompt processing, n_tokens = 5623, progress = 0.92, t = 5.40 s / 1040.38 tokens per second
llama-server | 11379.29.858.994 I slot print_timing: id 1 | task 2840017 | prompt processing, n_tokens = 6135, progress = 1.00, t = 5.81 s / 1056.09 tokens per second
llama-server | 11379.33.062.794 I slot print_timing: id 1 | task 2840017 | n_gen = 149, tg = 48.25 t/s, tg_3s = 48.57 t/s
llama-server | 11379.36.080.427 I slot print_timing: id 1 | task 2840017 | n_gen = 298, tg = 48.81 t/s, tg_3s = 49.38 t/s
llama-server | 11379.39.105.958 I slot print_timing: id 1 | task 2840017 | n_gen = 446, tg = 48.84 t/s, tg_3s = 48.92 t/s
llama-server | 11379.42.106.969 I slot print_timing: id 1 | task 2840017 | n_gen = 575, tg = 47.39 t/s, tg_3s = 42.99 t/s
llama-server | 11379.45.134.590 I slot print_timing: id 1 | task 2840017 | n_gen = 737, tg = 48.62 t/s, tg_3s = 53.51 t/s
llama-server | 11379.48.148.527 I slot print_timing: id 1 | task 2840017 | n_gen = 884, tg = 48.64 t/s, tg_3s = 48.77 t/s
llama-server | 11379.51.188.181 I slot print_timing: id 1 | task 2840017 | n_gen = 1048, tg = 49.40 t/s, tg_3s = 53.95 t/s
llama-server | 11379.54.229.862 I slot print_timing: id 1 | task 2840017 | n_gen = 1225, tg = 50.51 t/s, tg_3s = 58.19 t/s
llama-server | 11379.57.254.805 I slot print_timing: id 1 | task 2840017 | n_gen = 1416, tg = 51.91 t/s, tg_3s = 63.14 t/s
llama-server | 11380.00.306.901 I slot print_timing: id 1 | task 2840017 | n_gen = 1618, tg = 53.35 t/s, tg_3s = 66.18 t/s
llama-server | 11380.03.372.454 I slot print_timing: id 1 | task 2840017 | n_gen = 1751, tg = 52.43 t/s, tg_3s = 43.39 t/s
llama-server | 11380.06.410.233 I slot print_timing: id 1 | task 2840017 | n_gen = 1944, tg = 53.36 t/s, tg_3s = 63.53 t/s
llama-server | 11380.09.314.021 I slot print_timing: id 1 | task 2840017 | prompt eval time = 6446.75 ms / 6139 tokens ( 1.05 ms per token, 952.26 tokens per second)
llama-server | 11380.09.314.029 I slot print_timing: id 1 | task 2840017 | eval time = 39318.70 ms / 2161 tokens ( 18.20 ms per token, 54.94 tokens per second)
llama-server | 11380.09.314.029 I slot print_timing: id 1 | task 2840017 | total time = 45765.46 ms / 8300 tokens
llama-server | 11380.09.314.030 I slot print_timing: id 1 | task 2840017 | graphs reused = 2750177
llama-server | 11380.09.314.033 I slot print_timing: id 1 | task 2840017 | draft acceptance = 0.65545 ( 1655 accepted / 2525 generated), mean len = 4.28
llama-server | 11380.09.314.217 I slot release: id 1 | task 2840017 | stop processing: n_tokens = 8299, truncated = 0
llama-server | 11380.09.437.170 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.172
llama-server | 11380.09.437.961 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 930.650 MiB)
llama-server | 11380.10.115.896 I slot launch_slot_: id 0 | task 2840530 | processing task, is_child = 0
llama-server | 11380.10.117.334 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1004.648 MiB)
llama-server | 11380.14.299.826 I slot print_timing: id 0 | task 2840530 | n_gen = 209, tg = 68.46 t/s, tg_3s = 68.78 t/s
llama-server | 11380.17.335.206 I slot print_timing: id 0 | task 2840530 | n_gen = 450, tg = 73.93 t/s, tg_3s = 79.40 t/s
llama-server | 11380.19.212.030 I slot print_timing: id 0 | task 2840530 | prompt eval time = 537.29 ms / 255 tokens ( 2.11 ms per token, 474.60 tokens per second)
llama-server | 11380.19.212.035 I slot print_timing: id 0 | task 2840530 | eval time = 7950.51 ms / 603 tokens ( 13.21 ms per token, 75.72 tokens per second)
llama-server | 11380.19.212.035 I slot print_timing: id 0 | task 2840530 | total time = 8487.80 ms / 858 tokens
llama-server | 11380.19.212.036 I slot print_timing: id 0 | task 2840530 | graphs reused = 2750286
llama-server | 11380.19.212.040 I slot print_timing: id 0 | task 2840530 | draft acceptance = 0.89455 ( 492 accepted / 550 generated), mean len = 5.47
llama-server | 11380.19.212.139 I slot release: id 0 | task 2840530 | stop processing: n_tokens = 2149, truncated = 0
llama-server | 11380.28.539.120 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.604
llama-server | 11380.28.539.681 I slot launch_slot_: id 0 | task 2840643 | processing task, is_child = 0
llama-server | 11380.32.403.580 I slot print_timing: id 0 | task 2840643 | prompt processing, n_tokens = 3930, progress = 1.00, t = 3.40 s / 1154.48 tokens per second
llama-server | 11380.35.646.860 I slot print_timing: id 0 | task 2840643 | n_gen = 185, tg = 60.08 t/s, tg_3s = 60.40 t/s
llama-server | 11380.38.669.366 I slot print_timing: id 0 | task 2840643 | n_gen = 324, tg = 53.08 t/s, tg_3s = 45.99 t/s
llama-server | 11380.41.728.533 I slot print_timing: id 0 | task 2840643 | n_gen = 492, tg = 53.70 t/s, tg_3s = 54.92 t/s
llama-server | 11380.44.781.039 I slot print_timing: id 0 | task 2840643 | n_gen = 643, tg = 52.64 t/s, tg_3s = 49.47 t/s
llama-server | 11380.47.784.692 I slot print_timing: id 0 | task 2840643 | n_gen = 813, tg = 53.42 t/s, tg_3s = 56.60 t/s
llama-server | 11380.50.786.218 I slot print_timing: id 0 | task 2840643 | n_gen = 968, tg = 53.13 t/s, tg_3s = 51.64 t/s
llama-server | 11380.53.848.485 I slot print_timing: id 0 | task 2840643 | n_gen = 1130, tg = 53.09 t/s, tg_3s = 52.90 t/s
llama-server | 11380.56.871.068 I slot print_timing: id 0 | task 2840643 | n_gen = 1337, tg = 55.01 t/s, tg_3s = 68.48 t/s
llama-server | 11380.58.541.796 W srv stop: cancel task, id_task = 2840643
llama-server | 11380.58.578.704 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 682825154269
llama-server | 11380.58.579.080 I slot launch_slot_: id 1 | task 2841004 | processing task, is_child = 0
llama-server | 11380.58.579.083 I slot release: id 0 | task 2840643 | stop processing: n_tokens = 6665, truncated = 0
llama-server | 11381.03.315.603 I slot print_timing: id 1 | task 2841004 | prompt processing, n_tokens = 4710, progress = 0.90, t = 4.26 s / 1105.34 tokens per second
llama-server | 11381.03.918.358 I slot print_timing: id 1 | task 2841004 | prompt processing, n_tokens = 5222, progress = 1.00, t = 4.85 s / 1077.39 tokens per second
llama-server | 11381.07.138.480 I slot print_timing: id 1 | task 2841004 | n_gen = 186, tg = 60.63 t/s, tg_3s = 60.95 t/s
llama-server | 11381.10.163.553 I slot print_timing: id 1 | task 2841004 | n_gen = 352, tg = 57.76 t/s, tg_3s = 54.87 t/s
llama-server | 11381.13.203.769 I slot print_timing: id 1 | task 2841004 | n_gen = 499, tg = 54.62 t/s, tg_3s = 48.35 t/s
llama-server | 11381.16.227.814 I slot print_timing: id 1 | task 2841004 | n_gen = 645, tg = 53.04 t/s, tg_3s = 48.28 t/s
llama-server | 11381.19.277.928 I slot print_timing: id 1 | task 2841004 | n_gen = 793, tg = 52.14 t/s, tg_3s = 48.52 t/s
llama-server | 11381.22.329.146 I slot print_timing: id 1 | task 2841004 | n_gen = 959, tg = 52.52 t/s, tg_3s = 54.40 t/s
llama-server | 11381.25.392.841 I slot print_timing: id 1 | task 2841004 | n_gen = 1181, tg = 55.38 t/s, tg_3s = 72.46 t/s
llama-server | 11381.28.371.987 I slot print_timing: id 1 | task 2841004 | prompt eval time = 5507.63 ms / 5226 tokens ( 1.05 ms per token, 948.87 tokens per second)
llama-server | 11381.28.371.991 I slot print_timing: id 1 | task 2841004 | eval time = 24285.01 ms / 1411 tokens ( 17.22 ms per token, 58.06 tokens per second)
llama-server | 11381.28.371.991 I slot print_timing: id 1 | task 2841004 | total time = 29792.64 ms / 6637 tokens
llama-server | 11381.28.371.992 I slot print_timing: id 1 | task 2841004 | graphs reused = 2750949
llama-server | 11381.28.371.995 I slot print_timing: id 1 | task 2841004 | draft acceptance = 0.68679 ( 1092 accepted / 1590 generated), mean len = 4.43
llama-server | 11381.28.372.188 I slot release: id 1 | task 2841004 | stop processing: n_tokens = 6636, truncated = 0
llama-server | 11381.28.493.322 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.825 (> 0.100 thold), f_keep = 0.195
llama-server | 11381.28.494.087 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 979.459 MiB)
llama-server | 11381.29.197.964 I slot launch_slot_: id 0 | task 2841329 | processing task, is_child = 0
llama-server | 11381.29.198.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 996.901 MiB)
llama-server | 11381.33.496.502 I slot print_timing: id 0 | task 2841329 | n_gen = 196, tg = 64.36 t/s, tg_3s = 64.68 t/s
llama-server | 11381.36.514.699 I slot print_timing: id 0 | task 2841329 | n_gen = 403, tg = 66.47 t/s, tg_3s = 68.58 t/s
llama-server | 11381.38.893.198 I slot print_timing: id 0 | task 2841329 | prompt eval time = 568.89 ms / 280 tokens ( 2.03 ms per token, 492.19 tokens per second)
llama-server | 11381.38.893.201 I slot print_timing: id 0 | task 2841329 | eval time = 8426.56 ms / 597 tokens ( 14.14 ms per token, 70.73 tokens per second)
llama-server | 11381.38.893.202 I slot print_timing: id 0 | task 2841329 | total time = 8995.44 ms / 877 tokens
llama-server | 11381.38.893.202 I slot print_timing: id 0 | task 2841329 | graphs reused = 2751065
llama-server | 11381.38.893.205 I slot print_timing: id 0 | task 2841329 | draft acceptance = 0.81880 ( 479 accepted / 585 generated), mean len = 5.09
llama-server | 11381.38.893.292 I slot release: id 0 | task 2841329 | stop processing: n_tokens = 2168, truncated = 0
llama-server | 11381.43.799.542 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.244 (> 0.100 thold), f_keep = 0.598
llama-server | 11381.43.800.332 I slot launch_slot_: id 0 | task 2841449 | processing task, is_child = 0
llama-server | 11381.47.756.778 I slot print_timing: id 0 | task 2841449 | prompt processing, n_tokens = 4016, progress = 1.00, t = 3.49 s / 1150.67 tokens per second
llama-server | 11381.50.930.285 I slot print_timing: id 0 | task 2841449 | n_gen = 184, tg = 60.91 t/s, tg_3s = 61.24 t/s
llama-server | 11381.53.993.940 I slot print_timing: id 0 | task 2841449 | n_gen = 362, tg = 59.49 t/s, tg_3s = 58.10 t/s
llama-server | 11381.57.046.830 I slot print_timing: id 0 | task 2841449 | n_gen = 514, tg = 56.24 t/s, tg_3s = 49.79 t/s
llama-server | 11382.00.052.903 I slot print_timing: id 0 | task 2841449 | n_gen = 646, tg = 53.19 t/s, tg_3s = 43.91 t/s
llama-server | 11382.03.111.997 I slot print_timing: id 0 | task 2841449 | n_gen = 806, tg = 53.01 t/s, tg_3s = 52.30 t/s
llama-server | 11382.06.127.894 I slot print_timing: id 0 | task 2841449 | n_gen = 1005, tg = 55.16 t/s, tg_3s = 65.98 t/s
llama-server | 11382.09.150.398 I slot print_timing: id 0 | task 2841449 | n_gen = 1219, tg = 57.39 t/s, tg_3s = 70.80 t/s
llama-server | 11382.11.521.329 I slot print_timing: id 0 | task 2841449 | prompt eval time = 4124.75 ms / 4020 tokens ( 1.03 ms per token, 974.60 tokens per second)
llama-server | 11382.11.521.332 I slot print_timing: id 0 | task 2841449 | eval time = 23595.47 ms / 1391 tokens ( 16.98 ms per token, 58.91 tokens per second)
llama-server | 11382.11.521.333 I slot print_timing: id 0 | task 2841449 | total time = 27720.22 ms / 5411 tokens
llama-server | 11382.11.521.333 I slot print_timing: id 0 | task 2841449 | graphs reused = 2751382
llama-server | 11382.11.521.336 I slot print_timing: id 0 | task 2841449 | draft acceptance = 0.66335 ( 1068 accepted / 1610 generated), mean len = 4.32
llama-server | 11382.11.521.551 I slot release: id 0 | task 2841449 | stop processing: n_tokens = 6702, truncated = 0
llama-server | 11382.11.637.728 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.194
llama-server | 11382.11.638.477 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 964.164 MiB)
llama-server | 11382.12.243.569 I slot launch_slot_: id 0 | task 2841776 | processing task, is_child = 0
llama-server | 11382.15.876.715 I slot print_timing: id 0 | task 2841776 | n_gen = 196, tg = 64.27 t/s, tg_3s = 64.60 t/s
llama-server | 11382.18.901.072 I slot print_timing: id 0 | task 2841776 | n_gen = 400, tg = 65.86 t/s, tg_3s = 67.45 t/s
llama-server | 11382.21.928.747 I slot print_timing: id 0 | task 2841776 | n_gen = 608, tg = 66.81 t/s, tg_3s = 68.70 t/s
llama-server | 11382.24.959.841 I slot print_timing: id 0 | task 2841776 | n_gen = 846, tg = 69.74 t/s, tg_3s = 78.52 t/s
llama-server | 11382.27.054.418 I slot print_timing: id 0 | task 2841776 | prompt eval time = 598.49 ms / 278 tokens ( 2.15 ms per token, 464.50 tokens per second)
llama-server | 11382.27.054.421 I slot print_timing: id 0 | task 2841776 | eval time = 14211.58 ms / 1017 tokens ( 13.99 ms per token, 71.49 tokens per second)
llama-server | 11382.27.054.422 I slot print_timing: id 0 | task 2841776 | total time = 14810.07 ms / 1295 tokens
llama-server | 11382.27.054.422 I slot print_timing: id 0 | task 2841776 | graphs reused = 2751578
llama-server | 11382.27.054.425 I slot print_timing: id 0 | task 2841776 | draft acceptance = 0.83147 ( 819 accepted / 985 generated), mean len = 5.16
llama-server | 11382.27.054.517 I slot release: id 0 | task 2841776 | stop processing: n_tokens = 2586, truncated = 0
llama-server | 11382.33.879.305 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.302 (> 0.100 thold), f_keep = 0.502
llama-server | 11382.33.880.077 I slot launch_slot_: id 0 | task 2841976 | processing task, is_child = 0
llama-server | 11382.40.061.057 I slot print_timing: id 0 | task 2841976 | n_gen = 159, tg = 51.95 t/s, tg_3s = 52.27 t/s
llama-server | 11382.43.076.649 I slot print_timing: id 0 | task 2841976 | n_gen = 313, tg = 51.51 t/s, tg_3s = 51.07 t/s
llama-server | 11382.46.114.676 I slot print_timing: id 0 | task 2841976 | n_gen = 451, tg = 49.48 t/s, tg_3s = 45.42 t/s
llama-server | 11382.49.154.734 I slot print_timing: id 0 | task 2841976 | n_gen = 592, tg = 48.70 t/s, tg_3s = 46.38 t/s
llama-server | 11382.52.199.694 I slot print_timing: id 0 | task 2841976 | n_gen = 794, tg = 52.24 t/s, tg_3s = 66.34 t/s
llama-server | 11382.55.204.162 I slot print_timing: id 0 | task 2841976 | n_gen = 1014, tg = 55.71 t/s, tg_3s = 73.22 t/s
llama-server | 11382.57.698.228 I slot print_timing: id 0 | task 2841976 | prompt eval time = 3138.58 ms / 3004 tokens ( 1.04 ms per token, 957.12 tokens per second)
llama-server | 11382.57.698.232 I slot print_timing: id 0 | task 2841976 | eval time = 20678.77 ms / 1211 tokens ( 17.09 ms per token, 58.51 tokens per second)
llama-server | 11382.57.698.232 I slot print_timing: id 0 | task 2841976 | total time = 23817.35 ms / 4215 tokens
llama-server | 11382.57.698.233 I slot print_timing: id 0 | task 2841976 | graphs reused = 2751859
llama-server | 11382.57.698.236 I slot print_timing: id 0 | task 2841976 | draft acceptance = 0.64912 ( 925 accepted / 1425 generated), mean len = 4.25
llama-server | 11382.57.698.407 I slot release: id 0 | task 2841976 | stop processing: n_tokens = 5506, truncated = 0
llama-server | 11382.57.799.775 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.825 (> 0.100 thold), f_keep = 0.236
llama-server | 11382.57.800.496 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1136.247 MiB)
llama-server | 11382.58.333.796 I slot launch_slot_: id 0 | task 2842266 | processing task, is_child = 0
llama-server | 11383.01.949.312 I slot print_timing: id 0 | task 2842266 | n_gen = 177, tg = 58.16 t/s, tg_3s = 58.49 t/s
llama-server | 11383.04.972.746 I slot print_timing: id 0 | task 2842266 | n_gen = 387, tg = 63.81 t/s, tg_3s = 69.46 t/s
llama-server | 11383.08.001.657 I slot print_timing: id 0 | task 2842266 | n_gen = 624, tg = 68.62 t/s, tg_3s = 78.25 t/s
llama-server | 11383.08.939.876 I slot print_timing: id 0 | task 2842266 | prompt eval time = 589.02 ms / 281 tokens ( 2.10 ms per token, 477.07 tokens per second)
llama-server | 11383.08.939.879 I slot print_timing: id 0 | task 2842266 | eval time = 10016.55 ms / 702 tokens ( 14.29 ms per token, 69.98 tokens per second)
llama-server | 11383.08.939.879 I slot print_timing: id 0 | task 2842266 | total time = 10605.56 ms / 983 tokens
llama-server | 11383.08.939.880 I slot print_timing: id 0 | task 2842266 | graphs reused = 2751997
llama-server | 11383.08.939.883 I slot print_timing: id 0 | task 2842266 | draft acceptance = 0.80863 ( 562 accepted / 695 generated), mean len = 5.04
llama-server | 11383.08.939.989 I slot release: id 0 | task 2842266 | stop processing: n_tokens = 2274, truncated = 0
llama-server | 11383.14.070.317 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.211 (> 0.100 thold), f_keep = 0.570
llama-server | 11383.14.071.160 I slot launch_slot_: id 0 | task 2842408 | processing task, is_child = 0
llama-server | 11383.17.949.483 I slot print_timing: id 0 | task 2842408 | prompt processing, n_tokens = 4096, progress = 0.87, t = 3.26 s / 1258.09 tokens per second
llama-server | 11383.18.235.320 I slot print_timing: id 0 | task 2842408 | prompt processing, n_tokens = 4353, progress = 0.92, t = 3.89 s / 1119.64 tokens per second
llama-server | 11383.18.811.009 I slot print_timing: id 0 | task 2842408 | prompt processing, n_tokens = 4865, progress = 1.00, t = 4.29 s / 1134.62 tokens per second
llama-server | 11383.22.022.275 I slot print_timing: id 0 | task 2842408 | n_gen = 194, tg = 62.92 t/s, tg_3s = 63.24 t/s
llama-server | 11383.25.031.261 I slot print_timing: id 0 | task 2842408 | n_gen = 381, tg = 62.54 t/s, tg_3s = 62.15 t/s
llama-server | 11383.28.037.025 I slot print_timing: id 0 | task 2842408 | n_gen = 542, tg = 59.57 t/s, tg_3s = 53.56 t/s
llama-server | 11383.31.110.660 I slot print_timing: id 0 | task 2842408 | n_gen = 692, tg = 56.85 t/s, tg_3s = 48.80 t/s
llama-server | 11383.34.128.856 I slot print_timing: id 0 | task 2842408 | n_gen = 866, tg = 57.01 t/s, tg_3s = 57.65 t/s
llama-server | 11383.37.153.284 I slot print_timing: id 0 | task 2842408 | n_gen = 1031, tg = 56.60 t/s, tg_3s = 54.56 t/s
llama-server | 11383.40.169.349 I slot print_timing: id 0 | task 2842408 | n_gen = 1213, tg = 57.13 t/s, tg_3s = 60.34 t/s
llama-server | 11383.43.205.196 I slot print_timing: id 0 | task 2842408 | n_gen = 1400, tg = 57.69 t/s, tg_3s = 61.60 t/s
llama-server | 11383.44.073.422 W srv stop: cancel task, id_task = 2842408
llama-server | 11383.44.092.167 I slot release: id 0 | task 2842408 | stop processing: n_tokens = 7629, truncated = 0
llama-server | 11383.44.092.187 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 0.808
llama-server | 11383.44.092.522 I slot launch_slot_: id 0 | task 2842757 | processing task, is_child = 0
llama-server | 11383.47.310.650 I slot print_timing: id 0 | task 2842757 | n_gen = 179, tg = 58.93 t/s, tg_3s = 59.25 t/s
llama-server | 11383.50.328.138 I slot print_timing: id 0 | task 2842757 | n_gen = 360, tg = 59.45 t/s, tg_3s = 59.98 t/s
llama-server | 11383.53.348.327 I slot print_timing: id 0 | task 2842757 | n_gen = 530, tg = 58.40 t/s, tg_3s = 56.29 t/s
llama-server | 11383.56.355.773 I slot print_timing: id 0 | task 2842757 | n_gen = 683, tg = 56.52 t/s, tg_3s = 50.87 t/s
llama-server | 11383.59.387.995 I slot print_timing: id 0 | task 2842757 | n_gen = 854, tg = 56.50 t/s, tg_3s = 56.39 t/s
llama-server | 11384.02.422.296 I slot print_timing: id 0 | task 2842757 | n_gen = 1028, tg = 56.64 t/s, tg_3s = 57.34 t/s
llama-server | 11384.05.442.265 I slot print_timing: id 0 | task 2842757 | n_gen = 1199, tg = 56.64 t/s, tg_3s = 56.62 t/s
llama-server | 11384.08.511.744 I slot print_timing: id 0 | task 2842757 | n_gen = 1385, tg = 57.14 t/s, tg_3s = 60.60 t/s
llama-server | 11384.11.521.817 I slot print_timing: id 0 | task 2842757 | n_gen = 1547, tg = 56.77 t/s, tg_3s = 53.82 t/s
llama-server | 11384.14.593.175 I slot print_timing: id 0 | task 2842757 | n_gen = 1762, tg = 58.11 t/s, tg_3s = 70.00 t/s
llama-server | 11384.17.616.273 I slot print_timing: id 0 | task 2842757 | n_gen = 1959, tg = 58.75 t/s, tg_3s = 65.16 t/s
llama-server | 11384.20.611.793 I slot print_timing: id 0 | task 2842757 | prompt eval time = 196.91 ms / 4 tokens ( 49.23 ms per token, 20.31 tokens per second)
llama-server | 11384.20.611.797 I slot print_timing: id 0 | task 2842757 | eval time = 36321.86 ms / 2194 tokens ( 16.56 ms per token, 60.38 tokens per second)
llama-server | 11384.20.611.797 I slot print_timing: id 0 | task 2842757 | total time = 36518.77 ms / 2198 tokens
llama-server | 11384.20.611.798 I slot print_timing: id 0 | task 2842757 | graphs reused = 2752815
llama-server | 11384.20.611.801 I slot print_timing: id 0 | task 2842757 | draft acceptance = 0.69693 ( 1704 accepted / 2445 generated), mean len = 4.48
llama-server | 11384.20.611.990 I slot release: id 0 | task 2842757 | stop processing: n_tokens = 8354, truncated = 0
llama-server | 11384.20.754.066 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.830 (> 0.100 thold), f_keep = 0.155
llama-server | 11384.20.754.885 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 995.053 MiB)
llama-server | 11384.21.818.271 I slot launch_slot_: id 0 | task 2843248 | processing task, is_child = 0
llama-server | 11384.25.466.393 I slot print_timing: id 0 | task 2843248 | n_gen = 192, tg = 62.92 t/s, tg_3s = 63.25 t/s
llama-server | 11384.28.501.644 I slot print_timing: id 0 | task 2843248 | n_gen = 430, tg = 70.67 t/s, tg_3s = 78.41 t/s
llama-server | 11384.30.021.027 I slot print_timing: id 0 | task 2843248 | prompt eval time = 611.86 ms / 271 tokens ( 2.26 ms per token, 442.91 tokens per second)
llama-server | 11384.30.021.030 I slot print_timing: id 0 | task 2843248 | eval time = 7590.10 ms / 556 tokens ( 13.68 ms per token, 73.12 tokens per second)
llama-server | 11384.30.021.031 I slot print_timing: id 0 | task 2843248 | total time = 8201.96 ms / 827 tokens
llama-server | 11384.30.021.032 I slot print_timing: id 0 | task 2843248 | graphs reused = 2752919
llama-server | 11384.30.021.035 I slot print_timing: id 0 | task 2843248 | draft acceptance = 0.85714 ( 450 accepted / 525 generated), mean len = 5.29
llama-server | 11384.30.021.127 I slot release: id 0 | task 2843248 | stop processing: n_tokens = 2118, truncated = 0
llama-server | 11420.46.953.945 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.612
llama-server | 11420.46.954.490 I slot launch_slot_: id 0 | task 2843356 | processing task, is_child = 0
llama-server | 11420.50.509.193 I slot print_timing: id 0 | task 2843356 | prompt processing, n_tokens = 3772, progress = 0.91, t = 3.21 s / 1176.66 tokens per second
llama-server | 11420.51.054.897 I slot print_timing: id 0 | task 2843356 | prompt processing, n_tokens = 4284, progress = 1.00, t = 3.67 s / 1167.00 tokens per second
llama-server | 11420.54.244.915 I slot print_timing: id 0 | task 2843356 | n_gen = 162, tg = 52.72 t/s, tg_3s = 53.05 t/s
llama-server | 11420.57.282.241 I slot print_timing: id 0 | task 2843356 | n_gen = 312, tg = 51.06 t/s, tg_3s = 49.39 t/s
llama-server | 11421.00.314.199 I slot print_timing: id 0 | task 2843356 | n_gen = 467, tg = 51.08 t/s, tg_3s = 51.12 t/s
llama-server | 11421.03.330.550 I slot print_timing: id 0 | task 2843356 | n_gen = 623, tg = 51.24 t/s, tg_3s = 51.72 t/s
llama-server | 11421.06.386.126 I slot print_timing: id 0 | task 2843356 | n_gen = 768, tg = 50.48 t/s, tg_3s = 47.45 t/s
llama-server | 11421.09.401.567 I slot print_timing: id 0 | task 2843356 | n_gen = 924, tg = 50.69 t/s, tg_3s = 51.73 t/s
llama-server | 11421.12.433.567 I slot print_timing: id 0 | task 2843356 | n_gen = 1088, tg = 51.17 t/s, tg_3s = 54.09 t/s
llama-server | 11421.15.459.679 I slot print_timing: id 0 | task 2843356 | n_gen = 1238, tg = 50.97 t/s, tg_3s = 49.57 t/s
llama-server | 11421.16.956.250 W srv stop: cancel task, id_task = 2843356
llama-server | 11421.16.997.434 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 682904212240
llama-server | 11421.16.997.768 I slot launch_slot_: id 1 | task 2843722 | processing task, is_child = 0
llama-server | 11421.16.997.770 I slot release: id 0 | task 2843356 | stop processing: n_tokens = 6917, truncated = 0
llama-server | 11421.22.008.271 I slot print_timing: id 1 | task 2843722 | prompt processing, n_tokens = 5064, progress = 0.91, t = 4.64 s / 1090.69 tokens per second
llama-server | 11421.22.607.809 I slot print_timing: id 1 | task 2843722 | prompt processing, n_tokens = 5576, progress = 1.00, t = 5.12 s / 1089.56 tokens per second
llama-server | 11421.25.828.444 I slot print_timing: id 1 | task 2843722 | n_gen = 123, tg = 40.33 t/s, tg_3s = 40.66 t/s
llama-server | 11421.28.899.105 I slot print_timing: id 1 | task 2843722 | n_gen = 257, tg = 42.00 t/s, tg_3s = 43.64 t/s
llama-server | 11421.31.927.863 I slot print_timing: id 1 | task 2843722 | n_gen = 400, tg = 43.73 t/s, tg_3s = 47.21 t/s
llama-server | 11421.34.956.491 I slot print_timing: id 1 | task 2843722 | n_gen = 558, tg = 45.83 t/s, tg_3s = 52.17 t/s
llama-server | 11421.37.984.528 I slot print_timing: id 1 | task 2843722 | n_gen = 689, tg = 45.32 t/s, tg_3s = 43.26 t/s
llama-server | 11421.41.025.200 I slot print_timing: id 1 | task 2843722 | n_gen = 871, tg = 47.74 t/s, tg_3s = 59.86 t/s
llama-server | 11421.44.056.204 I slot print_timing: id 1 | task 2843722 | n_gen = 1031, tg = 48.46 t/s, tg_3s = 52.79 t/s
llama-server | 11421.47.099.761 I slot print_timing: id 1 | task 2843722 | n_gen = 1174, tg = 48.28 t/s, tg_3s = 46.98 t/s
llama-server | 11421.50.127.203 I slot print_timing: id 1 | task 2843722 | n_gen = 1310, tg = 47.91 t/s, tg_3s = 44.92 t/s
llama-server | 11421.53.177.053 I slot print_timing: id 1 | task 2843722 | n_gen = 1453, tg = 47.80 t/s, tg_3s = 46.89 t/s
llama-server | 11421.56.235.163 I slot print_timing: id 1 | task 2843722 | n_gen = 1599, tg = 47.80 t/s, tg_3s = 47.74 t/s
llama-server | 11421.59.276.330 I slot print_timing: id 1 | task 2843722 | n_gen = 1760, tg = 48.23 t/s, tg_3s = 52.94 t/s
llama-server | 11422.02.336.886 I slot print_timing: id 1 | task 2843722 | n_gen = 1899, tg = 48.01 t/s, tg_3s = 45.42 t/s
llama-server | 11422.05.393.052 I slot print_timing: id 1 | task 2843722 | n_gen = 2050, tg = 48.11 t/s, tg_3s = 49.41 t/s
llama-server | 11422.08.395.659 I slot print_timing: id 1 | task 2843722 | n_gen = 2185, tg = 47.90 t/s, tg_3s = 44.96 t/s
llama-server | 11422.11.466.993 I slot print_timing: id 1 | task 2843722 | n_gen = 2355, tg = 48.37 t/s, tg_3s = 55.35 t/s
llama-server | 11422.14.531.401 I slot print_timing: id 1 | task 2843722 | n_gen = 2519, tg = 48.68 t/s, tg_3s = 53.52 t/s
llama-server | 11422.17.542.472 I slot print_timing: id 1 | task 2843722 | n_gen = 2681, tg = 48.96 t/s, tg_3s = 53.80 t/s
llama-server | 11422.20.558.956 I slot print_timing: id 1 | task 2843722 | n_gen = 2892, tg = 50.06 t/s, tg_3s = 69.95 t/s
llama-server | 11422.23.331.481 I slot print_timing: id 1 | task 2843722 | prompt eval time = 5805.30 ms / 5580 tokens ( 1.04 ms per token, 961.19 tokens per second)
llama-server | 11422.23.331.484 I slot print_timing: id 1 | task 2843722 | eval time = 60528.15 ms / 3102 tokens ( 19.52 ms per token, 51.23 tokens per second)
llama-server | 11422.23.331.485 I slot print_timing: id 1 | task 2843722 | total time = 66333.45 ms / 8682 tokens
llama-server | 11422.23.331.485 I slot print_timing: id 1 | task 2843722 | graphs reused = 2754056
llama-server | 11422.23.331.488 I slot print_timing: id 1 | task 2843722 | draft acceptance = 0.58111 ( 2307 accepted / 3970 generated), mean len = 3.91
llama-server | 11422.23.331.749 I slot release: id 1 | task 2843722 | stop processing: n_tokens = 8681, truncated = 0
llama-server | 11422.23.465.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.839 (> 0.100 thold), f_keep = 0.188
llama-server | 11422.23.466.258 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1023.035 MiB)
llama-server | 11422.24.032.885 I slot launch_slot_: id 0 | task 2844523 | processing task, is_child = 0
llama-server | 11422.24.033.615 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 994.354 MiB)
llama-server | 11422.28.294.163 I slot print_timing: id 0 | task 2844523 | n_gen = 181, tg = 59.55 t/s, tg_3s = 59.88 t/s
llama-server | 11422.31.296.324 I slot print_timing: id 0 | task 2844523 | n_gen = 364, tg = 60.25 t/s, tg_3s = 60.96 t/s
llama-server | 11422.34.094.826 I slot print_timing: id 0 | task 2844523 | prompt eval time = 527.29 ms / 254 tokens ( 2.08 ms per token, 481.71 tokens per second)
llama-server | 11422.34.094.829 I slot print_timing: id 0 | task 2844523 | eval time = 8823.32 ms / 594 tokens ( 14.88 ms per token, 67.21 tokens per second)
llama-server | 11422.34.094.830 I slot print_timing: id 0 | task 2844523 | total time = 9350.61 ms / 848 tokens
llama-server | 11422.34.094.830 I slot print_timing: id 0 | task 2844523 | graphs reused = 2754178
llama-server | 11422.34.094.834 I slot print_timing: id 0 | task 2844523 | draft acceptance = 0.76423 ( 470 accepted / 615 generated), mean len = 4.82
llama-server | 11422.34.094.919 I slot release: id 0 | task 2844523 | stop processing: n_tokens = 2139, truncated = 0
llama-server | 11422.40.073.168 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.304 (> 0.100 thold), f_keep = 0.606
llama-server | 11422.40.073.746 I slot launch_slot_: id 0 | task 2844649 | processing task, is_child = 0
llama-server | 11422.46.206.345 I slot print_timing: id 0 | task 2844649 | n_gen = 111, tg = 36.36 t/s, tg_3s = 36.69 t/s
llama-server | 11422.49.272.466 I slot print_timing: id 0 | task 2844649 | n_gen = 215, tg = 35.13 t/s, tg_3s = 33.92 t/s
llama-server | 11422.52.334.463 I slot print_timing: id 0 | task 2844649 | n_gen = 330, tg = 35.94 t/s, tg_3s = 37.56 t/s
llama-server | 11422.55.375.729 I slot print_timing: id 0 | task 2844649 | n_gen = 479, tg = 39.20 t/s, tg_3s = 48.99 t/s
llama-server | 11422.58.411.024 I slot print_timing: id 0 | task 2844649 | n_gen = 614, tg = 40.25 t/s, tg_3s = 44.48 t/s
llama-server | 11423.01.432.852 I slot print_timing: id 0 | task 2844649 | n_gen = 769, tg = 42.08 t/s, tg_3s = 51.29 t/s
llama-server | 11423.04.490.156 I slot print_timing: id 0 | task 2844649 | n_gen = 943, tg = 44.21 t/s, tg_3s = 56.91 t/s
llama-server | 11423.07.541.825 I slot print_timing: id 0 | task 2844649 | n_gen = 1111, tg = 45.57 t/s, tg_3s = 55.05 t/s
llama-server | 11423.10.075.507 W srv stop: cancel task, id_task = 2844649
llama-server | 11423.10.087.757 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 685359171801
llama-server | 11423.10.088.146 I slot launch_slot_: id 1 | task 2845027 | processing task, is_child = 0
llama-server | 11423.10.088.149 I slot release: id 0 | task 2844649 | stop processing: n_tokens = 5498, truncated = 0
llama-server | 11423.13.786.857 I slot print_timing: id 1 | task 2845027 | prompt processing, n_tokens = 3755, progress = 0.88, t = 3.27 s / 1147.78 tokens per second
llama-server | 11423.14.390.178 I slot print_timing: id 1 | task 2845027 | prompt processing, n_tokens = 4267, progress = 1.00, t = 3.82 s / 1118.39 tokens per second
llama-server | 11423.17.733.011 I slot print_timing: id 1 | task 2845027 | n_gen = 101, tg = 32.00 t/s, tg_3s = 32.32 t/s
llama-server | 11423.20.791.252 I slot print_timing: id 1 | task 2845027 | n_gen = 217, tg = 34.93 t/s, tg_3s = 37.93 t/s
llama-server | 11423.23.834.885 I slot print_timing: id 1 | task 2845027 | n_gen = 351, tg = 37.93 t/s, tg_3s = 44.03 t/s
llama-server | 11423.26.898.467 I slot print_timing: id 1 | task 2845027 | n_gen = 478, tg = 38.81 t/s, tg_3s = 41.45 t/s
llama-server | 11423.29.951.599 I slot print_timing: id 1 | task 2845027 | n_gen = 608, tg = 39.56 t/s, tg_3s = 42.58 t/s
llama-server | 11423.33.019.384 I slot print_timing: id 1 | task 2845027 | n_gen = 737, tg = 39.97 t/s, tg_3s = 42.05 t/s
llama-server | 11423.36.080.908 I slot print_timing: id 1 | task 2845027 | n_gen = 903, tg = 42.01 t/s, tg_3s = 54.22 t/s
llama-server | 11423.39.093.998 I slot print_timing: id 1 | task 2845027 | n_gen = 1067, tg = 43.53 t/s, tg_3s = 54.43 t/s
llama-server | 11423.42.183.400 I slot print_timing: id 1 | task 2845027 | n_gen = 1238, tg = 44.86 t/s, tg_3s = 55.35 t/s
llama-server | 11423.45.245.671 I slot print_timing: id 1 | task 2845027 | n_gen = 1358, tg = 44.29 t/s, tg_3s = 39.19 t/s
llama-server | 11423.48.263.145 I slot print_timing: id 1 | task 2845027 | n_gen = 1516, tg = 45.02 t/s, tg_3s = 52.36 t/s
llama-server | 11423.51.274.899 I slot print_timing: id 1 | task 2845027 | n_gen = 1701, tg = 46.36 t/s, tg_3s = 61.43 t/s
llama-server | 11423.54.296.133 I slot print_timing: id 1 | task 2845027 | n_gen = 1868, tg = 47.04 t/s, tg_3s = 55.28 t/s
llama-server | 11423.57.323.812 I slot print_timing: id 1 | task 2845027 | n_gen = 2036, tg = 47.64 t/s, tg_3s = 55.49 t/s
llama-server | 11424.00.339.374 I slot print_timing: id 1 | task 2845027 | n_gen = 2181, tg = 47.67 t/s, tg_3s = 48.08 t/s
llama-server | 11424.03.369.359 I slot print_timing: id 1 | task 2845027 | n_gen = 2304, tg = 47.23 t/s, tg_3s = 40.59 t/s
llama-server | 11424.06.383.545 I slot print_timing: id 1 | task 2845027 | n_gen = 2452, tg = 47.34 t/s, tg_3s = 49.10 t/s
llama-server | 11424.09.423.265 I slot print_timing: id 1 | task 2845027 | n_gen = 2632, tg = 48.00 t/s, tg_3s = 59.22 t/s
llama-server | 11424.12.470.921 I slot print_timing: id 1 | task 2845027 | n_gen = 2807, tg = 48.49 t/s, tg_3s = 57.42 t/s
llama-server | 11424.15.508.771 I slot print_timing: id 1 | task 2845027 | n_gen = 3015, tg = 49.49 t/s, tg_3s = 68.47 t/s
llama-server | 11424.18.565.496 I slot print_timing: id 1 | task 2845027 | n_gen = 3170, tg = 49.55 t/s, tg_3s = 50.71 t/s
llama-server | 11424.21.629.142 I slot print_timing: id 1 | task 2845027 | n_gen = 3346, tg = 49.91 t/s, tg_3s = 57.45 t/s
llama-server | 11424.24.670.580 I slot print_timing: id 1 | task 2845027 | n_gen = 3527, tg = 50.33 t/s, tg_3s = 59.51 t/s
llama-server | 11424.27.672.446 I slot print_timing: id 1 | task 2845027 | n_gen = 3744, tg = 51.23 t/s, tg_3s = 72.29 t/s
llama-server | 11424.30.673.461 I slot print_timing: id 1 | task 2845027 | n_gen = 3950, tg = 51.92 t/s, tg_3s = 68.64 t/s
llama-server | 11424.33.743.646 I slot print_timing: id 1 | task 2845027 | n_gen = 4110, tg = 51.92 t/s, tg_3s = 52.11 t/s
llama-server | 11424.36.803.059 I slot print_timing: id 1 | task 2845027 | n_gen = 4301, tg = 52.31 t/s, tg_3s = 62.43 t/s
llama-server | 11424.39.432.911 I slot print_timing: id 1 | task 2845027 | prompt eval time = 4519.43 ms / 4271 tokens ( 1.06 ms per token, 945.03 tokens per second)
llama-server | 11424.39.432.914 I slot print_timing: id 1 | task 2845027 | eval time = 84825.08 ms / 4502 tokens ( 18.85 ms per token, 53.06 tokens per second)
llama-server | 11424.39.432.915 I slot print_timing: id 1 | task 2845027 | total time = 89344.50 ms / 8773 tokens
llama-server | 11424.39.432.916 I slot print_timing: id 1 | task 2845027 | graphs reused = 2755651
llama-server | 11424.39.432.919 I slot print_timing: id 1 | task 2845027 | draft acceptance = 0.60232 ( 3379 accepted / 5610 generated), mean len = 4.01
llama-server | 11424.39.433.115 I slot release: id 1 | task 2845027 | stop processing: n_tokens = 8772, truncated = 0
llama-server | 11424.39.573.540 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.821 (> 0.100 thold), f_keep = 0.236
llama-server | 11424.39.574.270 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1019.843 MiB)
llama-server | 11424.40.083.605 I slot launch_slot_: id 0 | task 2846156 | processing task, is_child = 0
llama-server | 11424.40.084.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 965.494 MiB)
llama-server | 11424.44.586.876 I slot print_timing: id 0 | task 2846156 | n_gen = 202, tg = 66.35 t/s, tg_3s = 66.68 t/s
llama-server | 11424.47.604.228 I slot print_timing: id 0 | task 2846156 | n_gen = 416, tg = 68.63 t/s, tg_3s = 70.92 t/s
llama-server | 11424.49.118.636 I slot print_timing: id 0 | task 2846156 | prompt eval time = 580.82 ms / 287 tokens ( 2.02 ms per token, 494.13 tokens per second)
llama-server | 11424.49.118.639 I slot print_timing: id 0 | task 2846156 | eval time = 7560.93 ms / 539 tokens ( 14.05 ms per token, 71.16 tokens per second)
llama-server | 11424.49.118.640 I slot print_timing: id 0 | task 2846156 | total time = 8141.75 ms / 826 tokens
llama-server | 11424.49.118.640 I slot print_timing: id 0 | task 2846156 | graphs reused = 2755755
llama-server | 11424.49.118.644 I slot print_timing: id 0 | task 2846156 | draft acceptance = 0.82476 ( 433 accepted / 525 generated), mean len = 5.12
llama-server | 11424.49.118.736 I slot release: id 0 | task 2846156 | stop processing: n_tokens = 2117, truncated = 0
llama-server | 11424.55.214.483 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.315 (> 0.100 thold), f_keep = 0.613
llama-server | 11424.55.215.106 I slot launch_slot_: id 0 | task 2846264 | processing task, is_child = 0
llama-server | 11425.01.245.194 I slot print_timing: id 0 | task 2846264 | n_gen = 217, tg = 71.28 t/s, tg_3s = 71.61 t/s
llama-server | 11425.04.284.926 I slot print_timing: id 0 | task 2846264 | n_gen = 405, tg = 66.56 t/s, tg_3s = 61.85 t/s
llama-server | 11425.07.313.665 I slot print_timing: id 0 | task 2846264 | n_gen = 555, tg = 60.89 t/s, tg_3s = 49.53 t/s
llama-server | 11425.10.339.434 I slot print_timing: id 0 | task 2846264 | n_gen = 706, tg = 58.15 t/s, tg_3s = 49.90 t/s
llama-server | 11425.13.403.115 I slot print_timing: id 0 | task 2846264 | n_gen = 886, tg = 58.27 t/s, tg_3s = 58.75 t/s
llama-server | 11425.16.462.586 I slot print_timing: id 0 | task 2846264 | n_gen = 1049, tg = 57.43 t/s, tg_3s = 53.28 t/s
llama-server | 11425.19.510.491 I slot print_timing: id 0 | task 2846264 | n_gen = 1182, tg = 55.46 t/s, tg_3s = 43.64 t/s
llama-server | 11425.22.516.068 I slot print_timing: id 0 | task 2846264 | n_gen = 1371, tg = 56.38 t/s, tg_3s = 62.88 t/s
llama-server | 11425.25.216.776 W srv stop: cancel task, id_task = 2846264
llama-server | 11425.25.232.355 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 685495273169
llama-server | 11425.25.232.833 I slot launch_slot_: id 1 | task 2846641 | processing task, is_child = 0
llama-server | 11425.25.232.836 I slot release: id 0 | task 2846264 | stop processing: n_tokens = 5671, truncated = 0
llama-server | 11425.28.858.009 I slot print_timing: id 1 | task 2846641 | prompt processing, n_tokens = 3603, progress = 0.87, t = 3.34 s / 1080.01 tokens per second
llama-server | 11425.29.436.464 I slot print_timing: id 1 | task 2846641 | prompt processing, n_tokens = 4115, progress = 1.00, t = 3.74 s / 1101.48 tokens per second
llama-server | 11425.32.655.960 I slot print_timing: id 1 | task 2846641 | n_gen = 207, tg = 68.28 t/s, tg_3s = 68.60 t/s
llama-server | 11425.35.715.340 I slot print_timing: id 1 | task 2846641 | n_gen = 384, tg = 63.03 t/s, tg_3s = 57.85 t/s
llama-server | 11425.38.715.680 I slot print_timing: id 1 | task 2846641 | n_gen = 540, tg = 59.38 t/s, tg_3s = 51.99 t/s
llama-server | 11425.41.777.812 I slot print_timing: id 1 | task 2846641 | n_gen = 683, tg = 56.18 t/s, tg_3s = 46.70 t/s
llama-server | 11425.44.783.441 I slot print_timing: id 1 | task 2846641 | n_gen = 821, tg = 54.15 t/s, tg_3s = 45.91 t/s
llama-server | 11425.47.791.895 I slot print_timing: id 1 | task 2846641 | n_gen = 968, tg = 53.27 t/s, tg_3s = 48.86 t/s
llama-server | 11425.50.859.994 I slot print_timing: id 1 | task 2846641 | n_gen = 1116, tg = 52.54 t/s, tg_3s = 48.24 t/s
llama-server | 11425.53.873.262 I slot print_timing: id 1 | task 2846641 | n_gen = 1254, tg = 51.70 t/s, tg_3s = 45.80 t/s
llama-server | 11425.56.876.902 I slot print_timing: id 1 | task 2846641 | n_gen = 1431, tg = 52.50 t/s, tg_3s = 58.93 t/s
llama-server | 11425.59.902.716 I slot print_timing: id 1 | task 2846641 | n_gen = 1599, tg = 52.80 t/s, tg_3s = 55.52 t/s
llama-server | 11426.02.934.154 I slot print_timing: id 1 | task 2846641 | n_gen = 1826, tg = 54.81 t/s, tg_3s = 74.88 t/s
llama-server | 11426.04.216.694 I slot print_timing: id 1 | task 2846641 | prompt eval time = 4405.83 ms / 4119 tokens ( 1.07 ms per token, 934.90 tokens per second)
llama-server | 11426.04.216.699 I slot print_timing: id 1 | task 2846641 | eval time = 34577.74 ms / 1922 tokens ( 18.00 ms per token, 55.56 tokens per second)
llama-server | 11426.04.216.699 I slot print_timing: id 1 | task 2846641 | total time = 38983.57 ms / 6041 tokens
llama-server | 11426.04.216.700 I slot print_timing: id 1 | task 2846641 | graphs reused = 2756574
llama-server | 11426.04.216.703 I slot print_timing: id 1 | task 2846641 | draft acceptance = 0.63522 ( 1461 accepted / 2300 generated), mean len = 4.18
llama-server | 11426.04.216.882 I slot release: id 1 | task 2846641 | stop processing: n_tokens = 6040, truncated = 0
llama-server | 11426.04.344.002 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.839 (> 0.100 thold), f_keep = 0.229
llama-server | 11426.04.344.691 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 964.550 MiB)
llama-server | 11426.04.969.181 I slot launch_slot_: id 0 | task 2847108 | processing task, is_child = 0
llama-server | 11426.04.970.413 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 966.744 MiB)
llama-server | 11426.09.229.096 I slot print_timing: id 0 | task 2847108 | n_gen = 196, tg = 63.53 t/s, tg_3s = 63.85 t/s
llama-server | 11426.12.241.043 I slot print_timing: id 0 | task 2847108 | n_gen = 384, tg = 62.98 t/s, tg_3s = 62.42 t/s
llama-server | 11426.15.268.867 I slot print_timing: id 0 | task 2847108 | n_gen = 627, tg = 68.72 t/s, tg_3s = 80.26 t/s
llama-server | 11426.17.500.410 I slot print_timing: id 0 | task 2847108 | prompt eval time = 536.16 ms / 254 tokens ( 2.11 ms per token, 473.74 tokens per second)
llama-server | 11426.17.500.414 I slot print_timing: id 0 | task 2847108 | eval time = 11340.92 ms / 807 tokens ( 14.07 ms per token, 71.07 tokens per second)
llama-server | 11426.17.500.414 I slot print_timing: id 0 | task 2847108 | total time = 11877.08 ms / 1061 tokens
llama-server | 11426.17.500.415 I slot print_timing: id 0 | task 2847108 | graphs reused = 2756727
llama-server | 11426.17.500.418 I slot print_timing: id 0 | task 2847108 | draft acceptance = 0.84675 ( 652 accepted / 770 generated), mean len = 5.23
llama-server | 11426.17.500.502 I slot release: id 0 | task 2847108 | stop processing: n_tokens = 2352, truncated = 0
llama-server | 11426.25.380.421 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.247 (> 0.100 thold), f_keep = 0.551
llama-server | 11426.25.381.089 I slot launch_slot_: id 0 | task 2847265 | processing task, is_child = 0
llama-server | 11426.29.219.647 I slot print_timing: id 0 | task 2847265 | prompt processing, n_tokens = 3949, progress = 1.00, t = 3.39 s / 1163.28 tokens per second
llama-server | 11426.32.446.406 I slot print_timing: id 0 | task 2847265 | n_gen = 183, tg = 59.57 t/s, tg_3s = 59.89 t/s
llama-server | 11426.35.469.357 I slot print_timing: id 0 | task 2847265 | n_gen = 339, tg = 55.61 t/s, tg_3s = 51.61 t/s
llama-server | 11426.38.527.269 I slot print_timing: id 0 | task 2847265 | n_gen = 504, tg = 55.06 t/s, tg_3s = 53.96 t/s
llama-server | 11426.41.590.224 I slot print_timing: id 0 | task 2847265 | n_gen = 658, tg = 53.86 t/s, tg_3s = 50.28 t/s
llama-server | 11426.44.628.929 I slot print_timing: id 0 | task 2847265 | n_gen = 795, tg = 52.11 t/s, tg_3s = 45.09 t/s
llama-server | 11426.47.645.302 I slot print_timing: id 0 | task 2847265 | n_gen = 989, tg = 54.12 t/s, tg_3s = 64.32 t/s
llama-server | 11426.50.665.875 I slot print_timing: id 0 | task 2847265 | n_gen = 1189, tg = 55.84 t/s, tg_3s = 66.21 t/s
llama-server | 11426.53.692.534 I slot print_timing: id 0 | task 2847265 | n_gen = 1417, tg = 58.27 t/s, tg_3s = 75.33 t/s
llama-server | 11426.54.717.957 I slot print_timing: id 0 | task 2847265 | prompt eval time = 4009.36 ms / 3953 tokens ( 1.01 ms per token, 985.94 tokens per second)
llama-server | 11426.54.717.960 I slot print_timing: id 0 | task 2847265 | eval time = 25326.71 ms / 1494 tokens ( 16.96 ms per token, 58.95 tokens per second)
llama-server | 11426.54.717.961 I slot print_timing: id 0 | task 2847265 | total time = 29336.07 ms / 5447 tokens
llama-server | 11426.54.717.961 I slot print_timing: id 0 | task 2847265 | graphs reused = 2757069
llama-server | 11426.54.717.964 I slot print_timing: id 0 | task 2847265 | draft acceptance = 0.66052 ( 1146 accepted / 1735 generated), mean len = 4.30
llama-server | 11426.54.718.178 I slot release: id 0 | task 2847265 | stop processing: n_tokens = 6738, truncated = 0
llama-server | 11426.54.821.298 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.827 (> 0.100 thold), f_keep = 0.192
llama-server | 11426.54.822.010 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.979 MiB)
llama-server | 11426.55.498.620 I slot launch_slot_: id 0 | task 2847617 | processing task, is_child = 0
llama-server | 11426.59.121.883 I slot print_timing: id 0 | task 2847617 | n_gen = 213, tg = 69.69 t/s, tg_3s = 70.02 t/s
llama-server | 11427.02.144.197 I slot print_timing: id 0 | task 2847617 | n_gen = 406, tg = 66.78 t/s, tg_3s = 63.86 t/s
llama-server | 11427.05.175.244 I slot print_timing: id 0 | task 2847617 | n_gen = 648, tg = 71.14 t/s, tg_3s = 79.84 t/s
llama-server | 11427.06.620.614 I slot print_timing: id 0 | task 2847617 | prompt eval time = 580.62 ms / 277 tokens ( 2.10 ms per token, 477.08 tokens per second)
llama-server | 11427.06.620.618 I slot print_timing: id 0 | task 2847617 | eval time = 10540.68 ms / 768 tokens ( 13.74 ms per token, 72.77 tokens per second)
llama-server | 11427.06.620.618 I slot print_timing: id 0 | task 2847617 | total time = 11121.30 ms / 1045 tokens
llama-server | 11427.06.620.619 I slot print_timing: id 0 | task 2847617 | graphs reused = 2757214
llama-server | 11427.06.620.622 I slot print_timing: id 0 | task 2847617 | draft acceptance = 0.85068 ( 621 accepted / 730 generated), mean len = 5.25
llama-server | 11427.06.620.722 I slot release: id 0 | task 2847617 | stop processing: n_tokens = 2336, truncated = 0
llama-server | 11427.15.552.078 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.248 (> 0.100 thold), f_keep = 0.555
llama-server | 11427.15.552.669 I slot launch_slot_: id 0 | task 2847766 | processing task, is_child = 0
llama-server | 11427.19.482.079 I slot print_timing: id 0 | task 2847766 | prompt processing, n_tokens = 3939, progress = 1.00, t = 3.46 s / 1136.91 tokens per second
llama-server | 11427.22.686.816 I slot print_timing: id 0 | task 2847766 | n_gen = 175, tg = 56.89 t/s, tg_3s = 57.21 t/s
llama-server | 11427.25.711.155 I slot print_timing: id 0 | task 2847766 | n_gen = 323, tg = 52.94 t/s, tg_3s = 48.94 t/s
llama-server | 11427.28.768.916 I slot print_timing: id 0 | task 2847766 | n_gen = 491, tg = 53.61 t/s, tg_3s = 54.94 t/s
llama-server | 11427.31.827.538 I slot print_timing: id 0 | task 2847766 | n_gen = 651, tg = 53.28 t/s, tg_3s = 52.31 t/s
llama-server | 11427.34.894.927 I slot print_timing: id 0 | task 2847766 | n_gen = 831, tg = 54.37 t/s, tg_3s = 58.68 t/s
llama-server | 11427.37.967.031 I slot print_timing: id 0 | task 2847766 | n_gen = 987, tg = 53.77 t/s, tg_3s = 50.78 t/s
llama-server | 11427.40.987.989 I slot print_timing: id 0 | task 2847766 | n_gen = 1176, tg = 55.01 t/s, tg_3s = 62.56 t/s
llama-server | 11427.43.988.274 I slot print_timing: id 0 | task 2847766 | n_gen = 1335, tg = 54.76 t/s, tg_3s = 52.99 t/s
llama-server | 11427.45.554.383 W srv stop: cancel task, id_task = 2847766
llama-server | 11427.45.613.568 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 685580056934
llama-server | 11427.45.613.984 I slot launch_slot_: id 1 | task 2848123 | processing task, is_child = 0
llama-server | 11427.45.613.987 I slot release: id 0 | task 2847766 | stop processing: n_tokens = 6665, truncated = 0
llama-server | 11427.50.342.198 I slot print_timing: id 1 | task 2848123 | prompt processing, n_tokens = 4719, progress = 0.90, t = 4.26 s / 1109.00 tokens per second
llama-server | 11427.50.967.965 I slot print_timing: id 1 | task 2848123 | prompt processing, n_tokens = 5231, progress = 1.00, t = 4.86 s / 1075.82 tokens per second
llama-server | 11427.54.163.278 I slot print_timing: id 1 | task 2848123 | n_gen = 164, tg = 53.63 t/s, tg_3s = 53.96 t/s
llama-server | 11427.57.174.423 I slot print_timing: id 1 | task 2848123 | n_gen = 336, tg = 55.37 t/s, tg_3s = 57.12 t/s
llama-server | 11428.00.214.964 I slot print_timing: id 1 | task 2848123 | n_gen = 501, tg = 55.00 t/s, tg_3s = 54.27 t/s
llama-server | 11428.03.252.015 I slot print_timing: id 1 | task 2848123 | n_gen = 648, tg = 53.35 t/s, tg_3s = 48.40 t/s
llama-server | 11428.06.274.461 I slot print_timing: id 1 | task 2848123 | n_gen = 805, tg = 53.07 t/s, tg_3s = 51.94 t/s
llama-server | 11428.09.322.946 I slot print_timing: id 1 | task 2848123 | n_gen = 978, tg = 53.68 t/s, tg_3s = 56.75 t/s
llama-server | 11428.12.383.525 I slot print_timing: id 1 | task 2848123 | n_gen = 1174, tg = 55.18 t/s, tg_3s = 64.04 t/s
llama-server | 11428.15.430.410 I slot print_timing: id 1 | task 2848123 | n_gen = 1384, tg = 56.90 t/s, tg_3s = 68.92 t/s
llama-server | 11428.18.503.128 I slot print_timing: id 1 | task 2848123 | n_gen = 1614, tg = 58.91 t/s, tg_3s = 74.85 t/s
llama-server | 11428.20.968.988 I slot print_timing: id 1 | task 2848123 | prompt eval time = 5509.88 ms / 5235 tokens ( 1.05 ms per token, 950.11 tokens per second)
llama-server | 11428.20.968.992 I slot print_timing: id 1 | task 2848123 | eval time = 29844.86 ms / 1805 tokens ( 16.54 ms per token, 60.45 tokens per second)
llama-server | 11428.20.968.993 I slot print_timing: id 1 | task 2848123 | total time = 35354.75 ms / 7040 tokens
llama-server | 11428.20.968.993 I slot print_timing: id 1 | task 2848123 | graphs reused = 2757945
llama-server | 11428.20.968.996 I slot print_timing: id 1 | task 2848123 | draft acceptance = 0.72092 ( 1413 accepted / 1960 generated), mean len = 4.60
llama-server | 11428.20.969.190 I slot release: id 1 | task 2848123 | stop processing: n_tokens = 7040, truncated = 0
llama-server | 11428.21.081.017 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.195
llama-server | 11428.21.081.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1021.671 MiB)
llama-server | 11428.21.618.511 I slot launch_slot_: id 0 | task 2848522 | processing task, is_child = 0
llama-server | 11428.21.619.126 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 973.873 MiB)
llama-server | 11428.25.810.256 I slot print_timing: id 0 | task 2848522 | n_gen = 204, tg = 67.06 t/s, tg_3s = 67.38 t/s
llama-server | 11428.28.826.971 I slot print_timing: id 0 | task 2848522 | n_gen = 398, tg = 65.69 t/s, tg_3s = 64.31 t/s
llama-server | 11428.31.856.326 I slot print_timing: id 0 | task 2848522 | n_gen = 641, tg = 70.54 t/s, tg_3s = 80.22 t/s
llama-server | 11428.33.946.403 I slot print_timing: id 0 | task 2848522 | prompt eval time = 567.39 ms / 279 tokens ( 2.03 ms per token, 491.72 tokens per second)
llama-server | 11428.33.946.407 I slot print_timing: id 0 | task 2848522 | eval time = 11163.35 ms / 812 tokens ( 13.76 ms per token, 72.65 tokens per second)
llama-server | 11428.33.946.408 I slot print_timing: id 0 | task 2848522 | total time = 11730.75 ms / 1091 tokens
llama-server | 11428.33.946.408 I slot print_timing: id 0 | task 2848522 | graphs reused = 2758099
llama-server | 11428.33.946.413 I slot print_timing: id 0 | task 2848522 | draft acceptance = 0.84645 ( 656 accepted / 775 generated), mean len = 5.23
llama-server | 11428.33.946.506 I slot release: id 0 | task 2848522 | stop processing: n_tokens = 2382, truncated = 0
llama-server | 11428.40.607.256 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.212 (> 0.100 thold), f_keep = 0.545
llama-server | 11428.40.607.811 I slot launch_slot_: id 0 | task 2848680 | processing task, is_child = 0
llama-server | 11428.44.496.321 I slot print_timing: id 0 | task 2848680 | prompt processing, n_tokens = 4096, progress = 0.88, t = 3.27 s / 1254.15 tokens per second
llama-server | 11428.44.738.232 I slot print_timing: id 0 | task 2848680 | prompt processing, n_tokens = 4318, progress = 0.92, t = 3.90 s / 1107.73 tokens per second
llama-server | 11428.45.302.947 I slot print_timing: id 0 | task 2848680 | prompt processing, n_tokens = 4830, progress = 1.00, t = 4.23 s / 1141.95 tokens per second
llama-server | 11428.48.533.542 I slot print_timing: id 0 | task 2848680 | n_gen = 172, tg = 56.95 t/s, tg_3s = 57.28 t/s
llama-server | 11428.51.602.051 I slot print_timing: id 0 | task 2848680 | n_gen = 358, tg = 58.80 t/s, tg_3s = 60.62 t/s
llama-server | 11428.54.650.905 I slot print_timing: id 0 | task 2848680 | n_gen = 505, tg = 55.26 t/s, tg_3s = 48.21 t/s
llama-server | 11428.57.661.800 I slot print_timing: id 0 | task 2848680 | n_gen = 661, tg = 54.41 t/s, tg_3s = 51.81 t/s
llama-server | 11429.00.674.959 I slot print_timing: id 0 | task 2848680 | n_gen = 831, tg = 54.81 t/s, tg_3s = 56.42 t/s
llama-server | 11429.03.675.820 I slot print_timing: id 0 | task 2848680 | n_gen = 1004, tg = 55.28 t/s, tg_3s = 57.65 t/s
llama-server | 11429.06.698.230 I slot print_timing: id 0 | task 2848680 | n_gen = 1167, tg = 55.09 t/s, tg_3s = 53.93 t/s
llama-server | 11429.09.731.336 I slot print_timing: id 0 | task 2848680 | n_gen = 1357, tg = 56.03 t/s, tg_3s = 62.64 t/s
llama-server | 11429.10.612.032 W srv stop: cancel task, id_task = 2848680
llama-server | 11429.10.614.408 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 685716809243
llama-server | 11429.10.614.853 I slot launch_slot_: id 1 | task 2849028 | processing task, is_child = 0
llama-server | 11429.10.614.857 I slot release: id 0 | task 2848680 | stop processing: n_tokens = 7538, truncated = 0
llama-server | 11429.16.012.142 I slot print_timing: id 1 | task 2849028 | prompt processing, n_tokens = 5388, progress = 0.88, t = 4.75 s / 1135.33 tokens per second
llama-server | 11429.16.277.966 I slot print_timing: id 1 | task 2849028 | prompt processing, n_tokens = 5610, progress = 0.92, t = 5.41 s / 1037.32 tokens per second
llama-server | 11429.16.888.090 I slot print_timing: id 1 | task 2849028 | prompt processing, n_tokens = 6122, progress = 1.00, t = 5.77 s / 1060.72 tokens per second
llama-server | 11429.20.101.153 I slot print_timing: id 1 | task 2849028 | n_gen = 157, tg = 51.01 t/s, tg_3s = 51.33 t/s
llama-server | 11429.23.170.755 I slot print_timing: id 1 | task 2849028 | n_gen = 325, tg = 52.87 t/s, tg_3s = 54.73 t/s
llama-server | 11429.26.239.702 I slot print_timing: id 1 | task 2849028 | n_gen = 493, tg = 53.50 t/s, tg_3s = 54.74 t/s
llama-server | 11429.29.295.307 I slot print_timing: id 1 | task 2849028 | n_gen = 667, tg = 54.36 t/s, tg_3s = 56.94 t/s
llama-server | 11429.32.304.104 I slot print_timing: id 1 | task 2849028 | n_gen = 854, tg = 55.89 t/s, tg_3s = 62.15 t/s
llama-server | 11429.35.318.855 I slot print_timing: id 1 | task 2849028 | n_gen = 1019, tg = 55.70 t/s, tg_3s = 54.73 t/s
llama-server | 11429.38.388.269 I slot print_timing: id 1 | task 2849028 | n_gen = 1175, tg = 55.00 t/s, tg_3s = 50.82 t/s
llama-server | 11429.41.407.901 I slot print_timing: id 1 | task 2849028 | n_gen = 1347, tg = 55.24 t/s, tg_3s = 56.96 t/s
llama-server | 11429.44.436.745 I slot print_timing: id 1 | task 2849028 | n_gen = 1513, tg = 55.20 t/s, tg_3s = 54.81 t/s
llama-server | 11429.47.467.844 I slot print_timing: id 1 | task 2849028 | n_gen = 1729, tg = 56.80 t/s, tg_3s = 71.26 t/s
llama-server | 11429.50.472.677 I slot print_timing: id 1 | task 2849028 | n_gen = 1871, tg = 55.94 t/s, tg_3s = 47.26 t/s
llama-server | 11429.53.511.772 I slot print_timing: id 1 | task 2849028 | n_gen = 2103, tg = 57.64 t/s, tg_3s = 76.34 t/s
llama-server | 11429.54.599.577 I slot print_timing: id 1 | task 2849028 | prompt eval time = 6427.86 ms / 6126 tokens ( 1.05 ms per token, 953.04 tokens per second)
llama-server | 11429.54.599.580 I slot print_timing: id 1 | task 2849028 | eval time = 37556.60 ms / 2183 tokens ( 17.21 ms per token, 58.10 tokens per second)
llama-server | 11429.54.599.581 I slot print_timing: id 1 | task 2849028 | total time = 43984.46 ms / 8309 tokens
llama-server | 11429.54.599.581 I slot print_timing: id 1 | task 2849028 | graphs reused = 2758914
llama-server | 11429.54.599.584 I slot print_timing: id 1 | task 2849028 | draft acceptance = 0.69610 ( 1695 accepted / 2435 generated), mean len = 4.48
llama-server | 11429.54.599.767 I slot release: id 1 | task 2849028 | stop processing: n_tokens = 8308, truncated = 0
llama-server | 11429.54.708.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.838 (> 0.100 thold), f_keep = 0.172
llama-server | 11429.54.709.421 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1032.544 MiB)
llama-server | 11429.55.370.721 I slot launch_slot_: id 0 | task 2849523 | processing task, is_child = 0
llama-server | 11429.55.371.776 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 926.693 MiB)
llama-server | 11429.59.606.975 I slot print_timing: id 0 | task 2849523 | n_gen = 195, tg = 63.90 t/s, tg_3s = 64.22 t/s
llama-server | 11430.02.631.409 I slot print_timing: id 0 | task 2849523 | n_gen = 409, tg = 67.32 t/s, tg_3s = 70.76 t/s
llama-server | 11430.03.640.372 I slot print_timing: id 0 | task 2849523 | prompt eval time = 535.79 ms / 255 tokens ( 2.10 ms per token, 475.93 tokens per second)
llama-server | 11430.03.640.376 I slot print_timing: id 0 | task 2849523 | eval time = 7069.53 ms / 490 tokens ( 14.46 ms per token, 69.17 tokens per second)
llama-server | 11430.03.640.376 I slot print_timing: id 0 | task 2849523 | total time = 7605.32 ms / 745 tokens
llama-server | 11430.03.640.377 I slot print_timing: id 0 | task 2849523 | graphs reused = 2759011
llama-server | 11430.03.640.380 I slot print_timing: id 0 | task 2849523 | draft acceptance = 0.79796 ( 391 accepted / 490 generated), mean len = 4.99
llama-server | 11430.03.640.465 I slot release: id 0 | task 2849523 | stop processing: n_tokens = 2036, truncated = 0
llama-server | 11430.10.883.761 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.637
llama-server | 11430.10.884.444 I slot launch_slot_: id 0 | task 2849624 | processing task, is_child = 0
llama-server | 11430.14.778.756 I slot print_timing: id 0 | task 2849624 | prompt processing, n_tokens = 4096, progress = 0.67, t = 3.26 s / 1257.35 tokens per second
llama-server | 11430.16.717.444 I slot print_timing: id 0 | task 2849624 | prompt processing, n_tokens = 6144, progress = 0.92, t = 5.20 s / 1180.46 tokens per second
llama-server | 11430.16.870.737 I slot print_timing: id 0 | task 2849624 | prompt processing, n_tokens = 6254, progress = 0.94, t = 5.84 s / 1070.38 tokens per second
llama-server | 11430.17.443.286 I slot print_timing: id 0 | task 2849624 | prompt processing, n_tokens = 6766, progress = 1.00, t = 6.08 s / 1112.50 tokens per second
llama-server | 11430.20.709.461 I slot print_timing: id 0 | task 2849624 | n_gen = 169, tg = 55.34 t/s, tg_3s = 55.66 t/s
llama-server | 11430.23.725.236 I slot print_timing: id 0 | task 2849624 | n_gen = 363, tg = 59.82 t/s, tg_3s = 64.33 t/s
llama-server | 11430.26.755.943 I slot print_timing: id 0 | task 2849624 | n_gen = 505, tg = 55.49 t/s, tg_3s = 46.85 t/s
llama-server | 11430.29.803.228 I slot print_timing: id 0 | task 2849624 | n_gen = 685, tg = 56.39 t/s, tg_3s = 59.07 t/s
llama-server | 11430.32.855.305 I slot print_timing: id 0 | task 2849624 | n_gen = 889, tg = 58.49 t/s, tg_3s = 66.84 t/s
llama-server | 11430.35.912.781 I slot print_timing: id 0 | task 2849624 | n_gen = 1059, tg = 58.01 t/s, tg_3s = 55.60 t/s
llama-server | 11430.38.979.100 I slot print_timing: id 0 | task 2849624 | n_gen = 1257, tg = 58.95 t/s, tg_3s = 64.57 t/s
llama-server | 11430.40.885.773 W srv stop: cancel task, id_task = 2849624
llama-server | 11430.40.920.013 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 685810439818
llama-server | 11430.40.920.427 I slot launch_slot_: id 1 | task 2849944 | processing task, is_child = 0
llama-server | 11430.40.920.430 I slot release: id 0 | task 2849624 | stop processing: n_tokens = 9470, truncated = 0
llama-server | 11430.46.389.503 I slot print_timing: id 1 | task 2849944 | prompt processing, n_tokens = 5388, progress = 0.67, t = 4.81 s / 1120.40 tokens per second
llama-server | 11430.48.475.463 I slot print_timing: id 1 | task 2849944 | prompt processing, n_tokens = 7436, progress = 0.92, t = 6.88 s / 1080.10 tokens per second
llama-server | 11430.48.643.237 I slot print_timing: id 1 | task 2849944 | prompt processing, n_tokens = 7546, progress = 0.94, t = 7.57 s / 997.48 tokens per second
llama-server | 11430.49.296.282 I slot print_timing: id 1 | task 2849944 | prompt processing, n_tokens = 8058, progress = 1.00, t = 7.86 s / 1025.50 tokens per second
llama-server | 11430.52.516.764 I slot print_timing: id 1 | task 2849944 | n_gen = 135, tg = 43.72 t/s, tg_3s = 44.04 t/s
llama-server | 11430.55.553.897 I slot print_timing: id 1 | task 2849944 | n_gen = 272, tg = 44.41 t/s, tg_3s = 45.11 t/s
llama-server | 11430.58.619.309 I slot print_timing: id 1 | task 2849944 | n_gen = 414, tg = 45.05 t/s, tg_3s = 46.32 t/s
llama-server | 11431.01.661.287 I slot print_timing: id 1 | task 2849944 | n_gen = 549, tg = 44.88 t/s, tg_3s = 44.38 t/s
llama-server | 11431.04.727.014 I slot print_timing: id 1 | task 2849944 | n_gen = 684, tg = 44.71 t/s, tg_3s = 44.04 t/s
llama-server | 11431.07.781.416 I slot print_timing: id 1 | task 2849944 | n_gen = 844, tg = 45.99 t/s, tg_3s = 52.38 t/s
llama-server | 11431.10.851.344 I slot print_timing: id 1 | task 2849944 | n_gen = 1002, tg = 46.78 t/s, tg_3s = 51.47 t/s
llama-server | 11431.13.854.899 I slot print_timing: id 1 | task 2849944 | n_gen = 1181, tg = 48.35 t/s, tg_3s = 59.60 t/s
llama-server | 11431.16.929.524 I slot print_timing: id 1 | task 2849944 | n_gen = 1364, tg = 49.60 t/s, tg_3s = 59.52 t/s
llama-server | 11431.19.943.628 I slot print_timing: id 1 | task 2849944 | n_gen = 1531, tg = 50.18 t/s, tg_3s = 55.41 t/s
llama-server | 11431.22.956.039 I slot print_timing: id 1 | task 2849944 | n_gen = 1684, tg = 50.23 t/s, tg_3s = 50.79 t/s
llama-server | 11431.25.965.109 I slot print_timing: id 1 | task 2849944 | n_gen = 1909, tg = 52.25 t/s, tg_3s = 74.77 t/s
llama-server | 11431.26.379.356 I slot print_timing: id 1 | task 2849944 | prompt eval time = 8530.75 ms / 8062 tokens ( 1.06 ms per token, 945.05 tokens per second)
llama-server | 11431.26.379.360 I slot print_timing: id 1 | task 2849944 | eval time = 36927.91 ms / 1937 tokens ( 19.07 ms per token, 52.43 tokens per second)
llama-server | 11431.26.379.360 I slot print_timing: id 1 | task 2849944 | total time = 45458.66 ms / 9999 tokens
llama-server | 11431.26.379.361 I slot print_timing: id 1 | task 2849944 | graphs reused = 2759780
llama-server | 11431.26.379.364 I slot print_timing: id 1 | task 2849944 | draft acceptance = 0.62559 ( 1467 accepted / 2345 generated), mean len = 4.13
llama-server | 11431.26.379.577 I slot release: id 1 | task 2849944 | stop processing: n_tokens = 9998, truncated = 0
llama-server | 11431.26.513.063 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.830 (> 0.100 thold), f_keep = 0.137
llama-server | 11431.26.513.969 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1035.569 MiB)
llama-server | 11431.27.330.512 I slot launch_slot_: id 0 | task 2850422 | processing task, is_child = 0
llama-server | 11431.27.331.308 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 932.445 MiB)
llama-server | 11431.31.765.043 I slot print_timing: id 0 | task 2850422 | n_gen = 188, tg = 61.33 t/s, tg_3s = 61.65 t/s
llama-server | 11431.34.808.211 I slot print_timing: id 0 | task 2850422 | n_gen = 371, tg = 60.73 t/s, tg_3s = 60.13 t/s
llama-server | 11431.37.843.283 I slot print_timing: id 0 | task 2850422 | n_gen = 530, tg = 57.96 t/s, tg_3s = 52.39 t/s
llama-server | 11431.40.875.516 I slot print_timing: id 0 | task 2850422 | n_gen = 687, tg = 56.42 t/s, tg_3s = 51.78 t/s
llama-server | 11431.43.909.524 I slot print_timing: id 0 | task 2850422 | n_gen = 821, tg = 53.97 t/s, tg_3s = 44.17 t/s
llama-server | 11431.46.948.975 I slot print_timing: id 0 | task 2850422 | n_gen = 962, tg = 52.71 t/s, tg_3s = 46.39 t/s
llama-server | 11431.49.985.528 I slot print_timing: id 0 | task 2850422 | n_gen = 1119, tg = 52.56 t/s, tg_3s = 51.70 t/s
llama-server | 11431.53.029.898 I slot print_timing: id 0 | task 2850422 | n_gen = 1299, tg = 53.38 t/s, tg_3s = 59.13 t/s
llama-server | 11431.56.082.503 I slot print_timing: id 0 | task 2850422 | n_gen = 1520, tg = 55.51 t/s, tg_3s = 72.40 t/s
llama-server | 11431.56.516.271 W srv stop: cancel task, id_task = 2850422
llama-server | 11431.56.518.613 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 685902219629
llama-server | 11431.56.519.040 I slot launch_slot_: id 1 | task 2850809 | processing task, is_child = 0
llama-server | 11431.56.519.044 I slot release: id 0 | task 2850422 | stop processing: n_tokens = 3104, truncated = 0
llama-server | 11432.01.544.250 I slot print_timing: id 1 | task 2850809 | n_gen = 179, tg = 59.08 t/s, tg_3s = 59.40 t/s
llama-server | 11432.04.555.348 I slot print_timing: id 1 | task 2850809 | n_gen = 349, tg = 57.77 t/s, tg_3s = 56.46 t/s
llama-server | 11432.07.561.927 I slot print_timing: id 1 | task 2850809 | n_gen = 496, tg = 54.81 t/s, tg_3s = 48.89 t/s
llama-server | 11432.10.568.927 I slot print_timing: id 1 | task 2850809 | n_gen = 641, tg = 53.17 t/s, tg_3s = 48.22 t/s
llama-server | 11432.13.596.174 I slot print_timing: id 1 | task 2850809 | n_gen = 805, tg = 53.37 t/s, tg_3s = 54.17 t/s
llama-server | 11432.16.599.292 I slot print_timing: id 1 | task 2850809 | n_gen = 959, tg = 53.02 t/s, tg_3s = 51.28 t/s
llama-server | 11432.19.634.823 I slot print_timing: id 1 | task 2850809 | n_gen = 1137, tg = 53.83 t/s, tg_3s = 58.64 t/s
llama-server | 11432.22.665.406 I slot print_timing: id 1 | task 2850809 | n_gen = 1282, tg = 53.08 t/s, tg_3s = 47.85 t/s
llama-server | 11432.25.682.869 I slot print_timing: id 1 | task 2850809 | n_gen = 1420, tg = 52.26 t/s, tg_3s = 45.73 t/s
llama-server | 11432.28.718.240 I slot print_timing: id 1 | task 2850809 | n_gen = 1562, tg = 51.71 t/s, tg_3s = 46.78 t/s
llama-server | 11432.31.766.363 I slot print_timing: id 1 | task 2850809 | n_gen = 1757, tg = 52.84 t/s, tg_3s = 63.97 t/s
llama-server | 11432.34.784.305 I slot print_timing: id 1 | task 2850809 | n_gen = 1908, tg = 52.60 t/s, tg_3s = 50.03 t/s
llama-server | 11432.37.819.991 I slot print_timing: id 1 | task 2850809 | n_gen = 2057, tg = 52.33 t/s, tg_3s = 49.08 t/s
llama-server | 11432.40.849.839 I slot print_timing: id 1 | task 2850809 | n_gen = 2225, tg = 52.55 t/s, tg_3s = 55.45 t/s
llama-server | 11432.43.892.270 I slot print_timing: id 1 | task 2850809 | n_gen = 2369, tg = 52.20 t/s, tg_3s = 47.33 t/s
llama-server | 11432.46.943.806 I slot print_timing: id 1 | task 2850809 | n_gen = 2522, tg = 52.07 t/s, tg_3s = 50.14 t/s
llama-server | 11432.49.998.770 I slot print_timing: id 1 | task 2850809 | n_gen = 2714, tg = 52.71 t/s, tg_3s = 62.85 t/s
llama-server | 11432.53.055.360 I slot print_timing: id 1 | task 2850809 | n_gen = 2880, tg = 52.80 t/s, tg_3s = 54.31 t/s
llama-server | 11432.56.107.816 I slot print_timing: id 1 | task 2850809 | n_gen = 3031, tg = 52.63 t/s, tg_3s = 49.47 t/s
llama-server | 11432.59.161.520 I slot print_timing: id 1 | task 2850809 | n_gen = 3252, tg = 53.62 t/s, tg_3s = 72.37 t/s
llama-server | 11433.00.891.198 I slot print_timing: id 1 | task 2850809 | prompt eval time = 2011.94 ms / 1562 tokens ( 1.29 ms per token, 776.37 tokens per second)
llama-server | 11433.00.891.201 I slot print_timing: id 1 | task 2850809 | eval time = 62359.94 ms / 3387 tokens ( 18.42 ms per token, 54.30 tokens per second)
llama-server | 11433.00.891.202 I slot print_timing: id 1 | task 2850809 | total time = 64371.88 ms / 4949 tokens
llama-server | 11433.00.891.203 I slot print_timing: id 1 | task 2850809 | graphs reused = 2760992
llama-server | 11433.00.891.205 I slot print_timing: id 1 | task 2850809 | draft acceptance = 0.60332 ( 2543 accepted / 4215 generated), mean len = 4.02
llama-server | 11433.00.891.295 I slot release: id 1 | task 2850809 | stop processing: n_tokens = 4948, truncated = 0
llama-server | 11433.05.862.574 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.189 (> 0.100 thold), f_keep = 0.418
llama-server | 11433.05.863.118 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 944.733 MiB)
llama-server | 11433.06.288.300 I slot launch_slot_: id 0 | task 2851658 | processing task, is_child = 0
llama-server | 11433.06.288.807 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 967.941 MiB)
llama-server | 11433.10.756.288 I slot print_timing: id 0 | task 2851658 | prompt processing, n_tokens = 4096, progress = 0.78, t = 3.29 s / 1245.33 tokens per second
llama-server | 11433.11.681.645 I slot print_timing: id 0 | task 2851658 | prompt processing, n_tokens = 5060, progress = 0.92, t = 4.35 s / 1163.29 tokens per second
llama-server | 11433.12.268.817 I slot print_timing: id 0 | task 2851658 | prompt processing, n_tokens = 5572, progress = 1.00, t = 4.97 s / 1120.07 tokens per second
llama-server | 11433.15.520.270 I slot print_timing: id 0 | task 2851658 | n_gen = 193, tg = 63.06 t/s, tg_3s = 63.38 t/s
llama-server | 11433.18.547.120 I slot print_timing: id 0 | task 2851658 | n_gen = 361, tg = 59.29 t/s, tg_3s = 55.50 t/s
llama-server | 11433.21.566.048 I slot print_timing: id 0 | task 2851658 | n_gen = 520, tg = 57.09 t/s, tg_3s = 52.67 t/s
llama-server | 11433.24.626.813 I slot print_timing: id 0 | task 2851658 | n_gen = 710, tg = 58.35 t/s, tg_3s = 62.08 t/s
llama-server | 11433.27.678.419 I slot print_timing: id 0 | task 2851658 | n_gen = 870, tg = 57.16 t/s, tg_3s = 52.43 t/s
llama-server | 11433.30.747.975 I slot print_timing: id 0 | task 2851658 | n_gen = 1079, tg = 59.00 t/s, tg_3s = 68.09 t/s
llama-server | 11433.33.804.584 I slot print_timing: id 0 | task 2851658 | n_gen = 1280, tg = 59.96 t/s, tg_3s = 65.76 t/s
llama-server | 11433.35.865.239 W srv stop: cancel task, id_task = 2851658
llama-server | 11433.35.916.775 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 685996731348
llama-server | 11433.35.961.822 I slot launch_slot_: id 1 | task 2851979 | processing task, is_child = 0
llama-server | 11433.35.961.828 I slot release: id 0 | task 2851658 | stop processing: n_tokens = 8308, truncated = 0
llama-server | 11433.40.169.714 I slot print_timing: id 1 | task 2851979 | prompt processing, n_tokens = 4096, progress = 0.78, t = 3.55 s / 1153.74 tokens per second
llama-server | 11433.41.169.893 I slot print_timing: id 1 | task 2851979 | prompt processing, n_tokens = 5060, progress = 0.92, t = 4.68 s / 1080.47 tokens per second
llama-server | 11433.41.826.510 I slot print_timing: id 1 | task 2851979 | prompt processing, n_tokens = 5572, progress = 1.00, t = 5.37 s / 1037.25 tokens per second
llama-server | 11433.45.024.900 I slot print_timing: id 1 | task 2851979 | n_gen = 163, tg = 53.71 t/s, tg_3s = 54.04 t/s
llama-server | 11433.48.040.170 I slot print_timing: id 1 | task 2851979 | n_gen = 316, tg = 52.23 t/s, tg_3s = 50.74 t/s
llama-server | 11433.51.053.743 I slot print_timing: id 1 | task 2851979 | n_gen = 455, tg = 50.19 t/s, tg_3s = 46.12 t/s
llama-server | 11433.54.065.265 I slot print_timing: id 1 | task 2851979 | n_gen = 584, tg = 48.36 t/s, tg_3s = 42.84 t/s
llama-server | 11433.57.082.500 I slot print_timing: id 1 | task 2851979 | n_gen = 719, tg = 47.63 t/s, tg_3s = 44.74 t/s
llama-server | 11434.00.099.344 I slot print_timing: id 1 | task 2851979 | n_gen = 885, tg = 48.87 t/s, tg_3s = 55.02 t/s
llama-server | 11434.03.139.849 I slot print_timing: id 1 | task 2851979 | n_gen = 1061, tg = 50.16 t/s, tg_3s = 57.89 t/s
llama-server | 11434.06.181.046 I slot print_timing: id 1 | task 2851979 | n_gen = 1232, tg = 50.93 t/s, tg_3s = 56.23 t/s
llama-server | 11434.09.219.729 I slot print_timing: id 1 | task 2851979 | n_gen = 1457, tg = 53.51 t/s, tg_3s = 74.05 t/s
llama-server | 11434.12.278.881 I slot print_timing: id 1 | task 2851979 | n_gen = 1691, tg = 55.83 t/s, tg_3s = 76.49 t/s
llama-server | 11434.12.749.287 I slot print_timing: id 1 | task 2851979 | prompt eval time = 6046.74 ms / 5576 tokens ( 1.08 ms per token, 922.15 tokens per second)
llama-server | 11434.12.749.291 I slot print_timing: id 1 | task 2851979 | eval time = 30740.44 ms / 1723 tokens ( 17.85 ms per token, 56.02 tokens per second)
llama-server | 11434.12.749.292 I slot print_timing: id 1 | task 2851979 | total time = 36787.18 ms / 7299 tokens
llama-server | 11434.12.749.293 I slot print_timing: id 1 | task 2851979 | graphs reused = 2761692
llama-server | 11434.12.749.296 I slot print_timing: id 1 | task 2851979 | draft acceptance = 0.66970 ( 1326 accepted / 1980 generated), mean len = 4.35
llama-server | 11434.12.749.502 I slot release: id 1 | task 2851979 | stop processing: n_tokens = 8590, truncated = 0
llama-server | 11434.12.860.526 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.829 (> 0.100 thold), f_keep = 0.156
llama-server | 11434.13.602.549 I slot launch_slot_: id 0 | task 2852382 | processing task, is_child = 0
llama-server | 11434.17.787.849 I slot print_timing: id 0 | task 2852382 | n_gen = 202, tg = 66.80 t/s, tg_3s = 67.12 t/s
llama-server | 11434.20.805.033 I slot print_timing: id 0 | task 2852382 | n_gen = 420, tg = 69.53 t/s, tg_3s = 72.25 t/s
llama-server | 11434.22.685.695 I slot print_timing: id 0 | task 2852382 | prompt eval time = 621.81 ms / 272 tokens ( 2.29 ms per token, 437.43 tokens per second)
llama-server | 11434.22.685.698 I slot print_timing: id 0 | task 2852382 | eval time = 7907.03 ms / 575 tokens ( 13.78 ms per token, 72.59 tokens per second)
llama-server | 11434.22.685.699 I slot print_timing: id 0 | task 2852382 | total time = 8528.84 ms / 847 tokens
llama-server | 11434.22.685.699 I slot print_timing: id 0 | task 2852382 | graphs reused = 2761799
llama-server | 11434.22.685.702 I slot print_timing: id 0 | task 2852382 | draft acceptance = 0.84364 ( 464 accepted / 550 generated), mean len = 5.22
llama-server | 11434.22.685.786 I slot release: id 0 | task 2852382 | stop processing: n_tokens = 2138, truncated = 0
llama-server | 11434.31.088.273 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.607
llama-server | 11434.31.089.006 I slot launch_slot_: id 0 | task 2852495 | processing task, is_child = 0
llama-server | 11434.34.950.386 I slot print_timing: id 0 | task 2852495 | prompt processing, n_tokens = 4096, progress = 0.67, t = 3.22 s / 1272.39 tokens per second
llama-server | 11434.36.856.845 I slot print_timing: id 0 | task 2852495 | prompt processing, n_tokens = 6144, progress = 0.92, t = 5.14 s / 1195.40 tokens per second
llama-server | 11434.37.030.008 I slot print_timing: id 0 | task 2852495 | prompt processing, n_tokens = 6260, progress = 0.94, t = 5.79 s / 1080.50 tokens per second
llama-server | 11434.37.631.862 I slot print_timing: id 0 | task 2852495 | prompt processing, n_tokens = 6772, progress = 1.00, t = 6.08 s / 1112.99 tokens per second
llama-server | 11434.40.846.676 I slot print_timing: id 0 | task 2852495 | n_gen = 154, tg = 50.40 t/s, tg_3s = 50.73 t/s
llama-server | 11434.43.853.916 I slot print_timing: id 0 | task 2852495 | n_gen = 318, tg = 52.46 t/s, tg_3s = 54.54 t/s
llama-server | 11434.46.883.939 I slot print_timing: id 0 | task 2852495 | n_gen = 477, tg = 52.46 t/s, tg_3s = 52.47 t/s
llama-server | 11434.49.897.687 I slot print_timing: id 0 | task 2852495 | n_gen = 623, tg = 51.46 t/s, tg_3s = 48.44 t/s
llama-server | 11434.52.945.650 I slot print_timing: id 0 | task 2852495 | n_gen = 773, tg = 51.01 t/s, tg_3s = 49.21 t/s
llama-server | 11434.55.998.850 I slot print_timing: id 0 | task 2852495 | n_gen = 949, tg = 52.12 t/s, tg_3s = 57.64 t/s
llama-server | 11434.59.037.353 I slot print_timing: id 0 | task 2852495 | n_gen = 1115, tg = 52.48 t/s, tg_3s = 54.63 t/s
llama-server | 11435.01.091.902 W srv stop: cancel task, id_task = 2852495
llama-server | 11435.01.138.719 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686068589554
llama-server | 11435.01.139.212 I slot launch_slot_: id 1 | task 2852817 | processing task, is_child = 0
llama-server | 11435.01.139.214 I slot release: id 0 | task 2852495 | stop processing: n_tokens = 9299, truncated = 0
llama-server | 11435.06.595.375 I slot print_timing: id 1 | task 2852817 | prompt processing, n_tokens = 5388, progress = 0.67, t = 4.79 s / 1123.88 tokens per second
llama-server | 11435.08.686.061 I slot print_timing: id 1 | task 2852817 | prompt processing, n_tokens = 7436, progress = 0.92, t = 6.88 s / 1081.50 tokens per second
llama-server | 11435.08.859.958 I slot print_timing: id 1 | task 2852817 | prompt processing, n_tokens = 7552, progress = 0.94, t = 7.56 s / 999.43 tokens per second
llama-server | 11435.09.511.474 I slot print_timing: id 1 | task 2852817 | prompt processing, n_tokens = 8064, progress = 1.00, t = 7.87 s / 1024.66 tokens per second
llama-server | 11435.12.716.892 I slot print_timing: id 1 | task 2852817 | n_gen = 169, tg = 54.72 t/s, tg_3s = 55.04 t/s
llama-server | 11435.15.774.503 I slot print_timing: id 1 | task 2852817 | n_gen = 350, tg = 56.96 t/s, tg_3s = 59.20 t/s
llama-server | 11435.18.822.482 I slot print_timing: id 1 | task 2852817 | n_gen = 502, tg = 54.60 t/s, tg_3s = 49.87 t/s
llama-server | 11435.21.880.001 I slot print_timing: id 1 | task 2852817 | n_gen = 638, tg = 52.07 t/s, tg_3s = 44.48 t/s
llama-server | 11435.24.952.183 I slot print_timing: id 1 | task 2852817 | n_gen = 838, tg = 54.69 t/s, tg_3s = 65.10 t/s
llama-server | 11435.28.013.033 I slot print_timing: id 1 | task 2852817 | n_gen = 1008, tg = 54.83 t/s, tg_3s = 55.54 t/s
llama-server | 11435.31.017.699 I slot print_timing: id 1 | task 2852817 | n_gen = 1208, tg = 56.48 t/s, tg_3s = 66.56 t/s
llama-server | 11435.34.029.238 I slot print_timing: id 1 | task 2852817 | n_gen = 1432, tg = 58.69 t/s, tg_3s = 74.38 t/s
llama-server | 11435.35.923.260 I slot print_timing: id 1 | task 2852817 | prompt eval time = 8507.42 ms / 8068 tokens ( 1.05 ms per token, 948.35 tokens per second)
llama-server | 11435.35.923.264 I slot print_timing: id 1 | task 2852817 | eval time = 26276.34 ms / 1576 tokens ( 16.68 ms per token, 59.94 tokens per second)
llama-server | 11435.35.923.265 I slot print_timing: id 1 | task 2852817 | total time = 34783.76 ms / 9644 tokens
llama-server | 11435.35.923.266 I slot print_timing: id 1 | task 2852817 | graphs reused = 2762435
llama-server | 11435.35.923.270 I slot print_timing: id 1 | task 2852817 | draft acceptance = 0.74311 ( 1241 accepted / 1670 generated), mean len = 4.72
llama-server | 11435.35.923.498 I slot release: id 1 | task 2852817 | stop processing: n_tokens = 9643, truncated = 0
llama-server | 11435.36.032.928 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.830 (> 0.100 thold), f_keep = 0.139
llama-server | 11435.36.034.063 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 965.494 MiB)
llama-server | 11435.36.102.679 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 977.982 MiB)
llama-server | 11435.36.793.800 I slot launch_slot_: id 0 | task 2853160 | processing task, is_child = 0
llama-server | 11435.36.794.553 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 994.521 MiB)
llama-server | 11435.41.065.322 I slot print_timing: id 0 | task 2853160 | n_gen = 213, tg = 70.54 t/s, tg_3s = 70.87 t/s
llama-server | 11435.44.078.371 I slot print_timing: id 0 | task 2853160 | n_gen = 433, tg = 71.78 t/s, tg_3s = 73.02 t/s
llama-server | 11435.47.102.959 I slot print_timing: id 0 | task 2853160 | n_gen = 685, tg = 75.64 t/s, tg_3s = 83.32 t/s
llama-server | 11435.47.388.321 I slot print_timing: id 0 | task 2853160 | prompt eval time = 601.63 ms / 270 tokens ( 2.23 ms per token, 448.78 tokens per second)
llama-server | 11435.47.388.324 I slot print_timing: id 0 | task 2853160 | eval time = 9328.42 ms / 707 tokens ( 13.21 ms per token, 75.68 tokens per second)
llama-server | 11435.47.388.325 I slot print_timing: id 0 | task 2853160 | total time = 9930.05 ms / 977 tokens
llama-server | 11435.47.388.326 I slot print_timing: id 0 | task 2853160 | graphs reused = 2762562
llama-server | 11435.47.388.328 I slot print_timing: id 0 | task 2853160 | draft acceptance = 0.88615 ( 576 accepted / 650 generated), mean len = 5.43
llama-server | 11435.47.388.416 I slot release: id 0 | task 2853160 | stop processing: n_tokens = 2268, truncated = 0
llama-server | 11435.56.101.735 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.255 (> 0.100 thold), f_keep = 0.572
llama-server | 11435.56.102.595 I slot launch_slot_: id 0 | task 2853293 | processing task, is_child = 0
llama-server | 11435.59.735.030 I slot print_timing: id 0 | task 2853293 | prompt processing, n_tokens = 3781, progress = 1.00, t = 3.19 s / 1183.71 tokens per second
llama-server | 11436.02.996.605 I slot print_timing: id 0 | task 2853293 | n_gen = 178, tg = 57.78 t/s, tg_3s = 58.11 t/s
llama-server | 11436.06.042.139 I slot print_timing: id 0 | task 2853293 | n_gen = 333, tg = 54.35 t/s, tg_3s = 50.89 t/s
llama-server | 11436.09.085.961 I slot print_timing: id 0 | task 2853293 | n_gen = 522, tg = 56.92 t/s, tg_3s = 62.09 t/s
llama-server | 11436.12.156.049 I slot print_timing: id 0 | task 2853293 | n_gen = 702, tg = 57.35 t/s, tg_3s = 58.63 t/s
llama-server | 11436.15.225.469 I slot print_timing: id 0 | task 2853293 | n_gen = 874, tg = 57.09 t/s, tg_3s = 56.04 t/s
llama-server | 11436.18.237.116 I slot print_timing: id 0 | task 2853293 | n_gen = 1087, tg = 59.33 t/s, tg_3s = 70.73 t/s
llama-server | 11436.21.241.140 I slot print_timing: id 0 | task 2853293 | n_gen = 1280, tg = 60.03 t/s, tg_3s = 64.25 t/s
llama-server | 11436.24.258.683 I slot print_timing: id 0 | task 2853293 | n_gen = 1450, tg = 59.57 t/s, tg_3s = 56.34 t/s
llama-server | 11436.26.104.845 W srv stop: cancel task, id_task = 2853293
llama-server | 11436.26.112.021 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686151763550
llama-server | 11436.26.112.371 I slot launch_slot_: id 1 | task 2853656 | processing task, is_child = 0
llama-server | 11436.26.112.374 I slot release: id 0 | task 2853293 | stop processing: n_tokens = 6675, truncated = 0
llama-server | 11436.30.558.394 I slot print_timing: id 1 | task 2853656 | prompt processing, n_tokens = 4561, progress = 0.90, t = 4.15 s / 1100.05 tokens per second
llama-server | 11436.31.169.114 I slot print_timing: id 1 | task 2853656 | prompt processing, n_tokens = 5073, progress = 1.00, t = 4.58 s / 1107.74 tokens per second
llama-server | 11436.34.425.892 I slot print_timing: id 1 | task 2853656 | n_gen = 179, tg = 58.39 t/s, tg_3s = 58.71 t/s
llama-server | 11436.37.457.613 I slot print_timing: id 1 | task 2853656 | n_gen = 325, tg = 53.29 t/s, tg_3s = 48.16 t/s
llama-server | 11436.40.483.866 I slot print_timing: id 1 | task 2853656 | n_gen = 497, tg = 54.47 t/s, tg_3s = 56.84 t/s
llama-server | 11436.43.527.398 I slot print_timing: id 1 | task 2853656 | n_gen = 674, tg = 55.39 t/s, tg_3s = 58.16 t/s
llama-server | 11436.46.578.399 I slot print_timing: id 1 | task 2853656 | n_gen = 854, tg = 56.11 t/s, tg_3s = 59.00 t/s
llama-server | 11436.49.634.217 I slot print_timing: id 1 | task 2853656 | n_gen = 1063, tg = 58.17 t/s, tg_3s = 68.39 t/s
llama-server | 11436.52.677.582 I slot print_timing: id 1 | task 2853656 | n_gen = 1223, tg = 57.37 t/s, tg_3s = 52.57 t/s
llama-server | 11436.55.744.857 I slot print_timing: id 1 | task 2853656 | n_gen = 1461, tg = 59.92 t/s, tg_3s = 77.59 t/s
llama-server | 11436.56.661.709 I slot print_timing: id 1 | task 2853656 | prompt eval time = 5264.76 ms / 5077 tokens ( 1.04 ms per token, 964.34 tokens per second)
llama-server | 11436.56.661.713 I slot print_timing: id 1 | task 2853656 | eval time = 25284.32 ms / 1532 tokens ( 16.51 ms per token, 60.55 tokens per second)
llama-server | 11436.56.661.713 I slot print_timing: id 1 | task 2853656 | total time = 30549.08 ms / 6609 tokens
llama-server | 11436.56.661.714 I slot print_timing: id 1 | task 2853656 | graphs reused = 2763237
llama-server | 11436.56.661.717 I slot print_timing: id 1 | task 2853656 | draft acceptance = 0.72289 ( 1200 accepted / 1660 generated), mean len = 4.61
llama-server | 11436.56.661.888 I slot release: id 1 | task 2853656 | stop processing: n_tokens = 6609, truncated = 0
llama-server | 11436.56.780.983 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.829 (> 0.100 thold), f_keep = 0.194
llama-server | 11436.56.781.731 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1020.142 MiB)
llama-server | 11436.57.430.379 I slot launch_slot_: id 0 | task 2853995 | processing task, is_child = 0
llama-server | 11436.57.430.964 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1058.758 MiB)
llama-server | 11437.01.789.969 I slot print_timing: id 0 | task 2853995 | n_gen = 185, tg = 61.17 t/s, tg_3s = 61.49 t/s
llama-server | 11437.04.798.980 I slot print_timing: id 0 | task 2853995 | n_gen = 378, tg = 62.65 t/s, tg_3s = 64.14 t/s
llama-server | 11437.07.822.725 I slot print_timing: id 0 | task 2853995 | n_gen = 612, tg = 67.58 t/s, tg_3s = 77.39 t/s
llama-server | 11437.09.704.631 I slot print_timing: id 0 | task 2853995 | prompt eval time = 623.17 ms / 273 tokens ( 2.28 ms per token, 438.08 tokens per second)
llama-server | 11437.09.704.634 I slot print_timing: id 0 | task 2853995 | eval time = 10922.80 ms / 763 tokens ( 14.33 ms per token, 69.76 tokens per second)
llama-server | 11437.09.704.635 I slot print_timing: id 0 | task 2853995 | total time = 11545.97 ms / 1036 tokens
llama-server | 11437.09.704.635 I slot print_timing: id 0 | task 2853995 | graphs reused = 2763385
llama-server | 11437.09.704.638 I slot print_timing: id 0 | task 2853995 | draft acceptance = 0.80263 ( 610 accepted / 760 generated), mean len = 5.01
llama-server | 11437.09.704.732 I slot release: id 0 | task 2853995 | stop processing: n_tokens = 2327, truncated = 0
llama-server | 11437.16.351.533 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.249 (> 0.100 thold), f_keep = 0.557
llama-server | 11437.16.352.229 I slot launch_slot_: id 0 | task 2854150 | processing task, is_child = 0
llama-server | 11437.20.089.247 I slot print_timing: id 0 | task 2854150 | prompt processing, n_tokens = 3923, progress = 1.00, t = 3.29 s / 1194.18 tokens per second
llama-server | 11437.23.315.931 I slot print_timing: id 0 | task 2854150 | n_gen = 190, tg = 62.95 t/s, tg_3s = 63.28 t/s
llama-server | 11437.26.347.070 I slot print_timing: id 0 | task 2854150 | n_gen = 351, tg = 58.01 t/s, tg_3s = 53.12 t/s
llama-server | 11437.29.415.504 I slot print_timing: id 0 | task 2854150 | n_gen = 508, tg = 55.70 t/s, tg_3s = 51.17 t/s
llama-server | 11437.32.472.052 I slot print_timing: id 0 | task 2854150 | n_gen = 657, tg = 53.95 t/s, tg_3s = 48.75 t/s
llama-server | 11437.35.536.945 I slot print_timing: id 0 | task 2854150 | n_gen = 806, tg = 52.88 t/s, tg_3s = 48.62 t/s
llama-server | 11437.38.549.033 I slot print_timing: id 0 | task 2854150 | n_gen = 1018, tg = 55.77 t/s, tg_3s = 70.38 t/s
llama-server | 11437.41.618.319 I slot print_timing: id 0 | task 2854150 | n_gen = 1188, tg = 55.72 t/s, tg_3s = 55.39 t/s
llama-server | 11437.44.635.926 I slot print_timing: id 0 | task 2854150 | n_gen = 1371, tg = 56.33 t/s, tg_3s = 60.64 t/s
llama-server | 11437.46.354.541 W srv stop: cancel task, id_task = 2854150
llama-server | 11437.46.416.881 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686232501940
llama-server | 11437.46.417.313 I slot launch_slot_: id 1 | task 2854512 | processing task, is_child = 0
llama-server | 11437.46.417.316 I slot release: id 0 | task 2854150 | stop processing: n_tokens = 6714, truncated = 0
llama-server | 11437.51.049.001 I slot print_timing: id 1 | task 2854512 | prompt processing, n_tokens = 4703, progress = 0.90, t = 4.20 s / 1119.66 tokens per second
llama-server | 11437.51.716.065 I slot print_timing: id 1 | task 2854512 | prompt processing, n_tokens = 5215, progress = 1.00, t = 4.82 s / 1082.90 tokens per second
llama-server | 11437.54.949.894 I slot print_timing: id 1 | task 2854512 | n_gen = 176, tg = 57.29 t/s, tg_3s = 57.62 t/s
llama-server | 11437.57.968.524 I slot print_timing: id 1 | task 2854512 | n_gen = 342, tg = 56.15 t/s, tg_3s = 54.99 t/s
llama-server | 11438.01.007.072 I slot print_timing: id 1 | task 2854512 | n_gen = 483, tg = 52.90 t/s, tg_3s = 46.40 t/s
llama-server | 11438.04.032.889 I slot print_timing: id 1 | task 2854512 | n_gen = 613, tg = 50.42 t/s, tg_3s = 42.96 t/s
llama-server | 11438.07.069.733 I slot print_timing: id 1 | task 2854512 | n_gen = 743, tg = 48.90 t/s, tg_3s = 42.81 t/s
llama-server | 11438.10.109.670 I slot print_timing: id 1 | task 2854512 | n_gen = 880, tg = 48.26 t/s, tg_3s = 45.07 t/s
llama-server | 11438.13.148.009 I slot print_timing: id 1 | task 2854512 | n_gen = 1051, tg = 49.41 t/s, tg_3s = 56.28 t/s
llama-server | 11438.16.212.818 I slot print_timing: id 1 | task 2854512 | n_gen = 1238, tg = 50.87 t/s, tg_3s = 61.02 t/s
llama-server | 11438.19.281.282 I slot print_timing: id 1 | task 2854512 | n_gen = 1419, tg = 51.78 t/s, tg_3s = 58.99 t/s
llama-server | 11438.22.327.337 I slot print_timing: id 1 | task 2854512 | n_gen = 1549, tg = 50.87 t/s, tg_3s = 42.68 t/s
llama-server | 11438.25.399.899 I slot print_timing: id 1 | task 2854512 | n_gen = 1708, tg = 50.95 t/s, tg_3s = 51.75 t/s
llama-server | 11438.28.456.651 I slot print_timing: id 1 | task 2854512 | n_gen = 1886, tg = 51.56 t/s, tg_3s = 58.23 t/s
llama-server | 11438.31.462.736 I slot print_timing: id 1 | task 2854512 | n_gen = 2077, tg = 52.47 t/s, tg_3s = 63.54 t/s
llama-server | 11438.34.475.707 I slot print_timing: id 1 | task 2854512 | n_gen = 2293, tg = 53.83 t/s, tg_3s = 71.69 t/s
llama-server | 11438.37.109.664 I slot print_timing: id 1 | task 2854512 | prompt eval time = 5477.87 ms / 5219 tokens ( 1.05 ms per token, 952.74 tokens per second)
llama-server | 11438.37.109.668 I slot print_timing: id 1 | task 2854512 | eval time = 45214.22 ms / 2493 tokens ( 18.14 ms per token, 55.12 tokens per second)
llama-server | 11438.37.109.668 I slot print_timing: id 1 | task 2854512 | total time = 50692.09 ms / 7712 tokens
llama-server | 11438.37.109.669 I slot print_timing: id 1 | task 2854512 | graphs reused = 2764316
llama-server | 11438.37.109.672 I slot print_timing: id 1 | task 2854512 | draft acceptance = 0.64189 ( 1900 accepted / 2960 generated), mean len = 4.21
llama-server | 11438.37.109.863 I slot release: id 1 | task 2854512 | stop processing: n_tokens = 7711, truncated = 0
llama-server | 11438.37.234.038 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.829 (> 0.100 thold), f_keep = 0.193
llama-server | 11438.37.234.890 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1076.333 MiB)
llama-server | 11438.37.996.248 I slot launch_slot_: id 0 | task 2855111 | processing task, is_child = 0
llama-server | 11438.37.997.543 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1020.122 MiB)
llama-server | 11438.42.375.977 I slot print_timing: id 0 | task 2855111 | n_gen = 168, tg = 55.61 t/s, tg_3s = 55.94 t/s
llama-server | 11438.45.390.618 I slot print_timing: id 0 | task 2855111 | n_gen = 365, tg = 60.49 t/s, tg_3s = 65.35 t/s
llama-server | 11438.47.629.503 I slot print_timing: id 0 | task 2855111 | prompt eval time = 589.11 ms / 273 tokens ( 2.16 ms per token, 463.41 tokens per second)
llama-server | 11438.47.629.507 I slot print_timing: id 0 | task 2855111 | eval time = 8256.52 ms / 550 tokens ( 15.04 ms per token, 66.49 tokens per second)
llama-server | 11438.47.629.508 I slot print_timing: id 0 | task 2855111 | total time = 8845.63 ms / 823 tokens
llama-server | 11438.47.629.509 I slot print_timing: id 0 | task 2855111 | graphs reused = 2764428
llama-server | 11438.47.629.512 I slot print_timing: id 0 | task 2855111 | draft acceptance = 0.75652 ( 435 accepted / 575 generated), mean len = 4.78
llama-server | 11438.47.629.614 I slot release: id 0 | task 2855111 | stop processing: n_tokens = 2115, truncated = 0
llama-server | 11438.56.493.555 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.249 (> 0.100 thold), f_keep = 0.613
llama-server | 11438.56.494.433 I slot launch_slot_: id 0 | task 2855229 | processing task, is_child = 0
llama-server | 11439.00.301.346 I slot print_timing: id 0 | task 2855229 | prompt processing, n_tokens = 3904, progress = 1.00, t = 3.36 s / 1160.54 tokens per second
llama-server | 11439.03.567.280 I slot print_timing: id 0 | task 2855229 | n_gen = 154, tg = 50.31 t/s, tg_3s = 50.63 t/s
llama-server | 11439.06.615.227 I slot print_timing: id 0 | task 2855229 | n_gen = 323, tg = 52.88 t/s, tg_3s = 55.45 t/s
llama-server | 11439.09.667.088 I slot print_timing: id 0 | task 2855229 | n_gen = 481, tg = 52.51 t/s, tg_3s = 51.77 t/s
llama-server | 11439.12.712.816 I slot print_timing: id 0 | task 2855229 | n_gen = 630, tg = 51.61 t/s, tg_3s = 48.92 t/s
llama-server | 11439.15.774.790 I slot print_timing: id 0 | task 2855229 | n_gen = 772, tg = 50.56 t/s, tg_3s = 46.38 t/s
llama-server | 11439.18.827.473 I slot print_timing: id 0 | task 2855229 | n_gen = 907, tg = 49.50 t/s, tg_3s = 44.22 t/s
llama-server | 11439.21.841.978 I slot print_timing: id 0 | task 2855229 | n_gen = 1078, tg = 50.53 t/s, tg_3s = 56.73 t/s
llama-server | 11439.24.859.293 I slot print_timing: id 0 | task 2855229 | n_gen = 1260, tg = 51.74 t/s, tg_3s = 60.32 t/s
llama-server | 11439.26.495.833 W srv stop: cancel task, id_task = 2855229
llama-server | 11439.26.542.118 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686332949915
llama-server | 11439.26.542.586 I slot launch_slot_: id 1 | task 2855591 | processing task, is_child = 0
llama-server | 11439.26.542.592 I slot release: id 0 | task 2855229 | stop processing: n_tokens = 6550, truncated = 0
llama-server | 11439.31.210.171 I slot print_timing: id 1 | task 2855591 | prompt processing, n_tokens = 4684, progress = 0.90, t = 4.23 s / 1106.17 tokens per second
llama-server | 11439.31.863.726 I slot print_timing: id 1 | task 2855591 | prompt processing, n_tokens = 5196, progress = 1.00, t = 4.85 s / 1072.17 tokens per second
llama-server | 11439.35.105.292 I slot print_timing: id 1 | task 2855591 | n_gen = 146, tg = 47.63 t/s, tg_3s = 47.96 t/s
llama-server | 11439.38.142.433 I slot print_timing: id 1 | task 2855591 | n_gen = 312, tg = 51.14 t/s, tg_3s = 54.66 t/s
llama-server | 11439.41.162.730 I slot print_timing: id 1 | task 2855591 | n_gen = 477, tg = 52.30 t/s, tg_3s = 54.63 t/s
llama-server | 11439.44.206.749 I slot print_timing: id 1 | task 2855591 | n_gen = 620, tg = 50.97 t/s, tg_3s = 46.98 t/s
llama-server | 11439.47.240.597 I slot print_timing: id 1 | task 2855591 | n_gen = 774, tg = 50.92 t/s, tg_3s = 50.76 t/s
llama-server | 11439.50.293.466 I slot print_timing: id 1 | task 2855591 | n_gen = 933, tg = 51.12 t/s, tg_3s = 52.08 t/s
llama-server | 11439.53.358.960 I slot print_timing: id 1 | task 2855591 | n_gen = 1144, tg = 53.67 t/s, tg_3s = 68.83 t/s
llama-server | 11439.56.432.463 I slot print_timing: id 1 | task 2855591 | n_gen = 1382, tg = 56.67 t/s, tg_3s = 77.44 t/s
llama-server | 11439.57.043.870 I slot print_timing: id 1 | task 2855591 | prompt eval time = 5518.38 ms / 5200 tokens ( 1.06 ms per token, 942.31 tokens per second)
llama-server | 11439.57.043.874 I slot print_timing: id 1 | task 2855591 | eval time = 24982.62 ms / 1427 tokens ( 17.52 ms per token, 57.08 tokens per second)
llama-server | 11439.57.043.875 I slot print_timing: id 1 | task 2855591 | total time = 30500.99 ms / 6627 tokens
llama-server | 11439.57.043.875 I slot print_timing: id 1 | task 2855591 | graphs reused = 2765100
llama-server | 11439.57.043.878 I slot print_timing: id 1 | task 2855591 | draft acceptance = 0.66951 ( 1098 accepted / 1640 generated), mean len = 4.35
llama-server | 11439.57.044.064 I slot release: id 1 | task 2855591 | stop processing: n_tokens = 6626, truncated = 0
llama-server | 11439.57.186.485 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.198
llama-server | 11439.57.187.234 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1029.499 MiB)
llama-server | 11439.57.811.333 I slot launch_slot_: id 0 | task 2855926 | processing task, is_child = 0
llama-server | 11439.57.812.136 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1223.152 MiB)
llama-server | 11440.01.998.772 I slot print_timing: id 0 | task 2855926 | n_gen = 187, tg = 61.85 t/s, tg_3s = 62.18 t/s
llama-server | 11440.05.016.985 I slot print_timing: id 0 | task 2855926 | n_gen = 437, tg = 72.36 t/s, tg_3s = 82.83 t/s
llama-server | 11440.05.301.080 I slot print_timing: id 0 | task 2855926 | prompt eval time = 536.12 ms / 259 tokens ( 2.07 ms per token, 483.11 tokens per second)
llama-server | 11440.05.301.083 I slot print_timing: id 0 | task 2855926 | eval time = 6309.67 ms / 457 tokens ( 13.84 ms per token, 72.27 tokens per second)
llama-server | 11440.05.301.083 I slot print_timing: id 0 | task 2855926 | total time = 6845.78 ms / 716 tokens
llama-server | 11440.05.301.084 I slot print_timing: id 0 | task 2855926 | graphs reused = 2765186
llama-server | 11440.05.301.087 I slot print_timing: id 0 | task 2855926 | draft acceptance = 0.83636 ( 368 accepted / 440 generated), mean len = 5.18
llama-server | 11440.05.301.175 I slot release: id 0 | task 2855926 | stop processing: n_tokens = 2007, truncated = 0
llama-server | 11440.11.618.387 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.301 (> 0.100 thold), f_keep = 0.646
llama-server | 11440.11.619.096 I slot launch_slot_: id 0 | task 2856017 | processing task, is_child = 0
llama-server | 11440.17.761.832 I slot print_timing: id 0 | task 2856017 | n_gen = 152, tg = 49.58 t/s, tg_3s = 49.90 t/s
llama-server | 11440.20.796.258 I slot print_timing: id 0 | task 2856017 | n_gen = 305, tg = 50.00 t/s, tg_3s = 50.42 t/s
llama-server | 11440.23.818.021 I slot print_timing: id 0 | task 2856017 | n_gen = 427, tg = 46.80 t/s, tg_3s = 40.37 t/s
llama-server | 11440.26.864.942 I slot print_timing: id 0 | task 2856017 | n_gen = 565, tg = 46.42 t/s, tg_3s = 45.29 t/s
llama-server | 11440.29.901.411 I slot print_timing: id 0 | task 2856017 | n_gen = 710, tg = 46.69 t/s, tg_3s = 47.75 t/s
llama-server | 11440.32.967.782 I slot print_timing: id 0 | task 2856017 | n_gen = 883, tg = 48.32 t/s, tg_3s = 56.42 t/s
llama-server | 11440.36.018.180 I slot print_timing: id 0 | task 2856017 | n_gen = 1028, tg = 48.21 t/s, tg_3s = 47.53 t/s
llama-server | 11440.39.083.729 I slot print_timing: id 0 | task 2856017 | n_gen = 1153, tg = 47.28 t/s, tg_3s = 40.78 t/s
llama-server | 11440.41.620.733 W srv stop: cancel task, id_task = 2856017
llama-server | 11440.41.629.514 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686412884116
llama-server | 11440.41.629.903 I slot launch_slot_: id 1 | task 2856393 | processing task, is_child = 0
llama-server | 11440.41.629.906 I slot release: id 0 | task 2856017 | stop processing: n_tokens = 5594, truncated = 0
llama-server | 11440.45.418.018 I slot print_timing: id 1 | task 2856393 | prompt processing, n_tokens = 3799, progress = 0.88, t = 3.32 s / 1143.86 tokens per second
llama-server | 11440.46.028.140 I slot print_timing: id 1 | task 2856393 | prompt processing, n_tokens = 4311, progress = 1.00, t = 3.93 s / 1098.19 tokens per second
llama-server | 11440.49.232.577 I slot print_timing: id 1 | task 2856393 | n_gen = 155, tg = 51.08 t/s, tg_3s = 51.40 t/s
llama-server | 11440.52.318.914 I slot print_timing: id 1 | task 2856393 | n_gen = 341, tg = 55.73 t/s, tg_3s = 60.27 t/s
llama-server | 11440.55.384.768 I slot print_timing: id 1 | task 2856393 | n_gen = 493, tg = 53.67 t/s, tg_3s = 49.58 t/s
llama-server | 11440.58.396.097 I slot print_timing: id 1 | task 2856393 | n_gen = 625, tg = 51.24 t/s, tg_3s = 43.83 t/s
llama-server | 11441.01.398.292 I slot print_timing: id 1 | task 2856393 | n_gen = 786, tg = 51.71 t/s, tg_3s = 53.63 t/s
llama-server | 11441.04.418.344 I slot print_timing: id 1 | task 2856393 | n_gen = 962, tg = 52.80 t/s, tg_3s = 58.28 t/s
llama-server | 11441.07.438.238 I slot print_timing: id 1 | task 2856393 | n_gen = 1120, tg = 52.73 t/s, tg_3s = 52.32 t/s
llama-server | 11441.10.438.824 I slot print_timing: id 1 | task 2856393 | n_gen = 1266, tg = 52.23 t/s, tg_3s = 48.66 t/s
llama-server | 11441.13.476.451 I slot print_timing: id 1 | task 2856393 | n_gen = 1429, tg = 52.39 t/s, tg_3s = 53.66 t/s
llama-server | 11441.16.494.093 I slot print_timing: id 1 | task 2856393 | n_gen = 1582, tg = 52.22 t/s, tg_3s = 50.70 t/s
llama-server | 11441.19.527.407 I slot print_timing: id 1 | task 2856393 | n_gen = 1704, tg = 51.13 t/s, tg_3s = 40.22 t/s
llama-server | 11441.22.550.529 I slot print_timing: id 1 | task 2856393 | n_gen = 1852, tg = 50.95 t/s, tg_3s = 48.96 t/s
llama-server | 11441.25.589.011 I slot print_timing: id 1 | task 2856393 | n_gen = 2000, tg = 50.77 t/s, tg_3s = 48.71 t/s
llama-server | 11441.28.637.187 I slot print_timing: id 1 | task 2856393 | n_gen = 2180, tg = 51.37 t/s, tg_3s = 59.05 t/s
llama-server | 11441.31.676.134 I slot print_timing: id 1 | task 2856393 | n_gen = 2371, tg = 52.14 t/s, tg_3s = 62.85 t/s
llama-server | 11441.34.725.542 I slot print_timing: id 1 | task 2856393 | n_gen = 2506, tg = 51.64 t/s, tg_3s = 44.27 t/s
llama-server | 11441.37.780.514 I slot print_timing: id 1 | task 2856393 | n_gen = 2667, tg = 51.70 t/s, tg_3s = 52.70 t/s
llama-server | 11441.40.818.494 I slot print_timing: id 1 | task 2856393 | n_gen = 2845, tg = 52.09 t/s, tg_3s = 58.59 t/s
llama-server | 11441.43.887.392 I slot print_timing: id 1 | task 2856393 | n_gen = 3002, tg = 52.04 t/s, tg_3s = 51.16 t/s
llama-server | 11441.46.945.728 I slot print_timing: id 1 | task 2856393 | n_gen = 3160, tg = 52.02 t/s, tg_3s = 51.66 t/s
llama-server | 11441.50.001.332 I slot print_timing: id 1 | task 2856393 | n_gen = 3398, tg = 53.26 t/s, tg_3s = 77.89 t/s
llama-server | 11441.50.784.050 I slot print_timing: id 1 | task 2856393 | prompt eval time = 4587.34 ms / 4315 tokens ( 1.06 ms per token, 940.63 tokens per second)
llama-server | 11441.50.784.053 I slot print_timing: id 1 | task 2856393 | eval time = 64566.54 ms / 3451 tokens ( 18.71 ms per token, 53.43 tokens per second)
llama-server | 11441.50.784.054 I slot print_timing: id 1 | task 2856393 | total time = 69153.88 ms / 7766 tokens
llama-server | 11441.50.784.054 I slot print_timing: id 1 | task 2856393 | graphs reused = 2766388
llama-server | 11441.50.784.057 I slot print_timing: id 1 | task 2856393 | draft acceptance = 0.60986 ( 2598 accepted / 4260 generated), mean len = 4.05
llama-server | 11441.50.784.231 I slot release: id 1 | task 2856393 | stop processing: n_tokens = 7765, truncated = 0
llama-server | 11441.50.919.112 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.830 (> 0.100 thold), f_keep = 0.232
llama-server | 11441.50.919.686 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1064.529 MiB)
llama-server | 11441.51.532.887 I slot launch_slot_: id 0 | task 2857252 | processing task, is_child = 0
llama-server | 11441.51.533.523 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1135.907 MiB)
llama-server | 11441.55.746.511 I slot print_timing: id 0 | task 2857252 | n_gen = 208, tg = 68.83 t/s, tg_3s = 69.16 t/s
llama-server | 11441.58.764.500 I slot print_timing: id 0 | task 2857252 | n_gen = 444, tg = 73.52 t/s, tg_3s = 78.20 t/s
llama-server | 11442.01.794.274 I slot print_timing: id 0 | task 2857252 | prompt eval time = 574.87 ms / 271 tokens ( 2.12 ms per token, 471.41 tokens per second)
llama-server | 11442.01.794.278 I slot print_timing: id 0 | task 2857252 | eval time = 9055.06 ms / 692 tokens ( 13.10 ms per token, 76.31 tokens per second)
llama-server | 11442.01.794.278 I slot print_timing: id 0 | task 2857252 | total time = 9629.93 ms / 963 tokens
llama-server | 11442.01.794.279 I slot print_timing: id 0 | task 2857252 | graphs reused = 2766511
llama-server | 11442.01.794.282 I slot print_timing: id 0 | task 2857252 | draft acceptance = 0.89683 ( 565 accepted / 630 generated), mean len = 5.48
llama-server | 11442.01.794.374 I slot release: id 0 | task 2857252 | stop processing: n_tokens = 2254, truncated = 0
llama-server | 11442.06.952.980 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.232 (> 0.100 thold), f_keep = 0.575
llama-server | 11442.06.953.860 I slot launch_slot_: id 0 | task 2857381 | processing task, is_child = 0
llama-server | 11442.10.538.521 I slot print_timing: id 0 | task 2857381 | prompt processing, n_tokens = 3771, progress = 0.91, t = 3.22 s / 1169.33 tokens per second
llama-server | 11442.11.083.356 I slot print_timing: id 0 | task 2857381 | prompt processing, n_tokens = 4283, progress = 1.00, t = 3.68 s / 1163.31 tokens per second
llama-server | 11442.14.253.748 I slot print_timing: id 0 | task 2857381 | n_gen = 181, tg = 59.71 t/s, tg_3s = 60.03 t/s
llama-server | 11442.17.318.618 I slot print_timing: id 0 | task 2857381 | n_gen = 347, tg = 56.91 t/s, tg_3s = 54.16 t/s
llama-server | 11442.20.376.865 I slot print_timing: id 0 | task 2857381 | n_gen = 518, tg = 56.58 t/s, tg_3s = 55.91 t/s
llama-server | 11442.23.388.569 I slot print_timing: id 0 | task 2857381 | n_gen = 699, tg = 57.45 t/s, tg_3s = 60.10 t/s
llama-server | 11442.26.401.197 I slot print_timing: id 0 | task 2857381 | n_gen = 867, tg = 57.12 t/s, tg_3s = 55.77 t/s
llama-server | 11442.29.411.406 I slot print_timing: id 0 | task 2857381 | n_gen = 1078, tg = 59.27 t/s, tg_3s = 70.09 t/s
llama-server | 11442.32.449.297 I slot print_timing: id 0 | task 2857381 | n_gen = 1304, tg = 61.43 t/s, tg_3s = 74.39 t/s
llama-server | 11442.35.472.918 I slot print_timing: id 0 | task 2857381 | n_gen = 1454, tg = 59.96 t/s, tg_3s = 49.61 t/s
llama-server | 11442.36.956.085 W srv stop: cancel task, id_task = 2857381
llama-server | 11442.37.017.660 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686526624283
llama-server | 11442.37.018.126 I slot launch_slot_: id 1 | task 2857737 | processing task, is_child = 0
llama-server | 11442.37.018.129 I slot release: id 0 | task 2857381 | stop processing: n_tokens = 7144, truncated = 0
llama-server | 11442.42.079.317 I slot print_timing: id 1 | task 2857737 | prompt processing, n_tokens = 5063, progress = 0.91, t = 4.68 s / 1080.77 tokens per second
llama-server | 11442.42.697.959 I slot print_timing: id 1 | task 2857737 | prompt processing, n_tokens = 5575, progress = 1.00, t = 5.20 s / 1072.62 tokens per second
llama-server | 11442.45.936.685 I slot print_timing: id 1 | task 2857737 | n_gen = 182, tg = 58.99 t/s, tg_3s = 59.31 t/s
llama-server | 11442.48.970.027 I slot print_timing: id 1 | task 2857737 | n_gen = 328, tg = 53.59 t/s, tg_3s = 48.13 t/s
llama-server | 11442.52.024.155 I slot print_timing: id 1 | task 2857737 | n_gen = 482, tg = 52.54 t/s, tg_3s = 50.42 t/s
llama-server | 11442.55.088.868 I slot print_timing: id 1 | task 2857737 | n_gen = 644, tg = 52.62 t/s, tg_3s = 52.86 t/s
llama-server | 11442.58.136.639 I slot print_timing: id 1 | task 2857737 | n_gen = 803, tg = 52.53 t/s, tg_3s = 52.17 t/s
llama-server | 11443.01.203.360 I slot print_timing: id 1 | task 2857737 | n_gen = 957, tg = 52.14 t/s, tg_3s = 50.22 t/s
llama-server | 11443.04.206.855 I slot print_timing: id 1 | task 2857737 | n_gen = 1149, tg = 53.80 t/s, tg_3s = 63.93 t/s
llama-server | 11443.07.266.573 I slot print_timing: id 1 | task 2857737 | n_gen = 1299, tg = 53.20 t/s, tg_3s = 49.02 t/s
llama-server | 11443.10.277.327 I slot print_timing: id 1 | task 2857737 | n_gen = 1494, tg = 54.47 t/s, tg_3s = 64.77 t/s
llama-server | 11443.13.293.935 I slot print_timing: id 1 | task 2857737 | n_gen = 1692, tg = 55.58 t/s, tg_3s = 65.64 t/s
llama-server | 11443.16.366.787 I slot print_timing: id 1 | task 2857737 | n_gen = 1842, tg = 54.96 t/s, tg_3s = 48.81 t/s
llama-server | 11443.19.378.577 I slot print_timing: id 1 | task 2857737 | n_gen = 1980, tg = 54.20 t/s, tg_3s = 45.82 t/s
llama-server | 11443.22.393.335 I slot print_timing: id 1 | task 2857737 | n_gen = 2137, tg = 54.04 t/s, tg_3s = 52.08 t/s
llama-server | 11443.25.407.402 I slot print_timing: id 1 | task 2857737 | n_gen = 2360, tg = 55.45 t/s, tg_3s = 73.99 t/s
llama-server | 11443.28.450.395 I slot print_timing: id 1 | task 2857737 | n_gen = 2573, tg = 56.43 t/s, tg_3s = 70.00 t/s
llama-server | 11443.30.496.160 I slot print_timing: id 1 | task 2857737 | prompt eval time = 5849.99 ms / 5579 tokens ( 1.05 ms per token, 953.68 tokens per second)
llama-server | 11443.30.496.164 I slot print_timing: id 1 | task 2857737 | eval time = 47627.76 ms / 2723 tokens ( 17.50 ms per token, 57.15 tokens per second)
llama-server | 11443.30.496.165 I slot print_timing: id 1 | task 2857737 | total time = 53477.75 ms / 8302 tokens
llama-server | 11443.30.496.165 I slot print_timing: id 1 | task 2857737 | graphs reused = 2767462
llama-server | 11443.30.496.168 I slot print_timing: id 1 | task 2857737 | draft acceptance = 0.67948 ( 2103 accepted / 3095 generated), mean len = 4.40
llama-server | 11443.30.496.384 I slot release: id 1 | task 2857737 | stop processing: n_tokens = 8301, truncated = 0
llama-server | 11443.30.613.347 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.816 (> 0.100 thold), f_keep = 0.182
llama-server | 11443.30.614.133 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 963.652 MiB)
llama-server | 11443.31.275.738 I slot launch_slot_: id 0 | task 2858363 | processing task, is_child = 0
llama-server | 11443.31.277.011 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1137.204 MiB)
llama-server | 11443.35.665.879 I slot print_timing: id 0 | task 2858363 | n_gen = 204, tg = 67.03 t/s, tg_3s = 67.35 t/s
llama-server | 11443.38.708.346 I slot print_timing: id 0 | task 2858363 | n_gen = 412, tg = 67.70 t/s, tg_3s = 68.37 t/s
llama-server | 11443.41.759.453 I slot print_timing: id 0 | task 2858363 | n_gen = 660, tg = 72.24 t/s, tg_3s = 81.28 t/s
llama-server | 11443.44.601.178 I slot print_timing: id 0 | task 2858363 | prompt eval time = 588.76 ms / 297 tokens ( 1.98 ms per token, 504.45 tokens per second)
llama-server | 11443.44.601.182 I slot print_timing: id 0 | task 2858363 | eval time = 11963.82 ms / 894 tokens ( 13.40 ms per token, 74.64 tokens per second)
llama-server | 11443.44.601.182 I slot print_timing: id 0 | task 2858363 | total time = 12552.58 ms / 1191 tokens
llama-server | 11443.44.601.183 I slot print_timing: id 0 | task 2858363 | graphs reused = 2767623
llama-server | 11443.44.601.215 I slot print_timing: id 0 | task 2858363 | draft acceptance = 0.88242 ( 728 accepted / 825 generated), mean len = 5.41
llama-server | 11443.44.601.299 I slot release: id 0 | task 2858363 | stop processing: n_tokens = 2482, truncated = 0
llama-server | 11443.51.839.152 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.523
llama-server | 11443.51.839.979 I slot launch_slot_: id 0 | task 2858531 | processing task, is_child = 0
llama-server | 11443.57.939.907 I slot print_timing: id 0 | task 2858531 | n_gen = 159, tg = 51.38 t/s, tg_3s = 51.70 t/s
llama-server | 11444.00.976.176 I slot print_timing: id 0 | task 2858531 | n_gen = 313, tg = 51.05 t/s, tg_3s = 50.72 t/s
llama-server | 11444.04.041.990 I slot print_timing: id 0 | task 2858531 | n_gen = 472, tg = 51.32 t/s, tg_3s = 51.86 t/s
llama-server | 11444.07.100.806 I slot print_timing: id 0 | task 2858531 | n_gen = 632, tg = 51.57 t/s, tg_3s = 52.31 t/s
llama-server | 11444.10.114.329 I slot print_timing: id 0 | task 2858531 | n_gen = 811, tg = 53.12 t/s, tg_3s = 59.40 t/s
llama-server | 11444.13.139.572 I slot print_timing: id 0 | task 2858531 | n_gen = 1012, tg = 55.32 t/s, tg_3s = 66.44 t/s
llama-server | 11444.16.175.757 I slot print_timing: id 0 | task 2858531 | n_gen = 1252, tg = 58.70 t/s, tg_3s = 79.05 t/s
llama-server | 11444.17.352.271 I slot print_timing: id 0 | task 2858531 | prompt eval time = 3023.79 ms / 2906 tokens ( 1.04 ms per token, 961.05 tokens per second)
llama-server | 11444.17.352.274 I slot print_timing: id 0 | task 2858531 | eval time = 22487.73 ms / 1343 tokens ( 16.76 ms per token, 59.68 tokens per second)
llama-server | 11444.17.352.275 I slot print_timing: id 0 | task 2858531 | total time = 25511.52 ms / 4249 tokens
llama-server | 11444.17.352.276 I slot print_timing: id 0 | task 2858531 | graphs reused = 2767924
llama-server | 11444.17.352.279 I slot print_timing: id 0 | task 2858531 | draft acceptance = 0.67427 ( 1035 accepted / 1535 generated), mean len = 4.37
llama-server | 11444.17.352.434 I slot release: id 0 | task 2858531 | stop processing: n_tokens = 5540, truncated = 0
llama-server | 11444.17.468.171 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.831 (> 0.100 thold), f_keep = 0.234
llama-server | 11444.17.468.933 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1000.292 MiB)
llama-server | 11444.18.244.555 I slot launch_slot_: id 0 | task 2858843 | processing task, is_child = 0
llama-server | 11444.21.842.425 I slot print_timing: id 0 | task 2858843 | n_gen = 182, tg = 60.10 t/s, tg_3s = 60.43 t/s
llama-server | 11444.24.879.161 I slot print_timing: id 0 | task 2858843 | n_gen = 382, tg = 62.99 t/s, tg_3s = 65.86 t/s
llama-server | 11444.27.914.017 I slot print_timing: id 0 | task 2858843 | n_gen = 535, tg = 58.79 t/s, tg_3s = 50.41 t/s
llama-server | 11444.30.967.857 I slot print_timing: id 0 | task 2858843 | n_gen = 772, tg = 63.52 t/s, tg_3s = 77.61 t/s
llama-server | 11444.31.688.459 I slot print_timing: id 0 | task 2858843 | prompt eval time = 585.39 ms / 268 tokens ( 2.18 ms per token, 457.82 tokens per second)
llama-server | 11444.31.688.462 I slot print_timing: id 0 | task 2858843 | eval time = 12857.77 ms / 827 tokens ( 15.57 ms per token, 64.24 tokens per second)
llama-server | 11444.31.688.463 I slot print_timing: id 0 | task 2858843 | total time = 13443.16 ms / 1095 tokens
llama-server | 11444.31.688.464 I slot print_timing: id 0 | task 2858843 | graphs reused = 2768098
llama-server | 11444.31.688.467 I slot print_timing: id 0 | task 2858843 | draft acceptance = 0.72809 ( 648 accepted / 890 generated), mean len = 4.64
llama-server | 11444.31.688.566 I slot release: id 0 | task 2858843 | stop processing: n_tokens = 2386, truncated = 0
llama-server | 11444.36.987.781 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.265 (> 0.100 thold), f_keep = 0.544
llama-server | 11444.36.988.432 I slot launch_slot_: id 0 | task 2859024 | processing task, is_child = 0
llama-server | 11444.40.475.875 I slot print_timing: id 0 | task 2859024 | prompt processing, n_tokens = 3594, progress = 1.00, t = 3.04 s / 1180.80 tokens per second
llama-server | 11444.43.700.874 I slot print_timing: id 0 | task 2859024 | n_gen = 166, tg = 53.84 t/s, tg_3s = 54.17 t/s
llama-server | 11444.46.702.068 I slot print_timing: id 0 | task 2859024 | n_gen = 315, tg = 51.77 t/s, tg_3s = 49.65 t/s
llama-server | 11444.49.770.454 I slot print_timing: id 0 | task 2859024 | n_gen = 477, tg = 52.11 t/s, tg_3s = 52.80 t/s
llama-server | 11444.52.780.543 I slot print_timing: id 0 | task 2859024 | n_gen = 628, tg = 51.63 t/s, tg_3s = 50.16 t/s
llama-server | 11444.55.800.740 I slot print_timing: id 0 | task 2859024 | n_gen = 776, tg = 51.11 t/s, tg_3s = 49.00 t/s
llama-server | 11444.58.811.025 I slot print_timing: id 0 | task 2859024 | n_gen = 917, tg = 50.40 t/s, tg_3s = 46.84 t/s
llama-server | 11445.01.843.067 I slot print_timing: id 0 | task 2859024 | n_gen = 1061, tg = 49.98 t/s, tg_3s = 47.49 t/s
llama-server | 11445.04.865.530 I slot print_timing: id 0 | task 2859024 | n_gen = 1232, tg = 50.81 t/s, tg_3s = 56.58 t/s
llama-server | 11445.06.992.046 W srv stop: cancel task, id_task = 2859024
llama-server | 11445.07.012.113 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686626336436
llama-server | 11445.07.012.528 I slot launch_slot_: id 1 | task 2859388 | processing task, is_child = 0
llama-server | 11445.07.012.531 I slot release: id 0 | task 2859024 | stop processing: n_tokens = 6202, truncated = 0
llama-server | 11445.11.361.797 I slot print_timing: id 1 | task 2859388 | prompt processing, n_tokens = 4374, progress = 0.89, t = 4.20 s / 1041.70 tokens per second
llama-server | 11445.11.961.063 I slot print_timing: id 1 | task 2859388 | prompt processing, n_tokens = 4886, progress = 1.00, t = 4.47 s / 1091.97 tokens per second
llama-server | 11445.15.150.565 I slot print_timing: id 1 | task 2859388 | n_gen = 140, tg = 45.87 t/s, tg_3s = 46.20 t/s
llama-server | 11445.18.196.084 I slot print_timing: id 1 | task 2859388 | n_gen = 300, tg = 49.21 t/s, tg_3s = 52.54 t/s
llama-server | 11445.21.240.913 I slot print_timing: id 1 | task 2859388 | n_gen = 443, tg = 48.46 t/s, tg_3s = 46.96 t/s
llama-server | 11445.24.266.174 I slot print_timing: id 1 | task 2859388 | n_gen = 586, tg = 48.17 t/s, tg_3s = 47.27 t/s
llama-server | 11445.27.312.805 I slot print_timing: id 1 | task 2859388 | n_gen = 736, tg = 48.38 t/s, tg_3s = 49.23 t/s
llama-server | 11445.30.347.685 I slot print_timing: id 1 | task 2859388 | n_gen = 874, tg = 47.90 t/s, tg_3s = 45.47 t/s
llama-server | 11445.33.400.425 I slot print_timing: id 1 | task 2859388 | n_gen = 989, tg = 46.43 t/s, tg_3s = 37.67 t/s
llama-server | 11445.36.452.271 I slot print_timing: id 1 | task 2859388 | n_gen = 1144, tg = 46.98 t/s, tg_3s = 50.79 t/s
llama-server | 11445.39.526.293 I slot print_timing: id 1 | task 2859388 | n_gen = 1309, tg = 47.73 t/s, tg_3s = 53.68 t/s
llama-server | 11445.42.578.432 I slot print_timing: id 1 | task 2859388 | n_gen = 1431, tg = 46.95 t/s, tg_3s = 39.97 t/s
llama-server | 11445.45.586.506 I slot print_timing: id 1 | task 2859388 | n_gen = 1640, tg = 48.98 t/s, tg_3s = 69.48 t/s
llama-server | 11445.47.681.938 I slot print_timing: id 1 | task 2859388 | prompt eval time = 5107.68 ms / 4890 tokens ( 1.04 ms per token, 957.38 tokens per second)
llama-server | 11445.47.681.942 I slot print_timing: id 1 | task 2859388 | eval time = 35561.43 ms / 1795 tokens ( 19.82 ms per token, 50.45 tokens per second)
llama-server | 11445.47.681.942 I slot print_timing: id 1 | task 2859388 | total time = 40669.12 ms / 6685 tokens
llama-server | 11445.47.681.943 I slot print_timing: id 1 | task 2859388 | graphs reused = 2768909
llama-server | 11445.47.681.946 I slot print_timing: id 1 | task 2859388 | draft acceptance = 0.56996 ( 1328 accepted / 2330 generated), mean len = 3.85
llama-server | 11445.47.682.139 I slot release: id 1 | task 2859388 | stop processing: n_tokens = 6684, truncated = 0
llama-server | 11445.47.804.028 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.828 (> 0.100 thold), f_keep = 0.209
llama-server | 11445.47.804.767 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1131.751 MiB)
llama-server | 11445.48.417.820 I slot launch_slot_: id 0 | task 2859861 | processing task, is_child = 0
llama-server | 11445.48.418.426 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 964.217 MiB)
llama-server | 11445.52.603.075 I slot print_timing: id 0 | task 2859861 | n_gen = 191, tg = 62.66 t/s, tg_3s = 62.99 t/s
llama-server | 11445.55.646.646 I slot print_timing: id 0 | task 2859861 | n_gen = 389, tg = 63.86 t/s, tg_3s = 65.06 t/s
llama-server | 11445.58.704.557 I slot print_timing: id 0 | task 2859861 | n_gen = 640, tg = 69.96 t/s, tg_3s = 82.08 t/s
llama-server | 11445.59.209.394 I slot print_timing: id 0 | task 2859861 | prompt eval time = 567.14 ms / 274 tokens ( 2.07 ms per token, 483.13 tokens per second)
llama-server | 11445.59.209.398 I slot print_timing: id 0 | task 2859861 | eval time = 9638.30 ms / 678 tokens ( 14.24 ms per token, 70.24 tokens per second)
llama-server | 11445.59.209.398 I slot print_timing: id 0 | task 2859861 | total time = 10205.44 ms / 952 tokens
llama-server | 11445.59.209.400 I slot print_timing: id 0 | task 2859861 | graphs reused = 2769039
llama-server | 11445.59.209.403 I slot print_timing: id 0 | task 2859861 | draft acceptance = 0.81805 ( 544 accepted / 665 generated), mean len = 5.09
llama-server | 11445.59.209.517 I slot release: id 0 | task 2859861 | stop processing: n_tokens = 2243, truncated = 0
llama-server | 11446.07.203.649 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.247 (> 0.100 thold), f_keep = 0.578
llama-server | 11446.07.204.517 I slot launch_slot_: id 0 | task 2859997 | processing task, is_child = 0
llama-server | 11446.11.012.887 I slot print_timing: id 0 | task 2859997 | prompt processing, n_tokens = 3955, progress = 1.00, t = 3.36 s / 1175.40 tokens per second
llama-server | 11446.14.194.032 I slot print_timing: id 0 | task 2859997 | n_gen = 143, tg = 47.07 t/s, tg_3s = 47.40 t/s
llama-server | 11446.17.254.320 I slot print_timing: id 0 | task 2859997 | n_gen = 314, tg = 51.51 t/s, tg_3s = 55.88 t/s
llama-server | 11446.20.266.623 I slot print_timing: id 0 | task 2859997 | n_gen = 463, tg = 50.83 t/s, tg_3s = 49.46 t/s
llama-server | 11446.23.340.330 I slot print_timing: id 0 | task 2859997 | n_gen = 613, tg = 50.32 t/s, tg_3s = 48.80 t/s
llama-server | 11446.26.363.376 I slot print_timing: id 0 | task 2859997 | n_gen = 760, tg = 49.98 t/s, tg_3s = 48.63 t/s
llama-server | 11446.29.370.902 I slot print_timing: id 0 | task 2859997 | n_gen = 891, tg = 48.92 t/s, tg_3s = 43.56 t/s
llama-server | 11446.32.400.128 I slot print_timing: id 0 | task 2859997 | n_gen = 1029, tg = 48.44 t/s, tg_3s = 45.56 t/s
llama-server | 11446.35.437.023 I slot print_timing: id 0 | task 2859997 | n_gen = 1205, tg = 49.63 t/s, tg_3s = 57.95 t/s
llama-server | 11446.37.207.385 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686763522191
llama-server | 11446.37.207.515 W srv stop: cancel task, id_task = 2859997
llama-server | 11446.37.207.811 I slot launch_slot_: id 1 | task 2860356 | processing task, is_child = 0
llama-server | 11446.37.207.815 I slot release: id 0 | task 2859997 | stop processing: n_tokens = 6547, truncated = 0
llama-server | 11446.41.879.771 I slot print_timing: id 1 | task 2860356 | prompt processing, n_tokens = 4735, progress = 0.90, t = 4.19 s / 1130.44 tokens per second
llama-server | 11446.42.455.806 I slot print_timing: id 1 | task 2860356 | prompt processing, n_tokens = 5247, progress = 1.00, t = 4.77 s / 1099.80 tokens per second
llama-server | 11446.45.657.530 I slot print_timing: id 1 | task 2860356 | n_gen = 134, tg = 43.58 t/s, tg_3s = 43.90 t/s
llama-server | 11446.48.708.643 I slot print_timing: id 1 | task 2860356 | n_gen = 245, tg = 39.98 t/s, tg_3s = 36.38 t/s
llama-server | 11446.51.738.711 I slot print_timing: id 1 | task 2860356 | n_gen = 372, tg = 40.62 t/s, tg_3s = 41.91 t/s
llama-server | 11446.54.799.603 I slot print_timing: id 1 | task 2860356 | n_gen = 522, tg = 42.73 t/s, tg_3s = 49.01 t/s
llama-server | 11446.57.855.354 I slot print_timing: id 1 | task 2860356 | n_gen = 680, tg = 44.53 t/s, tg_3s = 51.71 t/s
llama-server | 11447.00.925.287 I slot print_timing: id 1 | task 2860356 | n_gen = 851, tg = 46.40 t/s, tg_3s = 55.70 t/s
llama-server | 11447.03.991.828 I slot print_timing: id 1 | task 2860356 | n_gen = 1016, tg = 47.46 t/s, tg_3s = 53.81 t/s
llama-server | 11447.07.054.853 I slot print_timing: id 1 | task 2860356 | n_gen = 1186, tg = 48.47 t/s, tg_3s = 55.50 t/s
llama-server | 11447.10.061.497 I slot print_timing: id 1 | task 2860356 | n_gen = 1351, tg = 49.17 t/s, tg_3s = 54.88 t/s
llama-server | 11447.13.127.601 I slot print_timing: id 1 | task 2860356 | n_gen = 1496, tg = 48.98 t/s, tg_3s = 47.29 t/s
llama-server | 11447.16.148.229 I slot print_timing: id 1 | task 2860356 | n_gen = 1673, tg = 49.85 t/s, tg_3s = 58.60 t/s
llama-server | 11447.18.787.924 I slot print_timing: id 1 | task 2860356 | prompt eval time = 5397.61 ms / 5251 tokens ( 1.03 ms per token, 972.84 tokens per second)
llama-server | 11447.18.787.928 I slot print_timing: id 1 | task 2860356 | eval time = 36182.22 ms / 1856 tokens ( 19.51 ms per token, 51.27 tokens per second)
llama-server | 11447.18.787.928 I slot print_timing: id 1 | task 2860356 | total time = 41579.82 ms / 7107 tokens
llama-server | 11447.18.787.929 I slot print_timing: id 1 | task 2860356 | graphs reused = 2769851
llama-server | 11447.18.787.932 I slot print_timing: id 1 | task 2860356 | draft acceptance = 0.58602 ( 1383 accepted / 2360 generated), mean len = 3.93
llama-server | 11447.18.788.162 I slot release: id 1 | task 2860356 | stop processing: n_tokens = 7106, truncated = 0
llama-server | 11447.18.912.479 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.846 (> 0.100 thold), f_keep = 0.198
llama-server | 11447.18.913.257 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1099.965 MiB)
llama-server | 11447.19.550.173 I slot launch_slot_: id 0 | task 2860835 | processing task, is_child = 0
llama-server | 11447.19.550.781 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1002.088 MiB)
llama-server | 11447.23.710.796 I slot print_timing: id 0 | task 2860835 | n_gen = 204, tg = 67.52 t/s, tg_3s = 67.84 t/s
llama-server | 11447.26.730.404 I slot print_timing: id 0 | task 2860835 | n_gen = 434, tg = 71.85 t/s, tg_3s = 76.17 t/s
llama-server | 11447.29.535.449 I slot print_timing: id 0 | task 2860835 | prompt eval time = 528.29 ms / 241 tokens ( 2.19 ms per token, 456.19 tokens per second)
llama-server | 11447.29.535.452 I slot print_timing: id 0 | task 2860835 | eval time = 8831.32 ms / 664 tokens ( 13.32 ms per token, 75.07 tokens per second)
llama-server | 11447.29.535.453 I slot print_timing: id 0 | task 2860835 | total time = 9359.61 ms / 905 tokens
llama-server | 11447.29.535.454 I slot print_timing: id 0 | task 2860835 | graphs reused = 2769971
llama-server | 11447.29.535.456 I slot print_timing: id 0 | task 2860835 | draft acceptance = 0.87967 ( 541 accepted / 615 generated), mean len = 5.40
llama-server | 11447.29.535.549 I slot release: id 0 | task 2860835 | stop processing: n_tokens = 2197, truncated = 0
llama-server | 11447.37.233.392 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.320 (> 0.100 thold), f_keep = 0.590
llama-server | 11447.37.234.181 I slot launch_slot_: id 0 | task 2860961 | processing task, is_child = 0
llama-server | 11447.43.171.489 I slot print_timing: id 0 | task 2860961 | n_gen = 194, tg = 63.28 t/s, tg_3s = 63.60 t/s
llama-server | 11447.46.196.846 I slot print_timing: id 0 | task 2860961 | n_gen = 335, tg = 54.98 t/s, tg_3s = 46.61 t/s
llama-server | 11447.49.210.358 I slot print_timing: id 0 | task 2860961 | n_gen = 491, tg = 53.91 t/s, tg_3s = 51.77 t/s
llama-server | 11447.52.251.749 I slot print_timing: id 0 | task 2860961 | n_gen = 648, tg = 53.34 t/s, tg_3s = 51.62 t/s
llama-server | 11447.55.293.708 I slot print_timing: id 0 | task 2860961 | n_gen = 818, tg = 53.85 t/s, tg_3s = 55.89 t/s
llama-server | 11447.58.353.659 I slot print_timing: id 0 | task 2860961 | n_gen = 982, tg = 53.81 t/s, tg_3s = 53.60 t/s
llama-server | 11448.01.420.631 I slot print_timing: id 0 | task 2860961 | n_gen = 1159, tg = 54.37 t/s, tg_3s = 57.71 t/s
llama-server | 11448.04.429.705 I slot print_timing: id 0 | task 2860961 | n_gen = 1372, tg = 56.40 t/s, tg_3s = 70.79 t/s
llama-server | 11448.07.133.829 I slot print_timing: id 0 | task 2860961 | prompt eval time = 2886.62 ms / 2760 tokens ( 1.05 ms per token, 956.13 tokens per second)
llama-server | 11448.07.133.832 I slot print_timing: id 0 | task 2860961 | eval time = 27012.23 ms / 1583 tokens ( 17.07 ms per token, 58.57 tokens per second)
llama-server | 11448.07.133.833 I slot print_timing: id 0 | task 2860961 | total time = 29898.85 ms / 4343 tokens
llama-server | 11448.07.133.833 I slot print_timing: id 0 | task 2860961 | graphs reused = 2770335
llama-server | 11448.07.133.836 I slot print_timing: id 0 | task 2860961 | draft acceptance = 0.65054 ( 1210 accepted / 1860 generated), mean len = 4.25
llama-server | 11448.07.134.044 I slot release: id 0 | task 2860961 | stop processing: n_tokens = 5634, truncated = 0
llama-server | 11448.07.247.226 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.842 (> 0.100 thold), f_keep = 0.230
llama-server | 11448.07.247.993 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1151.501 MiB)
llama-server | 11448.07.966.068 I slot launch_slot_: id 0 | task 2861338 | processing task, is_child = 0
llama-server | 11448.11.502.144 I slot print_timing: id 0 | task 2861338 | n_gen = 193, tg = 63.94 t/s, tg_3s = 64.27 t/s
llama-server | 11448.14.514.217 I slot print_timing: id 0 | task 2861338 | n_gen = 415, tg = 68.83 t/s, tg_3s = 73.70 t/s
llama-server | 11448.15.891.828 I slot print_timing: id 0 | task 2861338 | prompt eval time = 532.54 ms / 249 tokens ( 2.14 ms per token, 467.57 tokens per second)
llama-server | 11448.15.891.832 I slot print_timing: id 0 | task 2861338 | eval time = 7392.45 ms / 526 tokens ( 14.08 ms per token, 71.02 tokens per second)
llama-server | 11448.15.891.832 I slot print_timing: id 0 | task 2861338 | total time = 7924.99 ms / 775 tokens
llama-server | 11448.15.891.833 I slot print_timing: id 0 | task 2861338 | graphs reused = 2770435
llama-server | 11448.15.891.836 I slot print_timing: id 0 | task 2861338 | draft acceptance = 0.81942 ( 422 accepted / 515 generated), mean len = 5.10
llama-server | 11448.15.891.945 I slot release: id 0 | task 2861338 | stop processing: n_tokens = 2066, truncated = 0
llama-server | 11448.22.426.122 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.628
llama-server | 11448.22.426.816 I slot launch_slot_: id 0 | task 2861444 | processing task, is_child = 0
llama-server | 11448.25.994.572 I slot print_timing: id 0 | task 2861444 | prompt processing, n_tokens = 3801, progress = 1.00, t = 3.12 s / 1216.50 tokens per second
llama-server | 11448.29.219.407 I slot print_timing: id 0 | task 2861444 | n_gen = 174, tg = 56.42 t/s, tg_3s = 56.75 t/s
llama-server | 11448.32.272.913 I slot print_timing: id 0 | task 2861444 | n_gen = 342, tg = 55.72 t/s, tg_3s = 55.02 t/s
llama-server | 11448.35.310.804 I slot print_timing: id 0 | task 2861444 | n_gen = 497, tg = 54.16 t/s, tg_3s = 51.02 t/s
llama-server | 11448.38.373.428 I slot print_timing: id 0 | task 2861444 | n_gen = 645, tg = 52.70 t/s, tg_3s = 48.32 t/s
llama-server | 11448.41.375.800 I slot print_timing: id 0 | task 2861444 | n_gen = 799, tg = 52.42 t/s, tg_3s = 51.29 t/s
llama-server | 11448.44.439.263 I slot print_timing: id 0 | task 2861444 | n_gen = 989, tg = 54.03 t/s, tg_3s = 62.02 t/s
llama-server | 11448.47.453.286 I slot print_timing: id 0 | task 2861444 | n_gen = 1174, tg = 55.07 t/s, tg_3s = 61.38 t/s
llama-server | 11448.50.470.224 I slot print_timing: id 0 | task 2861444 | n_gen = 1320, tg = 54.24 t/s, tg_3s = 48.39 t/s
llama-server | 11448.52.429.373 W srv stop: cancel task, id_task = 2861444
llama-server | 11448.52.445.017 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686854628214
llama-server | 11448.52.445.450 I slot launch_slot_: id 1 | task 2861809 | processing task, is_child = 0
llama-server | 11448.52.445.453 I slot release: id 0 | task 2861444 | stop processing: n_tokens = 6518, truncated = 0
llama-server | 11448.56.873.896 I slot print_timing: id 1 | task 2861809 | prompt processing, n_tokens = 4581, progress = 0.90, t = 4.12 s / 1111.12 tokens per second
llama-server | 11448.57.464.975 I slot print_timing: id 1 | task 2861809 | prompt processing, n_tokens = 5093, progress = 1.00, t = 4.54 s / 1121.21 tokens per second
llama-server | 11449.00.679.624 I slot print_timing: id 1 | task 2861809 | n_gen = 170, tg = 55.45 t/s, tg_3s = 55.77 t/s
llama-server | 11449.03.696.461 I slot print_timing: id 1 | task 2861809 | n_gen = 315, tg = 51.78 t/s, tg_3s = 48.06 t/s
llama-server | 11449.06.732.481 I slot print_timing: id 1 | task 2861809 | n_gen = 470, tg = 51.53 t/s, tg_3s = 51.05 t/s
llama-server | 11449.09.757.202 I slot print_timing: id 1 | task 2861809 | n_gen = 631, tg = 51.96 t/s, tg_3s = 53.23 t/s
llama-server | 11449.12.798.452 I slot print_timing: id 1 | task 2861809 | n_gen = 772, tg = 50.84 t/s, tg_3s = 46.36 t/s
llama-server | 11449.15.853.871 I slot print_timing: id 1 | task 2861809 | n_gen = 965, tg = 52.90 t/s, tg_3s = 63.17 t/s
llama-server | 11449.18.886.375 I slot print_timing: id 1 | task 2861809 | n_gen = 1113, tg = 52.32 t/s, tg_3s = 48.80 t/s
llama-server | 11449.21.953.131 I slot print_timing: id 1 | task 2861809 | n_gen = 1320, tg = 54.23 t/s, tg_3s = 67.50 t/s
llama-server | 11449.25.019.001 I slot print_timing: id 1 | task 2861809 | n_gen = 1533, tg = 55.94 t/s, tg_3s = 69.47 t/s
llama-server | 11449.27.327.505 I slot print_timing: id 1 | task 2861809 | prompt eval time = 5186.13 ms / 5097 tokens ( 1.02 ms per token, 982.81 tokens per second)
llama-server | 11449.27.327.508 I slot print_timing: id 1 | task 2861809 | eval time = 29695.67 ms / 1713 tokens ( 17.35 ms per token, 57.65 tokens per second)
llama-server | 11449.27.327.509 I slot print_timing: id 1 | task 2861809 | total time = 34881.80 ms / 6810 tokens
llama-server | 11449.27.327.510 I slot print_timing: id 1 | task 2861809 | graphs reused = 2771170
llama-server | 11449.27.327.512 I slot print_timing: id 1 | task 2861809 | draft acceptance = 0.67795 ( 1322 accepted / 1950 generated), mean len = 4.39
llama-server | 11449.27.327.676 I slot release: id 1 | task 2861809 | stop processing: n_tokens = 6809, truncated = 0
llama-server | 11449.27.441.776 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.199
llama-server | 11449.27.442.536 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1019.909 MiB)
llama-server | 11449.28.115.283 I slot launch_slot_: id 0 | task 2862206 | processing task, is_child = 0
llama-server | 11449.28.116.499 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1098.189 MiB)
llama-server | 11449.32.381.966 I slot print_timing: id 0 | task 2862206 | n_gen = 190, tg = 62.80 t/s, tg_3s = 63.13 t/s
llama-server | 11449.35.399.864 I slot print_timing: id 0 | task 2862206 | n_gen = 400, tg = 66.20 t/s, tg_3s = 69.58 t/s
llama-server | 11449.38.416.687 I slot print_timing: id 0 | task 2862206 | n_gen = 582, tg = 64.24 t/s, tg_3s = 60.33 t/s
llama-server | 11449.41.453.254 I slot print_timing: id 0 | task 2862206 | n_gen = 813, tg = 67.21 t/s, tg_3s = 76.07 t/s
llama-server | 11449.43.316.411 I slot print_timing: id 0 | task 2862206 | prompt eval time = 564.33 ms / 279 tokens ( 2.02 ms per token, 494.39 tokens per second)
llama-server | 11449.43.316.415 I slot print_timing: id 0 | task 2862206 | eval time = 13944.06 ms / 965 tokens ( 14.46 ms per token, 69.13 tokens per second)
llama-server | 11449.43.316.415 I slot print_timing: id 0 | task 2862206 | total time = 14508.39 ms / 1244 tokens
llama-server | 11449.43.316.416 I slot print_timing: id 0 | task 2862206 | graphs reused = 2771360
llama-server | 11449.43.316.418 I slot print_timing: id 0 | task 2862206 | draft acceptance = 0.79381 ( 770 accepted / 970 generated), mean len = 4.97
llama-server | 11449.43.316.508 I slot release: id 0 | task 2862206 | stop processing: n_tokens = 2535, truncated = 0
llama-server | 11449.52.683.992 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.512
llama-server | 11449.52.684.695 I slot launch_slot_: id 0 | task 2862403 | processing task, is_child = 0
llama-server | 11449.58.717.020 I slot print_timing: id 0 | task 2862403 | n_gen = 150, tg = 49.32 t/s, tg_3s = 49.65 t/s
llama-server | 11450.01.743.603 I slot print_timing: id 0 | task 2862403 | n_gen = 300, tg = 49.44 t/s, tg_3s = 49.56 t/s
llama-server | 11450.04.781.341 I slot print_timing: id 0 | task 2862403 | n_gen = 457, tg = 50.19 t/s, tg_3s = 51.68 t/s
llama-server | 11450.07.806.998 I slot print_timing: id 0 | task 2862403 | n_gen = 612, tg = 50.45 t/s, tg_3s = 51.23 t/s
llama-server | 11450.10.861.552 I slot print_timing: id 0 | task 2862403 | n_gen = 811, tg = 53.41 t/s, tg_3s = 65.15 t/s
llama-server | 11450.13.925.349 I slot print_timing: id 0 | task 2862403 | n_gen = 996, tg = 54.58 t/s, tg_3s = 60.38 t/s
llama-server | 11450.16.997.574 I slot print_timing: id 0 | task 2862403 | n_gen = 1187, tg = 55.68 t/s, tg_3s = 62.17 t/s
llama-server | 11450.19.114.194 I slot print_timing: id 0 | task 2862403 | prompt eval time = 3010.74 ms / 2906 tokens ( 1.04 ms per token, 965.21 tokens per second)
llama-server | 11450.19.114.197 I slot print_timing: id 0 | task 2862403 | eval time = 23418.10 ms / 1359 tokens ( 17.24 ms per token, 57.99 tokens per second)
llama-server | 11450.19.114.198 I slot print_timing: id 0 | task 2862403 | total time = 26428.84 ms / 4265 tokens
llama-server | 11450.19.114.198 I slot print_timing: id 0 | task 2862403 | graphs reused = 2771677
llama-server | 11450.19.114.201 I slot print_timing: id 0 | task 2862403 | draft acceptance = 0.64087 ( 1035 accepted / 1615 generated), mean len = 4.20
llama-server | 11450.19.114.354 I slot release: id 0 | task 2862403 | stop processing: n_tokens = 5556, truncated = 0
llama-server | 11450.19.230.289 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.233
llama-server | 11450.19.231.145 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1120.180 MiB)
llama-server | 11450.19.847.617 I slot launch_slot_: id 0 | task 2862731 | processing task, is_child = 0
llama-server | 11450.23.406.913 I slot print_timing: id 0 | task 2862731 | n_gen = 184, tg = 60.93 t/s, tg_3s = 61.26 t/s
llama-server | 11450.26.413.994 I slot print_timing: id 0 | task 2862731 | n_gen = 372, tg = 61.73 t/s, tg_3s = 62.52 t/s
llama-server | 11450.29.436.556 I slot print_timing: id 0 | task 2862731 | n_gen = 595, tg = 65.76 t/s, tg_3s = 73.78 t/s
llama-server | 11450.31.391.490 I slot print_timing: id 0 | task 2862731 | prompt eval time = 555.36 ms / 266 tokens ( 2.09 ms per token, 478.97 tokens per second)
llama-server | 11450.31.391.494 I slot print_timing: id 0 | task 2862731 | eval time = 10988.00 ms / 753 tokens ( 14.61 ms per token, 68.44 tokens per second)
llama-server | 11450.31.391.494 I slot print_timing: id 0 | task 2862731 | total time = 11543.35 ms / 1019 tokens
llama-server | 11450.31.391.495 I slot print_timing: id 0 | task 2862731 | graphs reused = 2771826
llama-server | 11450.31.391.498 I slot print_timing: id 0 | task 2862731 | draft acceptance = 0.78301 ( 599 accepted / 765 generated), mean len = 4.92
llama-server | 11450.31.391.588 I slot release: id 0 | task 2862731 | stop processing: n_tokens = 2310, truncated = 0
llama-server | 11450.37.646.996 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.244 (> 0.100 thold), f_keep = 0.561
llama-server | 11450.37.647.829 I slot launch_slot_: id 0 | task 2862887 | processing task, is_child = 0
llama-server | 11450.41.554.681 I slot print_timing: id 0 | task 2862887 | prompt processing, n_tokens = 4023, progress = 1.00, t = 3.46 s / 1163.17 tokens per second
llama-server | 11450.44.791.620 I slot print_timing: id 0 | task 2862887 | n_gen = 152, tg = 49.20 t/s, tg_3s = 49.52 t/s
llama-server | 11450.47.819.350 I slot print_timing: id 0 | task 2862887 | n_gen = 311, tg = 50.84 t/s, tg_3s = 52.51 t/s
llama-server | 11450.50.882.947 I slot print_timing: id 0 | task 2862887 | n_gen = 479, tg = 52.18 t/s, tg_3s = 54.84 t/s
llama-server | 11450.53.952.579 I slot print_timing: id 0 | task 2862887 | n_gen = 652, tg = 53.23 t/s, tg_3s = 56.36 t/s
llama-server | 11450.57.006.286 I slot print_timing: id 0 | task 2862887 | n_gen = 820, tg = 53.59 t/s, tg_3s = 55.02 t/s
llama-server | 11451.00.023.347 I slot print_timing: id 0 | task 2862887 | n_gen = 1001, tg = 54.64 t/s, tg_3s = 59.99 t/s
llama-server | 11451.03.048.633 I slot print_timing: id 0 | task 2862887 | n_gen = 1237, tg = 57.96 t/s, tg_3s = 78.01 t/s
llama-server | 11451.04.759.127 I slot print_timing: id 0 | task 2862887 | prompt eval time = 4073.53 ms / 4027 tokens ( 1.01 ms per token, 988.58 tokens per second)
llama-server | 11451.04.759.132 I slot print_timing: id 0 | task 2862887 | eval time = 23036.70 ms / 1368 tokens ( 16.85 ms per token, 59.34 tokens per second)
llama-server | 11451.04.759.132 I slot print_timing: id 0 | task 2862887 | total time = 27110.22 ms / 5395 tokens
llama-server | 11451.04.759.133 I slot print_timing: id 0 | task 2862887 | graphs reused = 2772134
llama-server | 11451.04.759.136 I slot print_timing: id 0 | task 2862887 | draft acceptance = 0.66794 ( 1052 accepted / 1575 generated), mean len = 4.34
llama-server | 11451.04.759.351 I slot release: id 0 | task 2862887 | stop processing: n_tokens = 6686, truncated = 0
llama-server | 11451.04.875.283 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.194
llama-server | 11451.04.876.033 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 966.146 MiB)
llama-server | 11451.05.515.991 I slot launch_slot_: id 0 | task 2863207 | processing task, is_child = 0
llama-server | 11451.09.088.656 I slot print_timing: id 0 | task 2863207 | n_gen = 181, tg = 60.00 t/s, tg_3s = 60.33 t/s
llama-server | 11451.12.160.006 I slot print_timing: id 0 | task 2863207 | n_gen = 360, tg = 59.13 t/s, tg_3s = 58.28 t/s
llama-server | 11451.15.178.366 I slot print_timing: id 0 | task 2863207 | n_gen = 557, tg = 61.17 t/s, tg_3s = 65.27 t/s
llama-server | 11451.18.203.941 I slot print_timing: id 0 | task 2863207 | n_gen = 809, tg = 66.69 t/s, tg_3s = 83.29 t/s
llama-server | 11451.18.633.716 I slot print_timing: id 0 | task 2863207 | prompt eval time = 572.18 ms / 284 tokens ( 2.01 ms per token, 496.35 tokens per second)
llama-server | 11451.18.633.720 I slot print_timing: id 0 | task 2863207 | eval time = 12545.04 ms / 845 tokens ( 14.86 ms per token, 67.28 tokens per second)
llama-server | 11451.18.633.720 I slot print_timing: id 0 | task 2863207 | total time = 13117.22 ms / 1129 tokens
llama-server | 11451.18.633.721 I slot print_timing: id 0 | task 2863207 | graphs reused = 2772305
llama-server | 11451.18.633.724 I slot print_timing: id 0 | task 2863207 | draft acceptance = 0.76457 ( 669 accepted / 875 generated), mean len = 4.82
llama-server | 11451.18.633.811 I slot release: id 0 | task 2863207 | stop processing: n_tokens = 2420, truncated = 0
llama-server | 11451.27.796.917 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.316 (> 0.100 thold), f_keep = 0.536
llama-server | 11451.27.797.761 I slot launch_slot_: id 0 | task 2863385 | processing task, is_child = 0
llama-server | 11451.33.775.022 I slot print_timing: id 0 | task 2863385 | n_gen = 154, tg = 50.70 t/s, tg_3s = 51.02 t/s
llama-server | 11451.36.808.443 I slot print_timing: id 0 | task 2863385 | n_gen = 346, tg = 57.01 t/s, tg_3s = 63.29 t/s
llama-server | 11451.39.821.017 I slot print_timing: id 0 | task 2863385 | n_gen = 507, tg = 55.83 t/s, tg_3s = 53.44 t/s
llama-server | 11451.42.870.247 I slot print_timing: id 0 | task 2863385 | n_gen = 703, tg = 57.95 t/s, tg_3s = 64.28 t/s
llama-server | 11451.45.916.845 I slot print_timing: id 0 | task 2863385 | n_gen = 850, tg = 56.00 t/s, tg_3s = 48.25 t/s
llama-server | 11451.48.953.961 I slot print_timing: id 0 | task 2863385 | n_gen = 1019, tg = 55.94 t/s, tg_3s = 55.64 t/s
llama-server | 11451.52.020.881 I slot print_timing: id 0 | task 2863385 | n_gen = 1185, tg = 55.68 t/s, tg_3s = 54.13 t/s
llama-server | 11451.55.088.346 I slot print_timing: id 0 | task 2863385 | n_gen = 1338, tg = 54.95 t/s, tg_3s = 49.88 t/s
llama-server | 11451.57.803.089 W srv stop: cancel task, id_task = 2863385
llama-server | 11451.57.857.722 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 686983167728
llama-server | 11451.57.911.761 I slot launch_slot_: id 1 | task 2863764 | processing task, is_child = 0
llama-server | 11451.57.911.767 I slot release: id 0 | task 2863385 | stop processing: n_tokens = 5604, truncated = 0
llama-server | 11452.04.125.537 I slot print_timing: id 1 | task 2863764 | n_gen = 148, tg = 48.82 t/s, tg_3s = 49.15 t/s
llama-server | 11452.07.128.112 I slot print_timing: id 1 | task 2863764 | n_gen = 313, tg = 51.88 t/s, tg_3s = 54.95 t/s
llama-server | 11452.10.185.098 I slot print_timing: id 1 | task 2863764 | n_gen = 447, tg = 49.17 t/s, tg_3s = 43.83 t/s
llama-server | 11452.13.195.802 I slot print_timing: id 1 | task 2863764 | n_gen = 613, tg = 50.66 t/s, tg_3s = 55.14 t/s
llama-server | 11452.16.263.819 I slot print_timing: id 1 | task 2863764 | n_gen = 757, tg = 49.90 t/s, tg_3s = 46.94 t/s
llama-server | 11452.19.282.565 I slot print_timing: id 1 | task 2863764 | n_gen = 943, tg = 51.85 t/s, tg_3s = 61.62 t/s
llama-server | 11452.22.308.850 I slot print_timing: id 1 | task 2863764 | n_gen = 1154, tg = 54.40 t/s, tg_3s = 69.72 t/s
llama-server | 11452.25.309.093 I slot print_timing: id 1 | task 2863764 | n_gen = 1291, tg = 53.32 t/s, tg_3s = 45.66 t/s
llama-server | 11452.28.334.340 I slot print_timing: id 1 | task 2863764 | n_gen = 1486, tg = 54.56 t/s, tg_3s = 64.46 t/s
llama-server | 11452.30.920.400 I slot print_timing: id 1 | task 2863764 | prompt eval time = 3202.41 ms / 2811 tokens ( 1.14 ms per token, 877.78 tokens per second)
llama-server | 11452.30.920.404 I slot print_timing: id 1 | task 2863764 | eval time = 29805.95 ms / 1687 tokens ( 17.68 ms per token, 56.57 tokens per second)
llama-server | 11452.30.920.404 I slot print_timing: id 1 | task 2863764 | total time = 33008.37 ms / 4498 tokens
llama-server | 11452.30.920.405 I slot print_timing: id 1 | task 2863764 | graphs reused = 2773061
llama-server | 11452.30.920.408 I slot print_timing: id 1 | task 2863764 | draft acceptance = 0.65152 ( 1290 accepted / 1980 generated), mean len = 4.26
llama-server | 11452.30.920.602 I slot release: id 1 | task 2863764 | stop processing: n_tokens = 5789, truncated = 0
llama-server | 11452.31.045.566 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.839 (> 0.100 thold), f_keep = 0.231
llama-server | 11452.31.770.635 I slot launch_slot_: id 0 | task 2864166 | processing task, is_child = 0
llama-server | 11452.31.771.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1131.651 MiB)
llama-server | 11452.35.995.811 I slot print_timing: id 0 | task 2864166 | n_gen = 204, tg = 67.47 t/s, tg_3s = 67.80 t/s
llama-server | 11452.39.023.103 I slot print_timing: id 0 | task 2864166 | n_gen = 435, tg = 71.90 t/s, tg_3s = 76.31 t/s
llama-server | 11452.40.972.064 I slot print_timing: id 0 | task 2864166 | prompt eval time = 529.17 ms / 253 tokens ( 2.09 ms per token, 478.11 tokens per second)
llama-server | 11452.40.972.067 I slot print_timing: id 0 | task 2864166 | eval time = 7984.81 ms / 594 tokens ( 13.47 ms per token, 74.27 tokens per second)
llama-server | 11452.40.972.068 I slot print_timing: id 0 | task 2864166 | total time = 8513.97 ms / 847 tokens
llama-server | 11452.40.972.068 I slot print_timing: id 0 | task 2864166 | graphs reused = 2773169
llama-server | 11452.40.972.071 I slot print_timing: id 0 | task 2864166 | draft acceptance = 0.86847 ( 482 accepted / 555 generated), mean len = 5.34
llama-server | 11452.40.972.174 I slot release: id 0 | task 2864166 | stop processing: n_tokens = 2138, truncated = 0
llama-server | 11452.47.863.981 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.607
llama-server | 11452.47.864.660 I slot launch_slot_: id 0 | task 2864280 | processing task, is_child = 0
llama-server | 11452.53.955.873 I slot print_timing: id 0 | task 2864280 | n_gen = 153, tg = 50.10 t/s, tg_3s = 50.42 t/s
llama-server | 11452.56.988.151 I slot print_timing: id 0 | task 2864280 | n_gen = 307, tg = 50.44 t/s, tg_3s = 50.79 t/s
llama-server | 11453.00.035.809 I slot print_timing: id 0 | task 2864280 | n_gen = 473, tg = 51.79 t/s, tg_3s = 54.47 t/s
llama-server | 11453.03.072.027 I slot print_timing: id 0 | task 2864280 | n_gen = 617, tg = 50.70 t/s, tg_3s = 47.43 t/s
llama-server | 11453.06.125.327 I slot print_timing: id 0 | task 2864280 | n_gen = 767, tg = 50.38 t/s, tg_3s = 49.13 t/s
llama-server | 11453.09.181.905 I slot print_timing: id 0 | task 2864280 | n_gen = 929, tg = 50.82 t/s, tg_3s = 53.00 t/s
llama-server | 11453.12.241.156 I slot print_timing: id 0 | task 2864280 | n_gen = 1127, tg = 52.82 t/s, tg_3s = 64.72 t/s
llama-server | 11453.15.248.209 I slot print_timing: id 0 | task 2864280 | n_gen = 1367, tg = 56.15 t/s, tg_3s = 79.81 t/s
llama-server | 11453.15.904.232 I slot print_timing: id 0 | task 2864280 | prompt eval time = 3056.39 ms / 2906 tokens ( 1.05 ms per token, 950.79 tokens per second)
llama-server | 11453.15.904.235 I slot print_timing: id 0 | task 2864280 | eval time = 24982.51 ms / 1416 tokens ( 17.66 ms per token, 56.64 tokens per second)
llama-server | 11453.15.904.236 I slot print_timing: id 0 | task 2864280 | total time = 28038.90 ms / 4322 tokens
llama-server | 11453.15.904.236 I slot print_timing: id 0 | task 2864280 | graphs reused = 2773507
llama-server | 11453.15.904.239 I slot print_timing: id 0 | task 2864280 | draft acceptance = 0.62267 ( 1071 accepted / 1720 generated), mean len = 4.11
llama-server | 11453.15.904.383 I slot release: id 0 | task 2864280 | stop processing: n_tokens = 5613, truncated = 0
llama-server | 11453.16.023.489 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.825 (> 0.100 thold), f_keep = 0.231
llama-server | 11453.16.024.345 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 980.177 MiB)
llama-server | 11453.16.638.298 I slot launch_slot_: id 0 | task 2864629 | processing task, is_child = 0
llama-server | 11453.20.226.937 I slot print_timing: id 0 | task 2864629 | n_gen = 181, tg = 59.80 t/s, tg_3s = 60.13 t/s
llama-server | 11453.23.245.026 I slot print_timing: id 0 | task 2864629 | n_gen = 380, tg = 62.87 t/s, tg_3s = 65.94 t/s
llama-server | 11453.26.276.539 I slot print_timing: id 0 | task 2864629 | n_gen = 594, tg = 65.46 t/s, tg_3s = 70.59 t/s
llama-server | 11453.29.313.335 I slot print_timing: id 0 | task 2864629 | n_gen = 825, tg = 68.12 t/s, tg_3s = 76.07 t/s
llama-server | 11453.31.420.102 I slot print_timing: id 0 | task 2864629 | prompt eval time = 578.15 ms / 281 tokens ( 2.06 ms per token, 486.04 tokens per second)
llama-server | 11453.31.420.106 I slot print_timing: id 0 | task 2864629 | eval time = 14203.13 ms / 994 tokens ( 14.30 ms per token, 69.91 tokens per second)
llama-server | 11453.31.420.106 I slot print_timing: id 0 | task 2864629 | total time = 14781.28 ms / 1275 tokens
llama-server | 11453.31.420.107 I slot print_timing: id 0 | task 2864629 | graphs reused = 2773699
llama-server | 11453.31.420.110 I slot print_timing: id 0 | task 2864629 | draft acceptance = 0.80812 ( 796 accepted / 985 generated), mean len = 5.04
llama-server | 11453.31.420.219 I slot release: id 0 | task 2864629 | stop processing: n_tokens = 2566, truncated = 0
llama-server | 11453.38.053.846 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.505
llama-server | 11453.38.054.614 I slot launch_slot_: id 0 | task 2864829 | processing task, is_child = 0
llama-server | 11453.41.576.547 I slot print_timing: id 0 | task 2864829 | prompt processing, n_tokens = 3589, progress = 1.00, t = 3.08 s / 1165.84 tokens per second
llama-server | 11453.44.821.402 I slot print_timing: id 0 | task 2864829 | n_gen = 157, tg = 51.33 t/s, tg_3s = 51.65 t/s
llama-server | 11453.47.867.281 I slot print_timing: id 0 | task 2864829 | n_gen = 296, tg = 48.48 t/s, tg_3s = 45.64 t/s
llama-server | 11453.50.905.665 I slot print_timing: id 0 | task 2864829 | n_gen = 442, tg = 48.34 t/s, tg_3s = 48.05 t/s
llama-server | 11453.53.966.009 I slot print_timing: id 0 | task 2864829 | n_gen = 579, tg = 47.44 t/s, tg_3s = 44.77 t/s
llama-server | 11453.57.009.592 I slot print_timing: id 0 | task 2864829 | n_gen = 723, tg = 47.41 t/s, tg_3s = 47.31 t/s
llama-server | 11454.00.076.382 I slot print_timing: id 0 | task 2864829 | n_gen = 845, tg = 46.13 t/s, tg_3s = 39.78 t/s
llama-server | 11454.03.135.090 I slot print_timing: id 0 | task 2864829 | n_gen = 988, tg = 46.22 t/s, tg_3s = 46.75 t/s
llama-server | 11454.06.138.629 I slot print_timing: id 0 | task 2864829 | n_gen = 1121, tg = 45.98 t/s, tg_3s = 44.28 t/s
llama-server | 11454.08.057.268 W srv stop: cancel task, id_task = 2864829
llama-server | 11454.08.103.494 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 687166760654
llama-server | 11454.08.103.899 I slot launch_slot_: id 1 | task 2865196 | processing task, is_child = 0
llama-server | 11454.08.103.903 I slot release: id 0 | task 2864829 | stop processing: n_tokens = 6077, truncated = 0
llama-server | 11454.12.460.743 I slot print_timing: id 1 | task 2865196 | prompt processing, n_tokens = 4369, progress = 0.89, t = 4.20 s / 1041.15 tokens per second
llama-server | 11454.13.053.321 I slot print_timing: id 1 | task 2865196 | prompt processing, n_tokens = 4881, progress = 1.00, t = 4.48 s / 1090.23 tokens per second
llama-server | 11454.16.243.244 I slot print_timing: id 1 | task 2865196 | n_gen = 145, tg = 47.49 t/s, tg_3s = 47.82 t/s
llama-server | 11454.19.246.099 I slot print_timing: id 1 | task 2865196 | n_gen = 288, tg = 47.56 t/s, tg_3s = 47.62 t/s
llama-server | 11454.22.276.396 I slot print_timing: id 1 | task 2865196 | n_gen = 467, tg = 51.41 t/s, tg_3s = 59.07 t/s
llama-server | 11454.25.304.247 I slot print_timing: id 1 | task 2865196 | n_gen = 605, tg = 49.95 t/s, tg_3s = 45.58 t/s
llama-server | 11454.28.311.550 I slot print_timing: id 1 | task 2865196 | n_gen = 734, tg = 48.54 t/s, tg_3s = 42.90 t/s
llama-server | 11454.31.347.372 I slot print_timing: id 1 | task 2865196 | n_gen = 883, tg = 48.63 t/s, tg_3s = 49.08 t/s
llama-server | 11454.34.372.371 I slot print_timing: id 1 | task 2865196 | n_gen = 1047, tg = 49.43 t/s, tg_3s = 54.21 t/s
llama-server | 11454.37.409.429 I slot print_timing: id 1 | task 2865196 | n_gen = 1200, tg = 49.55 t/s, tg_3s = 50.38 t/s
llama-server | 11454.40.454.037 I slot print_timing: id 1 | task 2865196 | n_gen = 1379, tg = 50.58 t/s, tg_3s = 58.79 t/s
llama-server | 11454.43.491.289 I slot print_timing: id 1 | task 2865196 | n_gen = 1563, tg = 51.59 t/s, tg_3s = 60.58 t/s
llama-server | 11454.46.549.049 I slot print_timing: id 1 | task 2865196 | n_gen = 1734, tg = 51.98 t/s, tg_3s = 55.92 t/s
llama-server | 11454.49.620.820 I slot print_timing: id 1 | task 2865196 | n_gen = 1973, tg = 54.16 t/s, tg_3s = 77.81 t/s
llama-server | 11454.49.696.841 I slot print_timing: id 1 | task 2865196 | prompt eval time = 5107.02 ms / 4885 tokens ( 1.05 ms per token, 956.53 tokens per second)
llama-server | 11454.49.696.844 I slot print_timing: id 1 | task 2865196 | eval time = 36485.67 ms / 1977 tokens ( 18.46 ms per token, 54.16 tokens per second)
llama-server | 11454.49.696.845 I slot print_timing: id 1 | task 2865196 | total time = 41592.68 ms / 6862 tokens
llama-server | 11454.49.696.845 I slot print_timing: id 1 | task 2865196 | graphs reused = 2774528
llama-server | 11454.49.696.848 I slot print_timing: id 1 | task 2865196 | draft acceptance = 0.62162 ( 1495 accepted / 2405 generated), mean len = 4.11
llama-server | 11454.49.697.067 I slot release: id 1 | task 2865196 | stop processing: n_tokens = 6861, truncated = 0
llama-server | 11454.49.800.126 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.841 (> 0.100 thold), f_keep = 0.213
llama-server | 11454.49.800.856 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1130.687 MiB)
llama-server | 11454.50.536.336 I slot launch_slot_: id 0 | task 2865684 | processing task, is_child = 0
llama-server | 11454.50.537.279 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 970.302 MiB)
llama-server | 11454.54.893.495 I slot print_timing: id 0 | task 2865684 | n_gen = 190, tg = 62.85 t/s, tg_3s = 63.18 t/s
llama-server | 11454.57.907.278 I slot print_timing: id 0 | task 2865684 | n_gen = 401, tg = 66.43 t/s, tg_3s = 70.01 t/s
llama-server | 11455.00.931.078 I slot print_timing: id 0 | task 2865684 | n_gen = 616, tg = 67.99 t/s, tg_3s = 71.10 t/s
llama-server | 11455.03.960.464 I slot print_timing: id 0 | task 2865684 | n_gen = 862, tg = 71.31 t/s, tg_3s = 81.20 t/s
llama-server | 11455.04.103.864 I slot print_timing: id 0 | task 2865684 | prompt eval time = 528.27 ms / 251 tokens ( 2.10 ms per token, 475.14 tokens per second)
llama-server | 11455.04.103.868 I slot print_timing: id 0 | task 2865684 | eval time = 12217.58 ms / 870 tokens ( 14.06 ms per token, 71.13 tokens per second)
llama-server | 11455.04.103.869 I slot print_timing: id 0 | task 2865684 | total time = 12745.85 ms / 1121 tokens
llama-server | 11455.04.103.869 I slot print_timing: id 0 | task 2865684 | graphs reused = 2774694
llama-server | 11455.04.103.888 I slot print_timing: id 0 | task 2865684 | draft acceptance = 0.82235 ( 699 accepted / 850 generated), mean len = 5.11
llama-server | 11455.04.103.982 I slot release: id 0 | task 2865684 | stop processing: n_tokens = 2412, truncated = 0
llama-server | 11455.13.312.715 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.538
llama-server | 11455.13.313.537 I slot launch_slot_: id 0 | task 2865857 | processing task, is_child = 0
llama-server | 11455.19.379.445 I slot print_timing: id 0 | task 2865857 | n_gen = 178, tg = 58.04 t/s, tg_3s = 58.36 t/s
llama-server | 11455.22.381.396 I slot print_timing: id 0 | task 2865857 | n_gen = 322, tg = 53.04 t/s, tg_3s = 47.97 t/s
llama-server | 11455.25.412.742 I slot print_timing: id 0 | task 2865857 | n_gen = 455, tg = 49.98 t/s, tg_3s = 43.87 t/s
llama-server | 11455.28.439.830 I slot print_timing: id 0 | task 2865857 | n_gen = 615, tg = 50.70 t/s, tg_3s = 52.86 t/s
llama-server | 11455.31.491.778 I slot print_timing: id 0 | task 2865857 | n_gen = 772, tg = 50.85 t/s, tg_3s = 51.44 t/s
llama-server | 11455.34.546.588 I slot print_timing: id 0 | task 2865857 | n_gen = 938, tg = 51.44 t/s, tg_3s = 54.34 t/s
llama-server | 11455.37.591.847 I slot print_timing: id 0 | task 2865857 | n_gen = 1093, tg = 51.36 t/s, tg_3s = 50.90 t/s
llama-server | 11455.40.658.150 I slot print_timing: id 0 | task 2865857 | n_gen = 1264, tg = 51.91 t/s, tg_3s = 55.77 t/s
llama-server | 11455.43.315.407 W srv stop: cancel task, id_task = 2865857
llama-server | 11455.43.346.576 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 687305537119
llama-server | 11455.43.402.634 I slot launch_slot_: id 1 | task 2866235 | processing task, is_child = 0
llama-server | 11455.43.402.638 I slot release: id 0 | task 2865857 | stop processing: n_tokens = 5620, truncated = 0
llama-server | 11455.49.585.152 I slot print_timing: id 1 | task 2866235 | n_gen = 179, tg = 59.01 t/s, tg_3s = 59.34 t/s
llama-server | 11455.52.640.076 I slot print_timing: id 1 | task 2866235 | n_gen = 326, tg = 53.53 t/s, tg_3s = 48.12 t/s
llama-server | 11455.55.648.399 I slot print_timing: id 1 | task 2866235 | n_gen = 490, tg = 53.86 t/s, tg_3s = 54.52 t/s
llama-server | 11455.58.722.422 I slot print_timing: id 1 | task 2866235 | n_gen = 648, tg = 53.23 t/s, tg_3s = 51.40 t/s
llama-server | 11456.01.731.747 I slot print_timing: id 1 | task 2866235 | n_gen = 789, tg = 51.97 t/s, tg_3s = 46.85 t/s
llama-server | 11456.04.753.709 I slot print_timing: id 1 | task 2866235 | n_gen = 961, tg = 52.79 t/s, tg_3s = 56.92 t/s
llama-server | 11456.07.757.135 I slot print_timing: id 1 | task 2866235 | n_gen = 1082, tg = 51.02 t/s, tg_3s = 40.29 t/s
llama-server | 11456.10.785.391 I slot print_timing: id 1 | task 2866235 | n_gen = 1276, tg = 52.65 t/s, tg_3s = 64.06 t/s
llama-server | 11456.13.818.997 I slot print_timing: id 1 | task 2866235 | n_gen = 1485, tg = 54.46 t/s, tg_3s = 68.89 t/s
llama-server | 11456.16.836.074 I slot print_timing: id 1 | task 2866235 | n_gen = 1675, tg = 55.31 t/s, tg_3s = 62.97 t/s
llama-server | 11456.19.429.689 I slot print_timing: id 1 | task 2866235 | prompt eval time = 3165.73 ms / 2906 tokens ( 1.09 ms per token, 917.96 tokens per second)
llama-server | 11456.19.429.692 I slot print_timing: id 1 | task 2866235 | eval time = 32861.06 ms / 1872 tokens ( 17.56 ms per token, 56.94 tokens per second)
llama-server | 11456.19.429.693 I slot print_timing: id 1 | task 2866235 | total time = 36026.79 ms / 4778 tokens
llama-server | 11456.19.429.693 I slot print_timing: id 1 | task 2866235 | graphs reused = 2775489
llama-server | 11456.19.429.696 I slot print_timing: id 1 | task 2866235 | draft acceptance = 0.65826 ( 1435 accepted / 2180 generated), mean len = 4.29
llama-server | 11456.19.429.843 I slot release: id 1 | task 2866235 | stop processing: n_tokens = 6069, truncated = 0
llama-server | 11456.19.549.877 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.827 (> 0.100 thold), f_keep = 0.231
llama-server | 11456.20.177.161 I slot launch_slot_: id 0 | task 2866677 | processing task, is_child = 0
llama-server | 11456.20.178.319 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1136.292 MiB)
llama-server | 11456.24.457.075 I slot print_timing: id 0 | task 2866677 | n_gen = 190, tg = 62.95 t/s, tg_3s = 63.28 t/s
llama-server | 11456.27.467.899 I slot print_timing: id 0 | task 2866677 | n_gen = 389, tg = 64.53 t/s, tg_3s = 66.09 t/s
llama-server | 11456.30.493.073 I slot print_timing: id 0 | task 2866677 | n_gen = 641, tg = 70.81 t/s, tg_3s = 83.30 t/s
llama-server | 11456.30.851.124 I slot print_timing: id 0 | task 2866677 | prompt eval time = 565.22 ms / 277 tokens ( 2.04 ms per token, 490.07 tokens per second)
llama-server | 11456.30.851.127 I slot print_timing: id 0 | task 2866677 | eval time = 9396.37 ms / 668 tokens ( 14.09 ms per token, 70.98 tokens per second)
llama-server | 11456.30.851.127 I slot print_timing: id 0 | task 2866677 | total time = 9961.60 ms / 945 tokens
llama-server | 11456.30.851.128 I slot print_timing: id 0 | task 2866677 | graphs reused = 2775617
llama-server | 11456.30.851.131 I slot print_timing: id 0 | task 2866677 | draft acceptance = 0.81832 ( 536 accepted / 655 generated), mean len = 5.09
llama-server | 11456.30.851.220 I slot release: id 0 | task 2866677 | stop processing: n_tokens = 2236, truncated = 0
llama-server | 11456.38.369.618 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.249 (> 0.100 thold), f_keep = 0.580
llama-server | 11456.38.370.470 I slot launch_slot_: id 0 | task 2866811 | processing task, is_child = 0
llama-server | 11456.42.143.614 I slot print_timing: id 0 | task 2866811 | prompt processing, n_tokens = 3905, progress = 1.00, t = 3.33 s / 1173.29 tokens per second
llama-server | 11456.45.332.799 I slot print_timing: id 0 | task 2866811 | n_gen = 167, tg = 54.44 t/s, tg_3s = 54.76 t/s
llama-server | 11456.48.383.450 I slot print_timing: id 0 | task 2866811 | n_gen = 337, tg = 55.08 t/s, tg_3s = 55.73 t/s
llama-server | 11456.51.443.452 I slot print_timing: id 0 | task 2866811 | n_gen = 507, tg = 55.24 t/s, tg_3s = 55.56 t/s
llama-server | 11456.54.494.665 I slot print_timing: id 0 | task 2866811 | n_gen = 661, tg = 54.05 t/s, tg_3s = 50.47 t/s
llama-server | 11456.57.565.408 I slot print_timing: id 0 | task 2866811 | n_gen = 822, tg = 53.72 t/s, tg_3s = 52.43 t/s
llama-server | 11457.00.578.679 I slot print_timing: id 0 | task 2866811 | n_gen = 1000, tg = 54.60 t/s, tg_3s = 59.07 t/s
llama-server | 11457.03.645.746 I slot print_timing: id 0 | task 2866811 | n_gen = 1185, tg = 55.42 t/s, tg_3s = 60.32 t/s
llama-server | 11457.06.667.075 I slot print_timing: id 0 | task 2866811 | n_gen = 1392, tg = 57.05 t/s, tg_3s = 68.51 t/s
llama-server | 11457.08.372.156 W srv stop: cancel task, id_task = 2866811
llama-server | 11457.08.373.256 I slot release: id 0 | task 2866811 | stop processing: n_tokens = 6729, truncated = 0
llama-server | 11457.08.373.278 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 0.773
llama-server | 11457.08.373.717 I slot launch_slot_: id 0 | task 2867173 | processing task, is_child = 0
llama-server | 11457.11.604.631 I slot print_timing: id 0 | task 2867173 | n_gen = 166, tg = 53.77 t/s, tg_3s = 54.09 t/s
llama-server | 11457.14.671.505 I slot print_timing: id 0 | task 2867173 | n_gen = 323, tg = 52.48 t/s, tg_3s = 51.19 t/s
llama-server | 11457.17.744.092 I slot print_timing: id 0 | task 2867173 | n_gen = 489, tg = 53.00 t/s, tg_3s = 54.03 t/s
llama-server | 11457.20.745.287 I slot print_timing: id 0 | task 2867173 | n_gen = 651, tg = 53.24 t/s, tg_3s = 53.98 t/s
llama-server | 11457.23.754.563 I slot print_timing: id 0 | task 2867173 | n_gen = 795, tg = 52.17 t/s, tg_3s = 47.85 t/s
llama-server | 11457.26.763.983 I slot print_timing: id 0 | task 2867173 | n_gen = 954, tg = 52.28 t/s, tg_3s = 52.83 t/s
llama-server | 11457.29.773.379 I slot print_timing: id 0 | task 2867173 | n_gen = 1151, tg = 54.15 t/s, tg_3s = 65.46 t/s
llama-server | 11457.32.802.539 I slot print_timing: id 0 | task 2867173 | n_gen = 1341, tg = 55.22 t/s, tg_3s = 62.72 t/s
llama-server | 11457.35.840.253 I slot print_timing: id 0 | task 2867173 | n_gen = 1586, tg = 58.05 t/s, tg_3s = 80.65 t/s
llama-server | 11457.36.354.932 I slot print_timing: id 0 | task 2867173 | prompt eval time = 161.79 ms / 4 tokens ( 40.45 ms per token, 24.72 tokens per second)
llama-server | 11457.36.354.935 I slot print_timing: id 0 | task 2867173 | eval time = 27818.92 ms / 1625 tokens ( 17.13 ms per token, 58.38 tokens per second)
llama-server | 11457.36.354.936 I slot print_timing: id 0 | task 2867173 | total time = 27980.71 ms / 1629 tokens
llama-server | 11457.36.354.937 I slot print_timing: id 0 | task 2867173 | graphs reused = 2776339
llama-server | 11457.36.354.939 I slot print_timing: id 0 | task 2867173 | draft acceptance = 0.65699 ( 1245 accepted / 1895 generated), mean len = 4.28
llama-server | 11457.36.355.112 I slot release: id 0 | task 2867173 | stop processing: n_tokens = 6825, truncated = 0
llama-server | 11457.36.480.464 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.830 (> 0.100 thold), f_keep = 0.190
llama-server | 11457.36.481.353 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.297 MiB)
llama-server | 11457.37.107.854 I slot launch_slot_: id 0 | task 2867555 | processing task, is_child = 0
llama-server | 11457.40.695.704 I slot print_timing: id 0 | task 2867555 | n_gen = 203, tg = 66.87 t/s, tg_3s = 67.20 t/s
llama-server | 11457.43.717.210 I slot print_timing: id 0 | task 2867555 | n_gen = 444, tg = 73.32 t/s, tg_3s = 79.76 t/s
llama-server | 11457.44.381.163 I slot print_timing: id 0 | task 2867555 | prompt eval time = 566.63 ms / 270 tokens ( 2.10 ms per token, 476.50 tokens per second)
llama-server | 11457.44.381.167 I slot print_timing: id 0 | task 2867555 | eval time = 6706.14 ms / 493 tokens ( 13.63 ms per token, 73.37 tokens per second)
llama-server | 11457.44.381.167 I slot print_timing: id 0 | task 2867555 | total time = 7272.78 ms / 763 tokens
llama-server | 11457.44.381.168 I slot print_timing: id 0 | task 2867555 | graphs reused = 2776429
llama-server | 11457.44.381.171 I slot print_timing: id 0 | task 2867555 | draft acceptance = 0.85806 ( 399 accepted / 465 generated), mean len = 5.29
llama-server | 11457.44.381.266 I slot release: id 0 | task 2867555 | stop processing: n_tokens = 2054, truncated = 0
llama-server | 11457.53.555.979 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.274 (> 0.100 thold), f_keep = 0.631
llama-server | 11457.53.556.605 I slot launch_slot_: id 0 | task 2867651 | processing task, is_child = 0
llama-server | 11458.00.062.895 I slot print_timing: id 0 | task 2867651 | n_gen = 131, tg = 42.85 t/s, tg_3s = 43.17 t/s
llama-server | 11458.03.099.937 I slot print_timing: id 0 | task 2867651 | n_gen = 303, tg = 49.74 t/s, tg_3s = 56.63 t/s
llama-server | 11458.06.147.360 I slot print_timing: id 0 | task 2867651 | n_gen = 463, tg = 50.67 t/s, tg_3s = 52.50 t/s
llama-server | 11458.09.180.998 I slot print_timing: id 0 | task 2867651 | n_gen = 599, tg = 49.21 t/s, tg_3s = 44.83 t/s
llama-server | 11458.12.248.336 I slot print_timing: id 0 | task 2867651 | n_gen = 776, tg = 50.92 t/s, tg_3s = 57.70 t/s
llama-server | 11458.15.306.332 I slot print_timing: id 0 | task 2867651 | n_gen = 924, tg = 50.50 t/s, tg_3s = 48.40 t/s
llama-server | 11458.18.362.810 I slot print_timing: id 0 | task 2867651 | n_gen = 1095, tg = 51.28 t/s, tg_3s = 55.95 t/s
llama-server | 11458.21.371.834 I slot print_timing: id 0 | task 2867651 | n_gen = 1274, tg = 52.29 t/s, tg_3s = 59.49 t/s
llama-server | 11458.23.559.792 W srv stop: cancel task, id_task = 2867651
llama-server | 11458.23.583.523 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 687395269895
llama-server | 11458.23.583.901 I slot launch_slot_: id 1 | task 2868021 | processing task, is_child = 0
llama-server | 11458.23.583.904 I slot release: id 0 | task 2867651 | stop processing: n_tokens = 6151, truncated = 0
llama-server | 11458.27.744.962 I slot print_timing: id 1 | task 2868021 | prompt processing, n_tokens = 4221, progress = 0.89, t = 3.74 s / 1128.10 tokens per second
llama-server | 11458.28.330.848 I slot print_timing: id 1 | task 2868021 | prompt processing, n_tokens = 4733, progress = 1.00, t = 4.27 s / 1107.44 tokens per second
llama-server | 11458.31.510.848 I slot print_timing: id 1 | task 2868021 | n_gen = 131, tg = 43.05 t/s, tg_3s = 43.38 t/s
llama-server | 11458.34.582.445 I slot print_timing: id 1 | task 2868021 | n_gen = 287, tg = 46.95 t/s, tg_3s = 50.79 t/s
llama-server | 11458.37.598.035 I slot print_timing: id 1 | task 2868021 | n_gen = 437, tg = 47.88 t/s, tg_3s = 49.74 t/s
llama-server | 11458.40.606.076 I slot print_timing: id 1 | task 2868021 | n_gen = 601, tg = 49.53 t/s, tg_3s = 54.52 t/s
llama-server | 11458.43.630.650 I slot print_timing: id 1 | task 2868021 | n_gen = 741, tg = 48.88 t/s, tg_3s = 46.29 t/s
llama-server | 11458.46.661.170 I slot print_timing: id 1 | task 2868021 | n_gen = 907, tg = 49.86 t/s, tg_3s = 54.78 t/s
llama-server | 11458.49.686.482 I slot print_timing: id 1 | task 2868021 | n_gen = 1105, tg = 52.09 t/s, tg_3s = 65.45 t/s
llama-server | 11458.52.739.338 I slot print_timing: id 1 | task 2868021 | n_gen = 1336, tg = 55.06 t/s, tg_3s = 75.67 t/s
llama-server | 11458.52.891.064 I slot print_timing: id 1 | task 2868021 | prompt eval time = 4907.28 ms / 4737 tokens ( 1.04 ms per token, 965.30 tokens per second)
llama-server | 11458.52.891.067 I slot print_timing: id 1 | task 2868021 | eval time = 24399.62 ms / 1346 tokens ( 18.14 ms per token, 55.12 tokens per second)
llama-server | 11458.52.891.067 I slot print_timing: id 1 | task 2868021 | total time = 29306.90 ms / 6083 tokens
llama-server | 11458.52.891.068 I slot print_timing: id 1 | task 2868021 | graphs reused = 2777104
llama-server | 11458.52.891.071 I slot print_timing: id 1 | task 2868021 | draft acceptance = 0.63282 ( 1022 accepted / 1615 generated), mean len = 4.16
llama-server | 11458.52.891.289 I slot release: id 1 | task 2868021 | stop processing: n_tokens = 6082, truncated = 0
llama-server | 11458.53.004.684 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.825 (> 0.100 thold), f_keep = 0.211
llama-server | 11458.53.005.411 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1106.468 MiB)
llama-server | 11458.53.666.315 I slot launch_slot_: id 0 | task 2868351 | processing task, is_child = 0
llama-server | 11458.53.666.902 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.616 MiB)
llama-server | 11458.57.835.312 I slot print_timing: id 0 | task 2868351 | n_gen = 193, tg = 63.87 t/s, tg_3s = 64.20 t/s
llama-server | 11459.00.850.158 I slot print_timing: id 0 | task 2868351 | n_gen = 404, tg = 66.93 t/s, tg_3s = 69.99 t/s
llama-server | 11459.03.869.080 I slot print_timing: id 0 | task 2868351 | n_gen = 628, tg = 69.36 t/s, tg_3s = 74.20 t/s
llama-server | 11459.05.158.414 I slot print_timing: id 0 | task 2868351 | prompt eval time = 568.53 ms / 281 tokens ( 2.02 ms per token, 494.26 tokens per second)
llama-server | 11459.05.158.417 I slot print_timing: id 0 | task 2868351 | eval time = 10329.24 ms / 732 tokens ( 14.13 ms per token, 70.77 tokens per second)
llama-server | 11459.05.158.418 I slot print_timing: id 0 | task 2868351 | total time = 10897.77 ms / 1013 tokens
llama-server | 11459.05.158.419 I slot print_timing: id 0 | task 2868351 | graphs reused = 2777244
llama-server | 11459.05.158.422 I slot print_timing: id 0 | task 2868351 | draft acceptance = 0.81528 ( 587 accepted / 720 generated), mean len = 5.08
llama-server | 11459.05.158.512 I slot release: id 0 | task 2868351 | stop processing: n_tokens = 2304, truncated = 0
llama-server | 11459.13.726.405 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.270 (> 0.100 thold), f_keep = 0.563
llama-server | 11459.13.727.268 I slot launch_slot_: id 0 | task 2868498 | processing task, is_child = 0
llama-server | 11459.20.389.525 I slot print_timing: id 0 | task 2868498 | n_gen = 175, tg = 56.98 t/s, tg_3s = 57.30 t/s
llama-server | 11459.23.431.703 I slot print_timing: id 0 | task 2868498 | n_gen = 354, tg = 57.91 t/s, tg_3s = 58.84 t/s
llama-server | 11459.26.468.899 I slot print_timing: id 0 | task 2868498 | n_gen = 501, tg = 54.74 t/s, tg_3s = 48.40 t/s
llama-server | 11459.29.523.087 I slot print_timing: id 0 | task 2868498 | n_gen = 657, tg = 53.83 t/s, tg_3s = 51.08 t/s
llama-server | 11459.32.561.377 I slot print_timing: id 0 | task 2868498 | n_gen = 803, tg = 52.67 t/s, tg_3s = 48.05 t/s
llama-server | 11459.35.566.862 I slot print_timing: id 0 | task 2868498 | n_gen = 993, tg = 54.41 t/s, tg_3s = 63.22 t/s
llama-server | 11459.38.637.292 I slot print_timing: id 0 | task 2868498 | n_gen = 1138, tg = 53.38 t/s, tg_3s = 47.22 t/s
llama-server | 11459.41.692.731 I slot print_timing: id 0 | task 2868498 | n_gen = 1292, tg = 53.00 t/s, tg_3s = 50.40 t/s
llama-server | 11459.43.730.846 W srv stop: cancel task, id_task = 2868498
llama-server | 11459.43.760.664 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 687548731343
llama-server | 11459.43.812.036 I slot launch_slot_: id 1 | task 2868866 | processing task, is_child = 0
llama-server | 11459.43.812.040 I slot release: id 0 | task 2868498 | stop processing: n_tokens = 6246, truncated = 0
llama-server | 11459.47.453.155 I slot print_timing: id 1 | task 2868866 | prompt processing, n_tokens = 3506, progress = 1.00, t = 3.17 s / 1106.68 tokens per second
llama-server | 11459.50.677.336 I slot print_timing: id 1 | task 2868866 | n_gen = 176, tg = 58.07 t/s, tg_3s = 58.40 t/s
llama-server | 11459.53.701.333 I slot print_timing: id 1 | task 2868866 | n_gen = 345, tg = 56.98 t/s, tg_3s = 55.89 t/s
llama-server | 11459.56.725.595 I slot print_timing: id 1 | task 2868866 | n_gen = 485, tg = 53.41 t/s, tg_3s = 46.29 t/s
llama-server | 11459.59.736.551 I slot print_timing: id 1 | task 2868866 | n_gen = 649, tg = 53.67 t/s, tg_3s = 54.47 t/s
llama-server | 11460.02.777.552 I slot print_timing: id 1 | task 2868866 | n_gen = 840, tg = 55.51 t/s, tg_3s = 62.81 t/s
llama-server | 11460.05.826.046 I slot print_timing: id 1 | task 2868866 | n_gen = 1039, tg = 57.15 t/s, tg_3s = 65.28 t/s
llama-server | 11460.08.872.149 I slot print_timing: id 1 | task 2868866 | n_gen = 1254, tg = 59.08 t/s, tg_3s = 70.58 t/s
llama-server | 11460.10.543.665 I slot print_timing: id 1 | task 2868866 | prompt eval time = 3851.51 ms / 3510 tokens ( 1.10 ms per token, 911.33 tokens per second)
llama-server | 11460.10.543.668 I slot print_timing: id 1 | task 2868866 | eval time = 22879.86 ms / 1380 tokens ( 16.59 ms per token, 60.27 tokens per second)
llama-server | 11460.10.543.669 I slot print_timing: id 1 | task 2868866 | total time = 26731.36 ms / 4890 tokens
llama-server | 11460.10.543.669 I slot print_timing: id 1 | task 2868866 | graphs reused = 2777896
llama-server | 11460.10.543.672 I slot print_timing: id 1 | task 2868866 | draft acceptance = 0.71325 ( 1077 accepted / 1510 generated), mean len = 4.57
llama-server | 11460.10.543.832 I slot release: id 1 | task 2868866 | stop processing: n_tokens = 6181, truncated = 0
llama-server | 11460.10.639.256 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.208
llama-server | 11460.11.249.616 I slot launch_slot_: id 0 | task 2869174 | processing task, is_child = 0
llama-server | 11460.11.250.837 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1116.024 MiB)
llama-server | 11460.15.649.742 I slot print_timing: id 0 | task 2869174 | n_gen = 186, tg = 61.63 t/s, tg_3s = 61.95 t/s
llama-server | 11460.18.671.497 I slot print_timing: id 0 | task 2869174 | n_gen = 430, tg = 71.22 t/s, tg_3s = 80.75 t/s
llama-server | 11460.21.268.702 I slot print_timing: id 0 | task 2869174 | prompt eval time = 565.76 ms / 266 tokens ( 2.13 ms per token, 470.16 tokens per second)
llama-server | 11460.21.268.706 I slot print_timing: id 0 | task 2869174 | eval time = 8620.97 ms / 642 tokens ( 13.45 ms per token, 74.35 tokens per second)
llama-server | 11460.21.268.706 I slot print_timing: id 0 | task 2869174 | total time = 9186.73 ms / 908 tokens
llama-server | 11460.21.268.707 I slot print_timing: id 0 | task 2869174 | graphs reused = 2778013
llama-server | 11460.21.268.710 I slot print_timing: id 0 | task 2869174 | draft acceptance = 0.86833 ( 521 accepted / 600 generated), mean len = 5.34
llama-server | 11460.21.268.796 I slot release: id 0 | task 2869174 | stop processing: n_tokens = 2199, truncated = 0
llama-server | 11460.28.646.071 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.590
llama-server | 11460.28.646.722 I slot launch_slot_: id 0 | task 2869297 | processing task, is_child = 0
llama-server | 11460.34.753.515 I slot print_timing: id 0 | task 2869297 | n_gen = 160, tg = 52.32 t/s, tg_3s = 52.64 t/s
llama-server | 11460.37.764.477 I slot print_timing: id 0 | task 2869297 | n_gen = 307, tg = 50.58 t/s, tg_3s = 48.82 t/s
llama-server | 11460.40.801.011 I slot print_timing: id 0 | task 2869297 | n_gen = 461, tg = 50.62 t/s, tg_3s = 50.72 t/s
llama-server | 11460.43.833.575 I slot print_timing: id 0 | task 2869297 | n_gen = 647, tg = 53.30 t/s, tg_3s = 61.33 t/s
llama-server | 11460.46.894.898 I slot print_timing: id 0 | task 2869297 | n_gen = 860, tg = 56.59 t/s, tg_3s = 69.58 t/s
llama-server | 11460.49.960.609 I slot print_timing: id 0 | task 2869297 | n_gen = 1021, tg = 55.90 t/s, tg_3s = 52.52 t/s
llama-server | 11460.52.962.155 I slot print_timing: id 0 | task 2869297 | n_gen = 1221, tg = 57.42 t/s, tg_3s = 66.63 t/s
llama-server | 11460.55.299.738 I slot print_timing: id 0 | task 2869297 | prompt eval time = 3067.11 ms / 2906 tokens ( 1.06 ms per token, 947.47 tokens per second)
llama-server | 11460.55.299.741 I slot print_timing: id 0 | task 2869297 | eval time = 23585.22 ms / 1411 tokens ( 16.73 ms per token, 59.78 tokens per second)
llama-server | 11460.55.299.741 I slot print_timing: id 0 | task 2869297 | total time = 26652.33 ms / 4317 tokens
llama-server | 11460.55.299.742 I slot print_timing: id 0 | task 2869297 | graphs reused = 2778332
llama-server | 11460.55.299.745 I slot print_timing: id 0 | task 2869297 | draft acceptance = 0.66831 ( 1086 accepted / 1625 generated), mean len = 4.34
llama-server | 11460.55.299.899 I slot release: id 0 | task 2869297 | stop processing: n_tokens = 5609, truncated = 0
llama-server | 11460.55.417.190 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.821 (> 0.100 thold), f_keep = 0.231
llama-server | 11460.55.417.887 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 972.031 MiB)
llama-server | 11460.56.085.797 I slot launch_slot_: id 0 | task 2869627 | processing task, is_child = 0
llama-server | 11460.59.652.798 I slot print_timing: id 0 | task 2869627 | n_gen = 193, tg = 63.95 t/s, tg_3s = 64.28 t/s
llama-server | 11461.02.656.733 I slot print_timing: id 0 | task 2869627 | n_gen = 364, tg = 60.44 t/s, tg_3s = 56.93 t/s
llama-server | 11461.05.672.091 I slot print_timing: id 0 | task 2869627 | n_gen = 560, tg = 61.96 t/s, tg_3s = 65.00 t/s
llama-server | 11461.08.696.979 I slot print_timing: id 0 | task 2869627 | n_gen = 764, tg = 63.34 t/s, tg_3s = 67.44 t/s
llama-server | 11461.11.705.476 I slot print_timing: id 0 | task 2869627 | n_gen = 959, tg = 63.63 t/s, tg_3s = 64.82 t/s
llama-server | 11461.13.879.708 I slot print_timing: id 0 | task 2869627 | prompt eval time = 564.05 ms / 288 tokens ( 1.96 ms per token, 510.59 tokens per second)
llama-server | 11461.13.879.711 I slot print_timing: id 0 | task 2869627 | eval time = 17229.35 ms / 1134 tokens ( 15.21 ms per token, 65.76 tokens per second)
llama-server | 11461.13.879.712 I slot print_timing: id 0 | task 2869627 | total time = 17793.40 ms / 1422 tokens
llama-server | 11461.13.879.712 I slot print_timing: id 0 | task 2869627 | graphs reused = 2778567
llama-server | 11461.13.879.716 I slot print_timing: id 0 | task 2869627 | draft acceptance = 0.74417 ( 893 accepted / 1200 generated), mean len = 4.72
llama-server | 11461.13.879.806 I slot release: id 0 | task 2869627 | stop processing: n_tokens = 2713, truncated = 0
llama-server | 11461.18.926.064 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.266 (> 0.100 thold), f_keep = 0.478
llama-server | 11461.18.926.924 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1115.778 MiB)
llama-server | 11461.19.447.963 I slot launch_slot_: id 0 | task 2869870 | processing task, is_child = 0
llama-server | 11461.25.962.412 I slot print_timing: id 0 | task 2869870 | n_gen = 168, tg = 54.85 t/s, tg_3s = 55.17 t/s
llama-server | 11461.29.022.774 I slot print_timing: id 0 | task 2869870 | n_gen = 342, tg = 55.85 t/s, tg_3s = 56.86 t/s
llama-server | 11461.32.086.301 I slot print_timing: id 0 | task 2869870 | n_gen = 505, tg = 54.97 t/s, tg_3s = 53.21 t/s
llama-server | 11461.35.138.448 I slot print_timing: id 0 | task 2869870 | n_gen = 689, tg = 56.30 t/s, tg_3s = 60.29 t/s
llama-server | 11461.38.139.914 I slot print_timing: id 0 | task 2869870 | n_gen = 843, tg = 55.31 t/s, tg_3s = 51.31 t/s
llama-server | 11461.41.203.206 I slot print_timing: id 0 | task 2869870 | n_gen = 1000, tg = 54.63 t/s, tg_3s = 51.25 t/s
llama-server | 11461.44.220.982 I slot print_timing: id 0 | task 2869870 | n_gen = 1202, tg = 56.38 t/s, tg_3s = 66.94 t/s
llama-server | 11461.47.246.399 I slot print_timing: id 0 | task 2869870 | n_gen = 1402, tg = 57.59 t/s, tg_3s = 66.11 t/s
llama-server | 11461.48.929.487 W srv stop: cancel task, id_task = 2869870
llama-server | 11461.48.929.656 I slot release: id 0 | task 2869870 | stop processing: n_tokens = 6363, truncated = 0
llama-server | 11461.48.929.693 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 1.000 (> 0.100 thold), f_keep = 0.766
llama-server | 11461.48.930.081 I slot launch_slot_: id 0 | task 2870231 | processing task, is_child = 0
llama-server | 11461.52.162.407 I slot print_timing: id 0 | task 2870231 | n_gen = 168, tg = 54.46 t/s, tg_3s = 54.78 t/s
llama-server | 11461.55.165.936 I slot print_timing: id 0 | task 2870231 | n_gen = 333, tg = 54.69 t/s, tg_3s = 54.94 t/s
llama-server | 11461.58.223.284 I slot print_timing: id 0 | task 2870231 | n_gen = 493, tg = 53.90 t/s, tg_3s = 52.33 t/s
llama-server | 11462.01.230.618 I slot print_timing: id 0 | task 2870231 | n_gen = 655, tg = 53.89 t/s, tg_3s = 53.87 t/s
llama-server | 11462.04.233.896 I slot print_timing: id 0 | task 2870231 | n_gen = 817, tg = 53.90 t/s, tg_3s = 53.94 t/s
llama-server | 11462.07.296.610 I slot print_timing: id 0 | task 2870231 | n_gen = 973, tg = 53.40 t/s, tg_3s = 50.94 t/s
llama-server | 11462.10.310.732 I slot print_timing: id 0 | task 2870231 | n_gen = 1132, tg = 53.31 t/s, tg_3s = 52.75 t/s
llama-server | 11462.13.327.875 I slot print_timing: id 0 | task 2870231 | n_gen = 1296, tg = 53.44 t/s, tg_3s = 54.36 t/s
llama-server | 11462.16.339.852 I slot print_timing: id 0 | task 2870231 | n_gen = 1526, tg = 55.98 t/s, tg_3s = 76.36 t/s
llama-server | 11462.19.372.875 I slot print_timing: id 0 | task 2870231 | n_gen = 1758, tg = 58.03 t/s, tg_3s = 76.49 t/s
llama-server | 11462.19.906.936 I slot print_timing: id 0 | task 2870231 | prompt eval time = 165.15 ms / 4 tokens ( 41.29 ms per token, 24.22 tokens per second)
llama-server | 11462.19.906.939 I slot print_timing: id 0 | task 2870231 | eval time = 30811.19 ms / 1798 tokens ( 17.15 ms per token, 58.32 tokens per second)
llama-server | 11462.19.906.940 I slot print_timing: id 0 | task 2870231 | total time = 30976.34 ms / 1802 tokens
llama-server | 11462.19.906.940 I slot print_timing: id 0 | task 2870231 | graphs reused = 2779329
llama-server | 11462.19.906.943 I slot print_timing: id 0 | task 2870231 | draft acceptance = 0.65571 ( 1377 accepted / 2100 generated), mean len = 4.28
llama-server | 11462.19.907.110 I slot release: id 0 | task 2870231 | stop processing: n_tokens = 6670, truncated = 0
llama-server | 11462.20.053.834 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.818 (> 0.100 thold), f_keep = 0.194
llama-server | 11462.20.054.773 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1140.914 MiB)
llama-server | 11462.20.791.500 I slot launch_slot_: id 0 | task 2870654 | processing task, is_child = 0
llama-server | 11462.24.381.126 I slot print_timing: id 0 | task 2870654 | n_gen = 190, tg = 62.74 t/s, tg_3s = 63.06 t/s
llama-server | 11462.27.397.843 I slot print_timing: id 0 | task 2870654 | n_gen = 381, tg = 63.03 t/s, tg_3s = 63.31 t/s
llama-server | 11462.30.416.654 I slot print_timing: id 0 | task 2870654 | n_gen = 591, tg = 65.21 t/s, tg_3s = 69.56 t/s
llama-server | 11462.32.663.131 I slot print_timing: id 0 | task 2870654 | prompt eval time = 576.55 ms / 294 tokens ( 1.96 ms per token, 509.93 tokens per second)
llama-server | 11462.32.663.135 I slot print_timing: id 0 | task 2870654 | eval time = 11294.56 ms / 776 tokens ( 14.57 ms per token, 68.62 tokens per second)
llama-server | 11462.32.663.135 I slot print_timing: id 0 | task 2870654 | total time = 11871.11 ms / 1070 tokens
llama-server | 11462.32.663.136 I slot print_timing: id 0 | task 2870654 | graphs reused = 2779482
llama-server | 11462.32.663.147 I slot print_timing: id 0 | task 2870654 | draft acceptance = 0.78854 ( 619 accepted / 785 generated), mean len = 4.94
llama-server | 11462.32.663.229 I slot release: id 0 | task 2870654 | stop processing: n_tokens = 2362, truncated = 0
llama-server | 11462.39.048.113 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.168 (> 0.100 thold), f_keep = 0.549
llama-server | 11462.39.048.750 I slot launch_slot_: id 0 | task 2870814 | processing task, is_child = 0
llama-server | 11462.42.770.067 I slot print_timing: id 0 | task 2870814 | prompt processing, n_tokens = 4096, progress = 0.70, t = 3.17 s / 1291.21 tokens per second
llama-server | 11462.44.428.388 I slot print_timing: id 0 | task 2870814 | prompt processing, n_tokens = 5890, progress = 0.93, t = 5.00 s / 1177.31 tokens per second
llama-server | 11462.45.060.401 I slot print_timing: id 0 | task 2870814 | prompt processing, n_tokens = 6402, progress = 1.00, t = 5.56 s / 1152.06 tokens per second
llama-server | 11462.48.222.974 I slot print_timing: id 0 | task 2870814 | n_gen = 164, tg = 53.95 t/s, tg_3s = 54.28 t/s
llama-server | 11462.51.251.728 I slot print_timing: id 0 | task 2870814 | n_gen = 334, tg = 55.04 t/s, tg_3s = 56.13 t/s
llama-server | 11462.54.265.168 I slot print_timing: id 0 | task 2870814 | n_gen = 475, tg = 52.30 t/s, tg_3s = 46.79 t/s
llama-server | 11462.57.294.073 I slot print_timing: id 0 | task 2870814 | n_gen = 597, tg = 49.29 t/s, tg_3s = 40.28 t/s
llama-server | 11463.00.338.082 I slot print_timing: id 0 | task 2870814 | n_gen = 752, tg = 49.62 t/s, tg_3s = 50.92 t/s
llama-server | 11463.03.366.710 I slot print_timing: id 0 | task 2870814 | n_gen = 888, tg = 48.83 t/s, tg_3s = 44.90 t/s
llama-server | 11463.06.425.742 I slot print_timing: id 0 | task 2870814 | n_gen = 1085, tg = 51.07 t/s, tg_3s = 64.40 t/s
llama-server | 11463.09.052.019 W srv stop: cancel task, id_task = 2870814
llama-server | 11463.09.099.587 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 687626383883
llama-server | 11463.09.099.935 I slot launch_slot_: id 1 | task 2871143 | processing task, is_child = 0
llama-server | 11463.09.099.938 I slot release: id 0 | task 2870814 | stop processing: n_tokens = 8944, truncated = 0
llama-server | 11463.14.327.016 I slot print_timing: id 1 | task 2871143 | prompt processing, n_tokens = 5388, progress = 0.70, t = 4.64 s / 1160.52 tokens per second
llama-server | 11463.16.139.046 I slot print_timing: id 1 | task 2871143 | prompt processing, n_tokens = 7182, progress = 0.93, t = 6.64 s / 1082.43 tokens per second
llama-server | 11463.16.736.308 I slot print_timing: id 1 | task 2871143 | prompt processing, n_tokens = 7694, progress = 1.00, t = 7.14 s / 1077.95 tokens per second
llama-server | 11463.19.926.910 I slot print_timing: id 1 | task 2871143 | n_gen = 173, tg = 56.42 t/s, tg_3s = 56.75 t/s
llama-server | 11463.22.972.511 I slot print_timing: id 1 | task 2871143 | n_gen = 325, tg = 53.17 t/s, tg_3s = 49.91 t/s
llama-server | 11463.26.010.789 I slot print_timing: id 1 | task 2871143 | n_gen = 473, tg = 51.69 t/s, tg_3s = 48.71 t/s
llama-server | 11463.29.059.869 I slot print_timing: id 1 | task 2871143 | n_gen = 621, tg = 50.90 t/s, tg_3s = 48.54 t/s
llama-server | 11463.32.091.099 I slot print_timing: id 1 | task 2871143 | n_gen = 756, tg = 49.63 t/s, tg_3s = 44.54 t/s
llama-server | 11463.35.155.192 I slot print_timing: id 1 | task 2871143 | n_gen = 956, tg = 52.25 t/s, tg_3s = 65.27 t/s
llama-server | 11463.38.216.582 I slot print_timing: id 1 | task 2871143 | n_gen = 1118, tg = 52.35 t/s, tg_3s = 52.92 t/s
llama-server | 11463.41.256.276 I slot print_timing: id 1 | task 2871143 | n_gen = 1227, tg = 50.29 t/s, tg_3s = 35.86 t/s
llama-server | 11463.44.328.868 I slot print_timing: id 1 | task 2871143 | n_gen = 1400, tg = 50.96 t/s, tg_3s = 56.30 t/s
llama-server | 11463.47.333.993 I slot print_timing: id 1 | task 2871143 | n_gen = 1579, tg = 51.81 t/s, tg_3s = 59.56 t/s
llama-server | 11463.50.341.248 I slot print_timing: id 1 | task 2871143 | n_gen = 1798, tg = 53.70 t/s, tg_3s = 72.82 t/s
llama-server | 11463.52.316.252 I slot print_timing: id 1 | task 2871143 | prompt eval time = 7778.36 ms / 7698 tokens ( 1.01 ms per token, 989.67 tokens per second)
llama-server | 11463.52.316.256 I slot print_timing: id 1 | task 2871143 | eval time = 35437.69 ms / 1947 tokens ( 18.21 ms per token, 54.91 tokens per second)
llama-server | 11463.52.316.257 I slot print_timing: id 1 | task 2871143 | total time = 43216.06 ms / 9645 tokens
llama-server | 11463.52.316.258 I slot print_timing: id 1 | task 2871143 | graphs reused = 2780244
llama-server | 11463.52.316.262 I slot print_timing: id 1 | task 2871143 | draft acceptance = 0.66150 ( 1495 accepted / 2260 generated), mean len = 4.31
llama-server | 11463.52.316.539 I slot release: id 1 | task 2871143 | stop processing: n_tokens = 9645, truncated = 0
llama-server | 11463.52.434.125 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.824 (> 0.100 thold), f_keep = 0.145
llama-server | 11463.53.162.514 I slot launch_slot_: id 0 | task 2871603 | processing task, is_child = 0
llama-server | 11463.53.164.021 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1118.484 MiB)
llama-server | 11463.57.443.136 I slot print_timing: id 0 | task 2871603 | n_gen = 199, tg = 65.89 t/s, tg_3s = 66.22 t/s
llama-server | 11464.00.448.050 I slot print_timing: id 0 | task 2871603 | n_gen = 376, tg = 62.40 t/s, tg_3s = 58.90 t/s
llama-server | 11464.03.471.030 I slot print_timing: id 0 | task 2871603 | n_gen = 613, tg = 67.75 t/s, tg_3s = 78.40 t/s
llama-server | 11464.06.502.077 I slot print_timing: id 0 | task 2871603 | n_gen = 863, tg = 71.45 t/s, tg_3s = 82.48 t/s
llama-server | 11464.06.859.735 I slot print_timing: id 0 | task 2871603 | prompt eval time = 568.98 ms / 282 tokens ( 2.02 ms per token, 495.63 tokens per second)
llama-server | 11464.06.859.739 I slot print_timing: id 0 | task 2871603 | eval time = 12421.58 ms / 892 tokens ( 13.94 ms per token, 71.73 tokens per second)
llama-server | 11464.06.859.740 I slot print_timing: id 0 | task 2871603 | total time = 12990.56 ms / 1174 tokens
llama-server | 11464.06.859.740 I slot print_timing: id 0 | task 2871603 | graphs reused = 2780413
llama-server | 11464.06.859.743 I slot print_timing: id 0 | task 2871603 | draft acceptance = 0.83121 ( 719 accepted / 865 generated), mean len = 5.16
llama-server | 11464.06.859.843 I slot release: id 0 | task 2871603 | stop processing: n_tokens = 2466, truncated = 0
llama-server | 11464.14.181.603 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.303 (> 0.100 thold), f_keep = 0.526
llama-server | 11464.14.182.381 I slot launch_slot_: id 0 | task 2871779 | processing task, is_child = 0
llama-server | 11464.20.304.835 I slot print_timing: id 0 | task 2871779 | n_gen = 190, tg = 61.82 t/s, tg_3s = 62.14 t/s
llama-server | 11464.23.344.299 I slot print_timing: id 0 | task 2871779 | n_gen = 384, tg = 62.82 t/s, tg_3s = 63.83 t/s
llama-server | 11464.26.377.660 I slot print_timing: id 0 | task 2871779 | n_gen = 575, tg = 62.87 t/s, tg_3s = 62.97 t/s
llama-server | 11464.29.429.231 I slot print_timing: id 0 | task 2871779 | n_gen = 735, tg = 60.25 t/s, tg_3s = 52.43 t/s
llama-server | 11464.32.488.508 I slot print_timing: id 0 | task 2871779 | n_gen = 891, tg = 58.40 t/s, tg_3s = 50.99 t/s
llama-server | 11464.35.564.879 I slot print_timing: id 0 | task 2871779 | n_gen = 1095, tg = 59.73 t/s, tg_3s = 66.31 t/s
llama-server | 11464.38.630.337 I slot print_timing: id 0 | task 2871779 | n_gen = 1308, tg = 61.12 t/s, tg_3s = 69.48 t/s
llama-server | 11464.41.640.916 I slot print_timing: id 0 | task 2871779 | n_gen = 1518, tg = 62.19 t/s, tg_3s = 69.75 t/s
llama-server | 11464.43.707.452 I slot print_timing: id 0 | task 2871779 | prompt eval time = 3064.46 ms / 2994 tokens ( 1.02 ms per token, 977.01 tokens per second)
llama-server | 11464.43.707.455 I slot print_timing: id 0 | task 2871779 | eval time = 26459.85 ms / 1683 tokens ( 15.73 ms per token, 63.57 tokens per second)
llama-server | 11464.43.707.456 I slot print_timing: id 0 | task 2871779 | total time = 29524.30 ms / 4677 tokens
llama-server | 11464.43.707.457 I slot print_timing: id 0 | task 2871779 | graphs reused = 2780768
llama-server | 11464.43.707.459 I slot print_timing: id 0 | task 2871779 | draft acceptance = 0.72672 ( 1319 accepted / 1815 generated), mean len = 4.63
llama-server | 11464.43.707.611 I slot release: id 0 | task 2871779 | stop processing: n_tokens = 5968, truncated = 0
llama-server | 11464.43.817.433 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.817 (> 0.100 thold), f_keep = 0.217
llama-server | 11464.43.817.999 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 946.130 MiB)
llama-server | 11464.44.444.031 I slot launch_slot_: id 0 | task 2872147 | processing task, is_child = 0
llama-server | 11464.48.063.053 I slot print_timing: id 0 | task 2872147 | n_gen = 215, tg = 70.57 t/s, tg_3s = 70.89 t/s
llama-server | 11464.51.127.608 I slot print_timing: id 0 | task 2872147 | n_gen = 456, tg = 74.63 t/s, tg_3s = 78.64 t/s
llama-server | 11464.54.156.107 I slot print_timing: id 0 | task 2872147 | n_gen = 678, tg = 74.19 t/s, tg_3s = 73.30 t/s
llama-server | 11464.57.187.759 I slot print_timing: id 0 | task 2872147 | n_gen = 925, tg = 76.00 t/s, tg_3s = 81.47 t/s
llama-server | 11464.57.473.720 I slot print_timing: id 0 | task 2872147 | prompt eval time = 586.00 ms / 296 tokens ( 1.98 ms per token, 505.12 tokens per second)
llama-server | 11464.57.473.723 I slot print_timing: id 0 | task 2872147 | eval time = 12443.18 ms / 947 tokens ( 13.15 ms per token, 76.03 tokens per second)
llama-server | 11464.57.473.724 I slot print_timing: id 0 | task 2872147 | total time = 13029.17 ms / 1243 tokens
llama-server | 11464.57.473.724 I slot print_timing: id 0 | task 2872147 | graphs reused = 2780937
llama-server | 11464.57.473.735 I slot print_timing: id 0 | task 2872147 | draft acceptance = 0.89364 ( 773 accepted / 865 generated), mean len = 5.47
llama-server | 11464.57.473.817 I slot release: id 0 | task 2872147 | stop processing: n_tokens = 2534, truncated = 0
llama-server | 11465.04.358.964 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.288 (> 0.100 thold), f_keep = 0.512
llama-server | 11465.04.359.591 I slot launch_slot_: id 0 | task 2872323 | processing task, is_child = 0
llama-server | 11465.10.688.902 I slot print_timing: id 0 | task 2872323 | n_gen = 191, tg = 62.14 t/s, tg_3s = 62.47 t/s
llama-server | 11465.13.718.727 I slot print_timing: id 0 | task 2872323 | n_gen = 365, tg = 59.80 t/s, tg_3s = 57.43 t/s
llama-server | 11465.16.773.105 I slot print_timing: id 0 | task 2872323 | n_gen = 529, tg = 57.76 t/s, tg_3s = 53.69 t/s
llama-server | 11465.19.835.850 I slot print_timing: id 0 | task 2872323 | n_gen = 700, tg = 57.27 t/s, tg_3s = 55.83 t/s
llama-server | 11465.22.902.800 I slot print_timing: id 0 | task 2872323 | n_gen = 889, tg = 58.15 t/s, tg_3s = 61.62 t/s
llama-server | 11465.25.956.766 I slot print_timing: id 0 | task 2872323 | n_gen = 1079, tg = 58.83 t/s, tg_3s = 62.21 t/s
llama-server | 11465.28.970.647 I slot print_timing: id 0 | task 2872323 | n_gen = 1303, tg = 61.01 t/s, tg_3s = 74.32 t/s
llama-server | 11465.31.992.549 I slot print_timing: id 0 | task 2872323 | n_gen = 1547, tg = 63.46 t/s, tg_3s = 80.74 t/s
llama-server | 11465.33.089.579 I slot print_timing: id 0 | task 2872323 | prompt eval time = 3271.28 ms / 3207 tokens ( 1.02 ms per token, 980.35 tokens per second)
llama-server | 11465.33.089.582 I slot print_timing: id 0 | task 2872323 | eval time = 25458.14 ms / 1633 tokens ( 15.60 ms per token, 64.11 tokens per second)
llama-server | 11465.33.089.583 I slot print_timing: id 0 | task 2872323 | total time = 28729.42 ms / 4840 tokens
llama-server | 11465.33.089.583 I slot print_timing: id 0 | task 2872323 | graphs reused = 2781279
llama-server | 11465.33.089.586 I slot print_timing: id 0 | task 2872323 | draft acceptance = 0.73524 ( 1283 accepted / 1745 generated), mean len = 4.68
llama-server | 11465.33.089.742 I slot release: id 0 | task 2872323 | stop processing: n_tokens = 6131, truncated = 0
llama-server | 11465.33.204.445 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.817 (> 0.100 thold), f_keep = 0.212
llama-server | 11465.33.205.336 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1121.643 MiB)
llama-server | 11465.33.877.071 I slot launch_slot_: id 0 | task 2872677 | processing task, is_child = 0
llama-server | 11465.37.471.976 I slot print_timing: id 0 | task 2872677 | n_gen = 206, tg = 68.18 t/s, tg_3s = 68.50 t/s
llama-server | 11465.40.489.751 I slot print_timing: id 0 | task 2872677 | n_gen = 416, tg = 68.88 t/s, tg_3s = 69.59 t/s
llama-server | 11465.43.511.238 I slot print_timing: id 0 | task 2872677 | n_gen = 663, tg = 73.18 t/s, tg_3s = 81.75 t/s
llama-server | 11465.45.320.626 I slot print_timing: id 0 | task 2872677 | prompt eval time = 587.45 ms / 296 tokens ( 1.98 ms per token, 503.87 tokens per second)
llama-server | 11465.45.320.629 I slot print_timing: id 0 | task 2872677 | eval time = 10855.58 ms / 809 tokens ( 13.44 ms per token, 74.43 tokens per second)
llama-server | 11465.45.320.630 I slot print_timing: id 0 | task 2872677 | total time = 11443.03 ms / 1105 tokens
llama-server | 11465.45.320.630 I slot print_timing: id 0 | task 2872677 | graphs reused = 2781426
llama-server | 11465.45.320.641 I slot print_timing: id 0 | task 2872677 | draft acceptance = 0.87020 ( 657 accepted / 755 generated), mean len = 5.35
llama-server | 11465.45.320.722 I slot release: id 0 | task 2872677 | stop processing: n_tokens = 2396, truncated = 0
llama-server | 11465.54.442.153 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.226 (> 0.100 thold), f_keep = 0.541
llama-server | 11465.54.442.897 I slot launch_slot_: id 0 | task 2872831 | processing task, is_child = 0
llama-server | 11465.58.040.023 I slot print_timing: id 0 | task 2872831 | prompt processing, n_tokens = 3935, progress = 0.91, t = 3.16 s / 1245.94 tokens per second
llama-server | 11465.58.580.508 I slot print_timing: id 0 | task 2872831 | prompt processing, n_tokens = 4447, progress = 1.00, t = 3.69 s / 1204.02 tokens per second
llama-server | 11466.01.740.052 I slot print_timing: id 0 | task 2872831 | n_gen = 161, tg = 53.25 t/s, tg_3s = 53.58 t/s
llama-server | 11466.04.772.854 I slot print_timing: id 0 | task 2872831 | n_gen = 325, tg = 53.66 t/s, tg_3s = 54.08 t/s
llama-server | 11466.07.836.677 I slot print_timing: id 0 | task 2872831 | n_gen = 501, tg = 54.94 t/s, tg_3s = 57.44 t/s
llama-server | 11466.10.838.288 I slot print_timing: id 0 | task 2872831 | n_gen = 671, tg = 55.36 t/s, tg_3s = 56.64 t/s
llama-server | 11466.13.901.968 I slot print_timing: id 0 | task 2872831 | n_gen = 852, tg = 56.11 t/s, tg_3s = 59.08 t/s
llama-server | 11466.16.917.801 I slot print_timing: id 0 | task 2872831 | n_gen = 1045, tg = 57.42 t/s, tg_3s = 64.00 t/s
llama-server | 11466.19.942.421 I slot print_timing: id 0 | task 2872831 | n_gen = 1242, tg = 58.52 t/s, tg_3s = 65.13 t/s
llama-server | 11466.22.950.611 I slot print_timing: id 0 | task 2872831 | n_gen = 1406, tg = 58.02 t/s, tg_3s = 54.52 t/s
llama-server | 11466.24.445.605 W srv stop: cancel task, id_task = 2872831
llama-server | 11466.24.511.417 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 687848156591
llama-server | 11466.24.511.785 I slot launch_slot_: id 1 | task 2873188 | processing task, is_child = 0
llama-server | 11466.24.511.788 I slot release: id 0 | task 2872831 | stop processing: n_tokens = 7254, truncated = 0
llama-server | 11466.29.587.007 I slot print_timing: id 1 | task 2873188 | prompt processing, n_tokens = 5227, progress = 0.91, t = 4.60 s / 1135.37 tokens per second
llama-server | 11466.30.161.053 I slot print_timing: id 1 | task 2873188 | prompt processing, n_tokens = 5739, progress = 1.00, t = 5.17 s / 1110.71 tokens per second
llama-server | 11466.33.370.766 I slot print_timing: id 1 | task 2873188 | n_gen = 154, tg = 49.82 t/s, tg_3s = 50.14 t/s
llama-server | 11466.36.411.873 I slot print_timing: id 1 | task 2873188 | n_gen = 316, tg = 51.54 t/s, tg_3s = 53.27 t/s
llama-server | 11466.39.479.735 I slot print_timing: id 1 | task 2873188 | n_gen = 487, tg = 52.94 t/s, tg_3s = 55.74 t/s
llama-server | 11466.42.541.957 I slot print_timing: id 1 | task 2873188 | n_gen = 639, tg = 52.11 t/s, tg_3s = 49.64 t/s
llama-server | 11466.45.591.360 I slot print_timing: id 1 | task 2873188 | n_gen = 807, tg = 52.71 t/s, tg_3s = 55.09 t/s
llama-server | 11466.48.591.936 I slot print_timing: id 1 | task 2873188 | n_gen = 1010, tg = 55.16 t/s, tg_3s = 67.65 t/s
llama-server | 11466.50.367.738 I slot print_timing: id 1 | task 2873188 | prompt eval time = 5787.63 ms / 5743 tokens ( 1.01 ms per token, 992.29 tokens per second)
llama-server | 11466.50.367.742 I slot print_timing: id 1 | task 2873188 | eval time = 20068.07 ms / 1133 tokens ( 17.73 ms per token, 56.41 tokens per second)
llama-server | 11466.50.367.743 I slot print_timing: id 1 | task 2873188 | total time = 25855.69 ms / 6876 tokens
llama-server | 11466.50.367.743 I slot print_timing: id 1 | task 2873188 | graphs reused = 2782027
llama-server | 11466.50.367.746 I slot print_timing: id 1 | task 2873188 | draft acceptance = 0.66412 ( 870 accepted / 1310 generated), mean len = 4.32
llama-server | 11466.50.367.954 I slot release: id 1 | task 2873188 | stop processing: n_tokens = 6875, truncated = 0
llama-server | 11466.50.486.637 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.179
llama-server | 11466.50.487.416 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1119.501 MiB)
llama-server | 11466.51.258.574 I slot launch_slot_: id 0 | task 2873457 | processing task, is_child = 0
llama-server | 11466.51.259.808 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1100.483 MiB)
llama-server | 11466.55.552.443 I slot print_timing: id 0 | task 2873457 | n_gen = 192, tg = 63.52 t/s, tg_3s = 63.85 t/s
llama-server | 11466.58.567.367 I slot print_timing: id 0 | task 2873457 | n_gen = 427, tg = 70.74 t/s, tg_3s = 77.95 t/s
llama-server | 11467.01.235.073 I slot print_timing: id 0 | task 2873457 | prompt eval time = 576.69 ms / 279 tokens ( 2.07 ms per token, 483.80 tokens per second)
llama-server | 11467.01.235.077 I slot print_timing: id 0 | task 2873457 | eval time = 8689.60 ms / 649 tokens ( 13.41 ms per token, 74.57 tokens per second)
llama-server | 11467.01.235.078 I slot print_timing: id 0 | task 2873457 | total time = 9266.29 ms / 928 tokens
llama-server | 11467.01.235.078 I slot print_timing: id 0 | task 2873457 | graphs reused = 2782145
llama-server | 11467.01.235.081 I slot print_timing: id 0 | task 2873457 | draft acceptance = 0.87107 ( 527 accepted / 605 generated), mean len = 5.36
llama-server | 11467.01.235.171 I slot release: id 0 | task 2873457 | stop processing: n_tokens = 2219, truncated = 0
llama-server | 11467.09.653.818 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.161 (> 0.100 thold), f_keep = 0.584
llama-server | 11467.09.654.533 I slot launch_slot_: id 0 | task 2873581 | processing task, is_child = 0
llama-server | 11467.13.512.589 I slot print_timing: id 0 | task 2873581 | prompt processing, n_tokens = 4096, progress = 0.67, t = 3.22 s / 1271.19 tokens per second
llama-server | 11467.15.423.911 I slot print_timing: id 0 | task 2873581 | prompt processing, n_tokens = 6144, progress = 0.92, t = 5.14 s / 1196.14 tokens per second
llama-server | 11467.15.593.516 I slot print_timing: id 0 | task 2873581 | prompt processing, n_tokens = 6242, progress = 0.94, t = 5.80 s / 1075.60 tokens per second
llama-server | 11467.16.149.303 I slot print_timing: id 0 | task 2873581 | prompt processing, n_tokens = 6754, progress = 1.00, t = 6.04 s / 1118.74 tokens per second
llama-server | 11467.19.354.062 I slot print_timing: id 0 | task 2873581 | n_gen = 152, tg = 49.78 t/s, tg_3s = 50.11 t/s
llama-server | 11467.22.358.074 I slot print_timing: id 0 | task 2873581 | n_gen = 325, tg = 53.67 t/s, tg_3s = 57.59 t/s
llama-server | 11467.25.390.034 I slot print_timing: id 0 | task 2873581 | n_gen = 490, tg = 53.92 t/s, tg_3s = 54.42 t/s
llama-server | 11467.28.406.991 I slot print_timing: id 0 | task 2873581 | n_gen = 660, tg = 54.53 t/s, tg_3s = 56.35 t/s
llama-server | 11467.31.447.091 I slot print_timing: id 0 | task 2873581 | n_gen = 812, tg = 53.62 t/s, tg_3s = 50.00 t/s
llama-server | 11467.34.499.740 I slot print_timing: id 0 | task 2873581 | n_gen = 969, tg = 53.25 t/s, tg_3s = 51.43 t/s
llama-server | 11467.37.537.807 I slot print_timing: id 0 | task 2873581 | n_gen = 1150, tg = 54.16 t/s, tg_3s = 59.58 t/s
llama-server | 11467.39.656.761 W srv stop: cancel task, id_task = 2873581
llama-server | 11467.39.713.593 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688026208006
llama-server | 11467.39.714.063 I slot launch_slot_: id 1 | task 2873904 | processing task, is_child = 0
llama-server | 11467.39.714.065 I slot release: id 0 | task 2873581 | stop processing: n_tokens = 9344, truncated = 0
llama-server | 11467.45.123.653 I slot print_timing: id 1 | task 2873904 | prompt processing, n_tokens = 5388, progress = 0.67, t = 4.75 s / 1134.80 tokens per second
llama-server | 11467.47.214.228 I slot print_timing: id 1 | task 2873904 | prompt processing, n_tokens = 7436, progress = 0.92, t = 6.83 s / 1088.89 tokens per second
llama-server | 11467.47.376.567 I slot print_timing: id 1 | task 2873904 | prompt processing, n_tokens = 7534, progress = 0.94, t = 7.51 s / 1003.24 tokens per second
llama-server | 11467.47.998.139 I slot print_timing: id 1 | task 2873904 | prompt processing, n_tokens = 8046, progress = 1.00, t = 7.78 s / 1033.97 tokens per second
llama-server | 11467.51.232.637 I slot print_timing: id 1 | task 2873904 | n_gen = 157, tg = 50.86 t/s, tg_3s = 51.18 t/s
llama-server | 11467.54.281.130 I slot print_timing: id 1 | task 2873904 | n_gen = 304, tg = 49.54 t/s, tg_3s = 48.22 t/s
llama-server | 11467.57.324.877 I slot print_timing: id 1 | task 2873904 | n_gen = 454, tg = 49.46 t/s, tg_3s = 49.28 t/s
llama-server | 11468.00.387.718 I slot print_timing: id 1 | task 2873904 | n_gen = 595, tg = 48.60 t/s, tg_3s = 46.04 t/s
llama-server | 11468.03.442.942 I slot print_timing: id 1 | task 2873904 | n_gen = 778, tg = 50.86 t/s, tg_3s = 59.90 t/s
llama-server | 11468.06.449.982 I slot print_timing: id 1 | task 2873904 | n_gen = 988, tg = 53.98 t/s, tg_3s = 69.84 t/s
llama-server | 11468.09.453.812 I slot print_timing: id 1 | task 2873904 | n_gen = 1201, tg = 56.37 t/s, tg_3s = 70.91 t/s
llama-server | 11468.11.753.242 I slot print_timing: id 1 | task 2873904 | prompt eval time = 8450.89 ms / 8050 tokens ( 1.05 ms per token, 952.56 tokens per second)
llama-server | 11468.11.753.245 I slot print_timing: id 1 | task 2873904 | eval time = 23588.02 ms / 1372 tokens ( 17.20 ms per token, 58.12 tokens per second)
llama-server | 11468.11.753.246 I slot print_timing: id 1 | task 2873904 | total time = 32038.90 ms / 9422 tokens
llama-server | 11468.11.753.247 I slot print_timing: id 1 | task 2873904 | graphs reused = 2782748
llama-server | 11468.11.753.250 I slot print_timing: id 1 | task 2873904 | draft acceptance = 0.71400 ( 1071 accepted / 1500 generated), mean len = 4.57
llama-server | 11468.11.753.476 I slot release: id 1 | task 2873904 | stop processing: n_tokens = 9421, truncated = 0
llama-server | 11468.11.883.654 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.820 (> 0.100 thold), f_keep = 0.139
llama-server | 11468.11.884.609 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1135.760 MiB)
llama-server | 11468.12.584.958 I slot launch_slot_: id 0 | task 2874213 | processing task, is_child = 0
llama-server | 11468.12.585.704 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1211.349 MiB)
llama-server | 11468.16.928.931 I slot print_timing: id 0 | task 2874213 | n_gen = 201, tg = 66.51 t/s, tg_3s = 66.83 t/s
llama-server | 11468.19.939.242 I slot print_timing: id 0 | task 2874213 | n_gen = 405, tg = 67.14 t/s, tg_3s = 67.77 t/s
llama-server | 11468.22.963.976 I slot print_timing: id 0 | task 2874213 | n_gen = 650, tg = 71.77 t/s, tg_3s = 81.00 t/s
llama-server | 11468.23.463.938 I slot print_timing: id 0 | task 2874213 | prompt eval time = 568.75 ms / 289 tokens ( 1.97 ms per token, 508.13 tokens per second)
llama-server | 11468.23.463.941 I slot print_timing: id 0 | task 2874213 | eval time = 9542.25 ms / 691 tokens ( 13.83 ms per token, 72.31 tokens per second)
llama-server | 11468.23.463.942 I slot print_timing: id 0 | task 2874213 | total time = 10111.00 ms / 980 tokens
llama-server | 11468.23.463.943 I slot print_timing: id 0 | task 2874213 | graphs reused = 2782878
llama-server | 11468.23.463.948 I slot print_timing: id 0 | task 2874213 | draft acceptance = 0.83910 ( 558 accepted / 665 generated), mean len = 5.20
llama-server | 11468.23.464.074 I slot release: id 0 | task 2874213 | stop processing: n_tokens = 2272, truncated = 0
llama-server | 11468.29.769.323 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.164 (> 0.100 thold), f_keep = 0.571
llama-server | 11468.29.770.018 I slot launch_slot_: id 0 | task 2874349 | processing task, is_child = 0
llama-server | 11468.33.623.512 I slot print_timing: id 0 | task 2874349 | prompt processing, n_tokens = 4096, progress = 0.68, t = 3.23 s / 1268.45 tokens per second
llama-server | 11468.35.520.173 I slot print_timing: id 0 | task 2874349 | prompt processing, n_tokens = 6083, progress = 0.93, t = 5.13 s / 1185.05 tokens per second
llama-server | 11468.36.099.188 I slot print_timing: id 0 | task 2874349 | prompt processing, n_tokens = 6595, progress = 1.00, t = 5.86 s / 1124.76 tokens per second
llama-server | 11468.39.294.673 I slot print_timing: id 0 | task 2874349 | n_gen = 166, tg = 54.15 t/s, tg_3s = 54.47 t/s
llama-server | 11468.42.312.090 I slot print_timing: id 0 | task 2874349 | n_gen = 309, tg = 50.79 t/s, tg_3s = 47.39 t/s
llama-server | 11468.45.330.411 I slot print_timing: id 0 | task 2874349 | n_gen = 470, tg = 51.64 t/s, tg_3s = 53.34 t/s
llama-server | 11468.48.368.210 I slot print_timing: id 0 | task 2874349 | n_gen = 618, tg = 50.90 t/s, tg_3s = 48.72 t/s
llama-server | 11468.51.397.432 I slot print_timing: id 0 | task 2874349 | n_gen = 810, tg = 53.40 t/s, tg_3s = 63.38 t/s
llama-server | 11468.54.454.623 I slot print_timing: id 0 | task 2874349 | n_gen = 1011, tg = 55.47 t/s, tg_3s = 65.75 t/s
llama-server | 11468.57.524.776 I slot print_timing: id 0 | task 2874349 | n_gen = 1246, tg = 58.51 t/s, tg_3s = 76.54 t/s
llama-server | 11468.57.972.540 I slot print_timing: id 0 | task 2874349 | prompt eval time = 6476.75 ms / 6599 tokens ( 0.98 ms per token, 1018.88 tokens per second)
llama-server | 11468.57.972.544 I slot print_timing: id 0 | task 2874349 | eval time = 21725.10 ms / 1278 tokens ( 17.01 ms per token, 58.78 tokens per second)
llama-server | 11468.57.972.544 I slot print_timing: id 0 | task 2874349 | total time = 28201.85 ms / 7877 tokens
llama-server | 11468.57.972.545 I slot print_timing: id 0 | task 2874349 | graphs reused = 2783165
llama-server | 11468.57.972.548 I slot print_timing: id 0 | task 2874349 | draft acceptance = 0.67167 ( 984 accepted / 1465 generated), mean len = 4.36
llama-server | 11468.57.972.798 I slot release: id 0 | task 2874349 | stop processing: n_tokens = 9168, truncated = 0
llama-server | 11468.58.084.988 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.822 (> 0.100 thold), f_keep = 0.141
llama-server | 11468.58.085.862 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1064.596 MiB)
llama-server | 11468.58.779.904 I slot launch_slot_: id 0 | task 2874648 | processing task, is_child = 0
llama-server | 11469.02.348.802 I slot print_timing: id 0 | task 2874648 | n_gen = 191, tg = 63.34 t/s, tg_3s = 63.66 t/s
llama-server | 11469.05.418.416 I slot print_timing: id 0 | task 2874648 | n_gen = 358, tg = 58.82 t/s, tg_3s = 54.40 t/s
llama-server | 11469.08.430.192 I slot print_timing: id 0 | task 2874648 | n_gen = 526, tg = 57.81 t/s, tg_3s = 55.78 t/s
llama-server | 11469.11.497.532 I slot print_timing: id 0 | task 2874648 | n_gen = 708, tg = 58.20 t/s, tg_3s = 59.33 t/s
llama-server | 11469.14.512.152 I slot print_timing: id 0 | task 2874648 | n_gen = 861, tg = 56.72 t/s, tg_3s = 50.75 t/s
llama-server | 11469.17.529.304 I slot print_timing: id 0 | task 2874648 | n_gen = 1007, tg = 55.33 t/s, tg_3s = 48.39 t/s
llama-server | 11469.20.539.231 I slot print_timing: id 0 | task 2874648 | n_gen = 1171, tg = 55.21 t/s, tg_3s = 54.49 t/s
llama-server | 11469.23.565.398 I slot print_timing: id 0 | task 2874648 | n_gen = 1321, tg = 54.51 t/s, tg_3s = 49.57 t/s
llama-server | 11469.26.577.252 I slot print_timing: id 0 | task 2874648 | n_gen = 1474, tg = 54.10 t/s, tg_3s = 50.80 t/s
llama-server | 11469.28.088.769 W srv stop: cancel task, id_task = 2874648
llama-server | 11469.28.101.232 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688107593528
llama-server | 11469.28.101.643 I slot launch_slot_: id 1 | task 2875052 | processing task, is_child = 0
llama-server | 11469.28.101.645 I slot release: id 0 | task 2874648 | stop processing: n_tokens = 3115, truncated = 0
llama-server | 11469.33.064.028 I slot print_timing: id 1 | task 2875052 | n_gen = 183, tg = 60.38 t/s, tg_3s = 60.71 t/s
llama-server | 11469.36.113.281 I slot print_timing: id 1 | task 2875052 | n_gen = 355, tg = 58.38 t/s, tg_3s = 56.41 t/s
llama-server | 11469.39.186.120 I slot print_timing: id 1 | task 2875052 | n_gen = 531, tg = 58.01 t/s, tg_3s = 57.28 t/s
llama-server | 11469.42.242.665 I slot print_timing: id 1 | task 2875052 | n_gen = 654, tg = 53.56 t/s, tg_3s = 40.24 t/s
llama-server | 11469.45.314.361 I slot print_timing: id 1 | task 2875052 | n_gen = 817, tg = 53.46 t/s, tg_3s = 53.07 t/s
llama-server | 11469.48.327.765 I slot print_timing: id 1 | task 2875052 | n_gen = 1014, tg = 55.42 t/s, tg_3s = 65.37 t/s
llama-server | 11469.51.350.394 I slot print_timing: id 1 | task 2875052 | n_gen = 1229, tg = 57.65 t/s, tg_3s = 71.13 t/s
llama-server | 11469.54.416.678 I slot print_timing: id 1 | task 2875052 | n_gen = 1408, tg = 57.74 t/s, tg_3s = 58.38 t/s
llama-server | 11469.57.433.531 I slot print_timing: id 1 | task 2875052 | n_gen = 1585, tg = 57.84 t/s, tg_3s = 58.67 t/s
llama-server | 11469.59.946.834 I slot print_timing: id 1 | task 2875052 | prompt eval time = 1947.86 ms / 1577 tokens ( 1.24 ms per token, 809.60 tokens per second)
llama-server | 11469.59.946.838 I slot print_timing: id 1 | task 2875052 | eval time = 29897.07 ms / 1789 tokens ( 16.72 ms per token, 59.81 tokens per second)
llama-server | 11469.59.946.838 I slot print_timing: id 1 | task 2875052 | total time = 31844.93 ms / 3366 tokens
llama-server | 11469.59.946.839 I slot print_timing: id 1 | task 2875052 | graphs reused = 2783959
llama-server | 11469.59.946.842 I slot print_timing: id 1 | task 2875052 | draft acceptance = 0.67647 ( 1380 accepted / 2040 generated), mean len = 4.38
llama-server | 11469.59.946.931 I slot release: id 1 | task 2875052 | stop processing: n_tokens = 3365, truncated = 0
llama-server | 11470.04.769.073 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.304 (> 0.100 thold), f_keep = 0.416
llama-server | 11470.04.769.654 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1112.419 MiB)
llama-server | 11470.05.267.795 I slot launch_slot_: id 0 | task 2875466 | processing task, is_child = 0
llama-server | 11470.05.268.289 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1117.839 MiB)
llama-server | 11470.11.993.977 I slot print_timing: id 0 | task 2875466 | n_gen = 211, tg = 68.57 t/s, tg_3s = 68.89 t/s
llama-server | 11470.15.030.496 I slot print_timing: id 0 | task 2875466 | n_gen = 382, tg = 62.47 t/s, tg_3s = 56.31 t/s
llama-server | 11470.18.069.090 I slot print_timing: id 0 | task 2875466 | n_gen = 558, tg = 60.96 t/s, tg_3s = 57.92 t/s
llama-server | 11470.21.116.236 I slot print_timing: id 0 | task 2875466 | n_gen = 681, tg = 55.81 t/s, tg_3s = 40.37 t/s
llama-server | 11470.24.144.438 I slot print_timing: id 0 | task 2875466 | n_gen = 831, tg = 54.56 t/s, tg_3s = 49.53 t/s
llama-server | 11470.27.212.137 I slot print_timing: id 0 | task 2875466 | n_gen = 1016, tg = 55.52 t/s, tg_3s = 60.31 t/s
llama-server | 11470.30.213.503 I slot print_timing: id 0 | task 2875466 | n_gen = 1192, tg = 55.96 t/s, tg_3s = 58.64 t/s
llama-server | 11470.33.222.655 I slot print_timing: id 0 | task 2875466 | n_gen = 1404, tg = 57.76 t/s, tg_3s = 70.45 t/s
llama-server | 11470.34.771.303 W srv stop: cancel task, id_task = 2875466
llama-server | 11470.34.830.363 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688215786982
llama-server | 11470.34.874.883 I slot launch_slot_: id 1 | task 2875827 | processing task, is_child = 0
llama-server | 11470.34.874.887 I slot release: id 0 | task 2875466 | stop processing: n_tokens = 5796, truncated = 0
llama-server | 11470.41.106.924 I slot print_timing: id 1 | task 2875827 | n_gen = 187, tg = 61.84 t/s, tg_3s = 62.17 t/s
llama-server | 11470.44.118.073 I slot print_timing: id 1 | task 2875827 | n_gen = 340, tg = 56.32 t/s, tg_3s = 50.81 t/s
llama-server | 11470.47.134.200 I slot print_timing: id 1 | task 2875827 | n_gen = 513, tg = 56.67 t/s, tg_3s = 57.36 t/s
llama-server | 11470.50.205.130 I slot print_timing: id 1 | task 2875827 | n_gen = 664, tg = 54.77 t/s, tg_3s = 49.17 t/s
llama-server | 11470.53.220.937 I slot print_timing: id 1 | task 2875827 | n_gen = 784, tg = 51.78 t/s, tg_3s = 39.79 t/s
llama-server | 11470.56.227.914 I slot print_timing: id 1 | task 2875827 | n_gen = 941, tg = 51.85 t/s, tg_3s = 52.21 t/s
llama-server | 11470.59.251.305 I slot print_timing: id 1 | task 2875827 | n_gen = 1092, tg = 51.58 t/s, tg_3s = 49.94 t/s
llama-server | 11471.02.285.052 I slot print_timing: id 1 | task 2875827 | n_gen = 1293, tg = 53.42 t/s, tg_3s = 66.25 t/s
llama-server | 11471.05.331.232 I slot print_timing: id 1 | task 2875827 | n_gen = 1509, tg = 55.38 t/s, tg_3s = 70.91 t/s
llama-server | 11471.08.374.926 I slot print_timing: id 1 | task 2875827 | n_gen = 1739, tg = 57.41 t/s, tg_3s = 75.57 t/s
llama-server | 11471.08.830.722 I slot print_timing: id 1 | task 2875827 | prompt eval time = 3223.93 ms / 2972 tokens ( 1.08 ms per token, 921.86 tokens per second)
llama-server | 11471.08.830.725 I slot print_timing: id 1 | task 2875827 | eval time = 30731.65 ms / 1775 tokens ( 17.32 ms per token, 57.73 tokens per second)
llama-server | 11471.08.830.726 I slot print_timing: id 1 | task 2875827 | total time = 33955.57 ms / 4747 tokens
llama-server | 11471.08.830.726 I slot print_timing: id 1 | task 2875827 | graphs reused = 2784707
llama-server | 11471.08.830.729 I slot print_timing: id 1 | task 2875827 | draft acceptance = 0.67174 ( 1367 accepted / 2035 generated), mean len = 4.36
llama-server | 11471.08.830.880 I slot release: id 1 | task 2875827 | stop processing: n_tokens = 6038, truncated = 0
llama-server | 11471.08.938.495 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.829 (> 0.100 thold), f_keep = 0.224
llama-server | 11471.09.684.879 I slot launch_slot_: id 0 | task 2876240 | processing task, is_child = 0
llama-server | 11471.13.985.959 I slot print_timing: id 0 | task 2876240 | n_gen = 170, tg = 56.30 t/s, tg_3s = 56.63 t/s
llama-server | 11471.17.001.701 I slot print_timing: id 0 | task 2876240 | n_gen = 419, tg = 69.47 t/s, tg_3s = 82.57 t/s
llama-server | 11471.19.669.312 I slot print_timing: id 0 | task 2876240 | prompt eval time = 676.94 ms / 273 tokens ( 2.48 ms per token, 403.28 tokens per second)
llama-server | 11471.19.669.315 I slot print_timing: id 0 | task 2876240 | eval time = 8684.97 ms / 636 tokens ( 13.68 ms per token, 73.11 tokens per second)
llama-server | 11471.19.669.316 I slot print_timing: id 0 | task 2876240 | total time = 9361.91 ms / 909 tokens
llama-server | 11471.19.669.316 I slot print_timing: id 0 | task 2876240 | graphs reused = 2784825
llama-server | 11471.19.669.319 I slot print_timing: id 0 | task 2876240 | draft acceptance = 0.84959 ( 514 accepted / 605 generated), mean len = 5.25
llama-server | 11471.19.669.408 I slot release: id 0 | task 2876240 | stop processing: n_tokens = 2200, truncated = 0
llama-server | 11471.25.022.236 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.590
llama-server | 11471.25.023.076 I slot launch_slot_: id 0 | task 2876364 | processing task, is_child = 0
llama-server | 11471.31.059.559 I slot print_timing: id 0 | task 2876364 | n_gen = 144, tg = 47.17 t/s, tg_3s = 47.50 t/s
llama-server | 11471.34.097.936 I slot print_timing: id 0 | task 2876364 | n_gen = 303, tg = 49.76 t/s, tg_3s = 52.33 t/s
llama-server | 11471.37.137.621 I slot print_timing: id 0 | task 2876364 | n_gen = 447, tg = 48.96 t/s, tg_3s = 47.37 t/s
llama-server | 11471.40.180.032 I slot print_timing: id 0 | task 2876364 | n_gen = 641, tg = 52.67 t/s, tg_3s = 63.77 t/s
llama-server | 11471.43.245.944 I slot print_timing: id 0 | task 2876364 | n_gen = 880, tg = 57.76 t/s, tg_3s = 77.95 t/s
llama-server | 11471.43.390.387 I slot print_timing: id 0 | task 2876364 | prompt eval time = 3004.05 ms / 2906 tokens ( 1.03 ms per token, 967.36 tokens per second)
llama-server | 11471.43.390.390 I slot print_timing: id 0 | task 2876364 | eval time = 15362.43 ms / 887 tokens ( 17.34 ms per token, 57.67 tokens per second)
llama-server | 11471.43.390.391 I slot print_timing: id 0 | task 2876364 | total time = 18366.48 ms / 3793 tokens
llama-server | 11471.43.390.391 I slot print_timing: id 0 | task 2876364 | graphs reused = 2785033
llama-server | 11471.43.390.394 I slot print_timing: id 0 | task 2876364 | draft acceptance = 0.63585 ( 674 accepted / 1060 generated), mean len = 4.18
llama-server | 11471.43.390.545 I slot release: id 0 | task 2876364 | stop processing: n_tokens = 5084, truncated = 0
llama-server | 11471.43.514.245 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.822 (> 0.100 thold), f_keep = 0.255
llama-server | 11471.43.514.889 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1155.158 MiB)
llama-server | 11471.44.142.578 I slot launch_slot_: id 0 | task 2876581 | processing task, is_child = 0
llama-server | 11471.47.795.975 I slot print_timing: id 0 | task 2876581 | n_gen = 205, tg = 66.47 t/s, tg_3s = 66.79 t/s
llama-server | 11471.50.866.110 I slot print_timing: id 0 | task 2876581 | n_gen = 357, tg = 57.99 t/s, tg_3s = 49.51 t/s
llama-server | 11471.53.868.165 I slot print_timing: id 0 | task 2876581 | n_gen = 503, tg = 54.91 t/s, tg_3s = 48.63 t/s
llama-server | 11471.56.871.021 I slot print_timing: id 0 | task 2876581 | n_gen = 711, tg = 58.46 t/s, tg_3s = 69.27 t/s
llama-server | 11471.59.893.705 I slot print_timing: id 0 | task 2876581 | n_gen = 887, tg = 58.42 t/s, tg_3s = 58.23 t/s
llama-server | 11472.02.914.601 I slot print_timing: id 0 | task 2876581 | n_gen = 1027, tg = 56.41 t/s, tg_3s = 46.34 t/s
llama-server | 11472.05.923.155 I slot print_timing: id 0 | task 2876581 | n_gen = 1178, tg = 55.53 t/s, tg_3s = 50.19 t/s
llama-server | 11472.08.947.729 I slot print_timing: id 0 | task 2876581 | n_gen = 1314, tg = 54.21 t/s, tg_3s = 44.96 t/s
llama-server | 11472.11.958.020 I slot print_timing: id 0 | task 2876581 | n_gen = 1471, tg = 53.98 t/s, tg_3s = 52.15 t/s
llama-server | 11472.13.516.455 W srv stop: cancel task, id_task = 2876581
llama-server | 11472.13.558.383 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688284670932
llama-server | 11472.13.609.900 I slot launch_slot_: id 1 | task 2876986 | processing task, is_child = 0
llama-server | 11472.13.609.906 I slot release: id 0 | task 2876581 | stop processing: n_tokens = 3128, truncated = 0
llama-server | 11472.17.298.496 I slot print_timing: id 1 | task 2876986 | n_gen = 200, tg = 65.89 t/s, tg_3s = 66.21 t/s
llama-server | 11472.20.345.520 I slot print_timing: id 1 | task 2876986 | n_gen = 344, tg = 56.53 t/s, tg_3s = 47.26 t/s
llama-server | 11472.23.355.783 I slot print_timing: id 1 | task 2876986 | n_gen = 541, tg = 59.49 t/s, tg_3s = 65.44 t/s
llama-server | 11472.26.363.585 I slot print_timing: id 1 | task 2876986 | n_gen = 707, tg = 58.42 t/s, tg_3s = 55.19 t/s
llama-server | 11472.29.425.852 I slot print_timing: id 1 | task 2876986 | n_gen = 854, tg = 56.31 t/s, tg_3s = 48.00 t/s
llama-server | 11472.32.434.661 I slot print_timing: id 1 | task 2876986 | n_gen = 1012, tg = 55.68 t/s, tg_3s = 52.51 t/s
llama-server | 11472.35.502.473 I slot print_timing: id 1 | task 2876986 | n_gen = 1168, tg = 54.98 t/s, tg_3s = 50.85 t/s
llama-server | 11472.38.512.898 I slot print_timing: id 1 | task 2876986 | n_gen = 1287, tg = 53.06 t/s, tg_3s = 39.53 t/s
llama-server | 11472.41.529.829 I slot print_timing: id 1 | task 2876986 | n_gen = 1453, tg = 53.28 t/s, tg_3s = 55.02 t/s
llama-server | 11472.44.533.739 I slot print_timing: id 1 | task 2876986 | n_gen = 1619, tg = 53.48 t/s, tg_3s = 55.26 t/s
llama-server | 11472.47.565.388 I slot print_timing: id 1 | task 2876986 | n_gen = 1813, tg = 54.44 t/s, tg_3s = 63.99 t/s
llama-server | 11472.50.587.069 I slot print_timing: id 1 | task 2876986 | n_gen = 1963, tg = 54.04 t/s, tg_3s = 49.64 t/s
llama-server | 11472.53.596.783 I slot print_timing: id 1 | task 2876986 | n_gen = 2101, tg = 53.41 t/s, tg_3s = 45.85 t/s
llama-server | 11472.56.631.141 I slot print_timing: id 1 | task 2876986 | n_gen = 2275, tg = 53.69 t/s, tg_3s = 57.34 t/s
llama-server | 11472.59.652.807 I slot print_timing: id 1 | task 2876986 | n_gen = 2454, tg = 54.06 t/s, tg_3s = 59.24 t/s
llama-server | 11473.02.699.725 I slot print_timing: id 1 | task 2876986 | n_gen = 2675, tg = 55.22 t/s, tg_3s = 72.53 t/s
llama-server | 11473.05.082.777 I slot print_timing: id 1 | task 2876986 | prompt eval time = 667.91 ms / 286 tokens ( 2.34 ms per token, 428.20 tokens per second)
llama-server | 11473.05.082.781 I slot print_timing: id 1 | task 2876986 | eval time = 50804.69 ms / 2863 tokens ( 17.75 ms per token, 56.33 tokens per second)
llama-server | 11473.05.082.782 I slot print_timing: id 1 | task 2876986 | total time = 51472.60 ms / 3149 tokens
llama-server | 11473.05.082.783 I slot print_timing: id 1 | task 2876986 | graphs reused = 2786107
llama-server | 11473.05.082.787 I slot print_timing: id 1 | task 2876986 | draft acceptance = 0.62836 ( 2171 accepted / 3455 generated), mean len = 4.14
llama-server | 11473.05.082.882 I slot release: id 1 | task 2876986 | stop processing: n_tokens = 4440, truncated = 0
llama-server | 11473.10.262.805 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.415
llama-server | 11473.10.794.195 I slot launch_slot_: id 0 | task 2877681 | processing task, is_child = 0
llama-server | 11473.10.795.452 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 972.496 MiB)
llama-server | 11473.15.232.327 I slot print_timing: id 0 | task 2877681 | prompt processing, n_tokens = 3974, progress = 1.00, t = 3.39 s / 1173.16 tokens per second
llama-server | 11473.18.445.246 I slot print_timing: id 0 | task 2877681 | n_gen = 181, tg = 58.58 t/s, tg_3s = 58.90 t/s
llama-server | 11473.21.482.330 I slot print_timing: id 0 | task 2877681 | n_gen = 336, tg = 54.83 t/s, tg_3s = 51.04 t/s
llama-server | 11473.24.548.165 I slot print_timing: id 0 | task 2877681 | n_gen = 501, tg = 54.49 t/s, tg_3s = 53.82 t/s
llama-server | 11473.27.614.219 I slot print_timing: id 0 | task 2877681 | n_gen = 652, tg = 53.18 t/s, tg_3s = 49.25 t/s
llama-server | 11473.30.676.026 I slot print_timing: id 0 | task 2877681 | n_gen = 822, tg = 53.65 t/s, tg_3s = 55.52 t/s
llama-server | 11473.33.693.884 I slot print_timing: id 0 | task 2877681 | n_gen = 1026, tg = 55.95 t/s, tg_3s = 67.60 t/s
llama-server | 11473.36.710.302 I slot print_timing: id 0 | task 2877681 | n_gen = 1226, tg = 57.41 t/s, tg_3s = 66.30 t/s
llama-server | 11473.39.081.528 I slot print_timing: id 0 | task 2877681 | prompt eval time = 3973.36 ms / 3978 tokens ( 1.00 ms per token, 1001.17 tokens per second)
llama-server | 11473.39.081.531 I slot print_timing: id 0 | task 2877681 | eval time = 23709.11 ms / 1417 tokens ( 16.74 ms per token, 59.72 tokens per second)
llama-server | 11473.39.081.532 I slot print_timing: id 0 | task 2877681 | total time = 27682.47 ms / 5395 tokens
llama-server | 11473.39.081.532 I slot print_timing: id 0 | task 2877681 | graphs reused = 2786424
llama-server | 11473.39.081.536 I slot print_timing: id 0 | task 2877681 | draft acceptance = 0.67407 ( 1092 accepted / 1620 generated), mean len = 4.37
llama-server | 11473.39.081.734 I slot release: id 0 | task 2877681 | stop processing: n_tokens = 6686, truncated = 0
llama-server | 11473.39.201.433 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.829 (> 0.100 thold), f_keep = 0.194
llama-server | 11473.39.202.187 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1224.648 MiB)
llama-server | 11473.39.967.706 I slot launch_slot_: id 0 | task 2878010 | processing task, is_child = 0
llama-server | 11473.43.583.921 I slot print_timing: id 0 | task 2878010 | n_gen = 198, tg = 65.58 t/s, tg_3s = 65.91 t/s
llama-server | 11473.46.595.142 I slot print_timing: id 0 | task 2878010 | n_gen = 409, tg = 67.83 t/s, tg_3s = 70.07 t/s
llama-server | 11473.49.613.083 I slot print_timing: id 0 | task 2878010 | n_gen = 595, tg = 65.76 t/s, tg_3s = 61.63 t/s
llama-server | 11473.52.647.308 I slot print_timing: id 0 | task 2878010 | n_gen = 812, tg = 67.21 t/s, tg_3s = 71.52 t/s
llama-server | 11473.55.680.491 I slot print_timing: id 0 | task 2878010 | n_gen = 1064, tg = 70.39 t/s, tg_3s = 83.08 t/s
llama-server | 11473.56.255.495 I slot print_timing: id 0 | task 2878010 | prompt eval time = 611.67 ms / 272 tokens ( 2.25 ms per token, 444.69 tokens per second)
llama-server | 11473.56.255.499 I slot print_timing: id 0 | task 2878010 | eval time = 15675.61 ms / 1110 tokens ( 14.13 ms per token, 70.75 tokens per second)
llama-server | 11473.56.255.499 I slot print_timing: id 0 | task 2878010 | total time = 16287.27 ms / 1382 tokens
llama-server | 11473.56.255.500 I slot print_timing: id 0 | task 2878010 | graphs reused = 2786637
llama-server | 11473.56.255.503 I slot print_timing: id 0 | task 2878010 | draft acceptance = 0.81743 ( 891 accepted / 1090 generated), mean len = 5.09
llama-server | 11473.56.255.590 I slot release: id 0 | task 2878010 | stop processing: n_tokens = 2673, truncated = 0
llama-server | 11474.05.303.958 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.485
llama-server | 11474.05.734.574 I slot launch_slot_: id 0 | task 2878231 | processing task, is_child = 0
llama-server | 11474.09.355.139 I slot print_timing: id 0 | task 2878231 | prompt processing, n_tokens = 3718, progress = 1.00, t = 3.18 s / 1169.48 tokens per second
llama-server | 11474.12.601.992 I slot print_timing: id 0 | task 2878231 | n_gen = 179, tg = 58.20 t/s, tg_3s = 58.52 t/s
llama-server | 11474.15.628.825 I slot print_timing: id 0 | task 2878231 | n_gen = 358, tg = 58.67 t/s, tg_3s = 59.14 t/s
llama-server | 11474.18.687.562 I slot print_timing: id 0 | task 2878231 | n_gen = 556, tg = 60.70 t/s, tg_3s = 64.73 t/s
llama-server | 11474.21.743.790 I slot print_timing: id 0 | task 2878231 | n_gen = 709, tg = 58.03 t/s, tg_3s = 50.06 t/s
llama-server | 11474.24.790.376 I slot print_timing: id 0 | task 2878231 | n_gen = 868, tg = 56.86 t/s, tg_3s = 52.19 t/s
llama-server | 11474.27.863.708 I slot print_timing: id 0 | task 2878231 | n_gen = 1038, tg = 56.60 t/s, tg_3s = 55.31 t/s
llama-server | 11474.30.865.109 I slot print_timing: id 0 | task 2878231 | n_gen = 1194, tg = 55.95 t/s, tg_3s = 51.98 t/s
llama-server | 11474.33.939.284 I slot print_timing: id 0 | task 2878231 | n_gen = 1388, tg = 56.85 t/s, tg_3s = 63.11 t/s
llama-server | 11474.35.306.597 W srv stop: cancel task, id_task = 2878231
llama-server | 11474.35.341.356 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688400922934
llama-server | 11474.35.389.028 I slot launch_slot_: id 1 | task 2878590 | processing task, is_child = 0
llama-server | 11474.35.389.032 I slot release: id 0 | task 2878231 | stop processing: n_tokens = 6483, truncated = 0
llama-server | 11474.38.635.555 I slot print_timing: id 1 | task 2878590 | prompt processing, n_tokens = 3206, progress = 0.90, t = 3.01 s / 1066.57 tokens per second
llama-server | 11474.39.292.360 I slot print_timing: id 1 | task 2878590 | prompt processing, n_tokens = 3718, progress = 1.00, t = 3.43 s / 1083.76 tokens per second
llama-server | 11474.42.534.937 I slot print_timing: id 1 | task 2878590 | n_gen = 177, tg = 57.82 t/s, tg_3s = 58.15 t/s
llama-server | 11474.45.560.808 I slot print_timing: id 1 | task 2878590 | n_gen = 348, tg = 57.17 t/s, tg_3s = 56.51 t/s
llama-server | 11474.48.571.269 I slot print_timing: id 1 | task 2878590 | n_gen = 504, tg = 55.40 t/s, tg_3s = 51.82 t/s
llama-server | 11474.51.608.185 I slot print_timing: id 1 | task 2878590 | n_gen = 686, tg = 56.53 t/s, tg_3s = 59.93 t/s
llama-server | 11474.54.650.742 I slot print_timing: id 1 | task 2878590 | n_gen = 850, tg = 56.00 t/s, tg_3s = 53.90 t/s
llama-server | 11474.57.674.072 I slot print_timing: id 1 | task 2878590 | n_gen = 980, tg = 53.84 t/s, tg_3s = 43.00 t/s
llama-server | 11475.00.722.740 I slot print_timing: id 1 | task 2878590 | n_gen = 1136, tg = 53.46 t/s, tg_3s = 51.17 t/s
llama-server | 11475.03.776.043 I slot print_timing: id 1 | task 2878590 | n_gen = 1310, tg = 53.90 t/s, tg_3s = 56.99 t/s
llama-server | 11475.06.811.192 I slot print_timing: id 1 | task 2878590 | n_gen = 1444, tg = 52.82 t/s, tg_3s = 44.15 t/s
llama-server | 11475.09.866.282 I slot print_timing: id 1 | task 2878590 | n_gen = 1589, tg = 52.28 t/s, tg_3s = 47.46 t/s
llama-server | 11475.12.919.165 I slot print_timing: id 1 | task 2878590 | n_gen = 1783, tg = 53.31 t/s, tg_3s = 63.55 t/s
llama-server | 11475.15.988.964 I slot print_timing: id 1 | task 2878590 | n_gen = 1959, tg = 53.65 t/s, tg_3s = 57.33 t/s
llama-server | 11475.18.991.606 I slot print_timing: id 1 | task 2878590 | n_gen = 2147, tg = 54.33 t/s, tg_3s = 62.61 t/s
llama-server | 11475.22.008.228 I slot print_timing: id 1 | task 2878590 | n_gen = 2350, tg = 55.25 t/s, tg_3s = 67.29 t/s
llama-server | 11475.25.017.106 I slot print_timing: id 1 | task 2878590 | n_gen = 2573, tg = 56.50 t/s, tg_3s = 74.11 t/s
llama-server | 11475.25.883.355 I slot print_timing: id 1 | task 2878590 | prompt eval time = 4101.91 ms / 3722 tokens ( 1.10 ms per token, 907.38 tokens per second)
llama-server | 11475.25.883.359 I slot print_timing: id 1 | task 2878590 | eval time = 46392.13 ms / 2636 tokens ( 17.61 ms per token, 56.80 tokens per second)
llama-server | 11475.25.883.359 I slot print_timing: id 1 | task 2878590 | total time = 50494.05 ms / 6358 tokens
llama-server | 11475.25.883.360 I slot print_timing: id 1 | task 2878590 | graphs reused = 2787580
llama-server | 11475.25.883.363 I slot print_timing: id 1 | task 2878590 | draft acceptance = 0.66678 ( 2027 accepted / 3040 generated), mean len = 4.33
llama-server | 11475.25.883.531 I slot release: id 1 | task 2878590 | stop processing: n_tokens = 7649, truncated = 0
llama-server | 11475.26.002.167 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.844 (> 0.100 thold), f_keep = 0.200
llama-server | 11475.26.654.839 I slot launch_slot_: id 0 | task 2879204 | processing task, is_child = 0
llama-server | 11475.30.960.636 I slot print_timing: id 0 | task 2879204 | n_gen = 213, tg = 70.20 t/s, tg_3s = 70.53 t/s
llama-server | 11475.33.996.960 I slot print_timing: id 0 | task 2879204 | n_gen = 436, tg = 71.83 t/s, tg_3s = 73.44 t/s
llama-server | 11475.37.040.840 I slot print_timing: id 0 | task 2879204 | n_gen = 680, tg = 74.62 t/s, tg_3s = 80.16 t/s
llama-server | 11475.38.503.923 I slot print_timing: id 0 | task 2879204 | prompt eval time = 664.88 ms / 244 tokens ( 2.72 ms per token, 366.99 tokens per second)
llama-server | 11475.38.503.927 I slot print_timing: id 0 | task 2879204 | eval time = 10563.06 ms / 795 tokens ( 13.30 ms per token, 75.17 tokens per second)
llama-server | 11475.38.503.928 I slot print_timing: id 0 | task 2879204 | total time = 11227.94 ms / 1039 tokens
llama-server | 11475.38.503.928 I slot print_timing: id 0 | task 2879204 | graphs reused = 2787722
llama-server | 11475.38.503.931 I slot print_timing: id 0 | task 2879204 | draft acceptance = 0.88767 ( 648 accepted / 730 generated), mean len = 5.44
llama-server | 11475.38.504.037 I slot release: id 0 | task 2879204 | stop processing: n_tokens = 2330, truncated = 0
llama-server | 11475.45.397.403 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.557
llama-server | 11475.45.398.227 I slot launch_slot_: id 0 | task 2879353 | processing task, is_child = 0
llama-server | 11475.51.575.753 I slot print_timing: id 0 | task 2879353 | n_gen = 157, tg = 50.69 t/s, tg_3s = 51.01 t/s
llama-server | 11475.54.614.863 I slot print_timing: id 0 | task 2879353 | n_gen = 320, tg = 52.15 t/s, tg_3s = 53.63 t/s
llama-server | 11475.57.682.170 I slot print_timing: id 0 | task 2879353 | n_gen = 477, tg = 51.83 t/s, tg_3s = 51.18 t/s
llama-server | 11476.00.746.154 I slot print_timing: id 0 | task 2879353 | n_gen = 663, tg = 54.05 t/s, tg_3s = 60.71 t/s
llama-server | 11476.03.752.785 I slot print_timing: id 0 | task 2879353 | n_gen = 881, tg = 57.69 t/s, tg_3s = 72.51 t/s
llama-server | 11476.05.604.122 I slot print_timing: id 0 | task 2879353 | prompt eval time = 3099.30 ms / 2910 tokens ( 1.07 ms per token, 938.92 tokens per second)
llama-server | 11476.05.604.125 I slot print_timing: id 0 | task 2879353 | eval time = 17105.81 ms / 1017 tokens ( 16.84 ms per token, 59.40 tokens per second)
llama-server | 11476.05.604.126 I slot print_timing: id 0 | task 2879353 | total time = 20205.11 ms / 3927 tokens
llama-server | 11476.05.604.127 I slot print_timing: id 0 | task 2879353 | graphs reused = 2787951
llama-server | 11476.05.604.130 I slot print_timing: id 0 | task 2879353 | draft acceptance = 0.66838 ( 782 accepted / 1170 generated), mean len = 4.34
llama-server | 11476.05.604.294 I slot release: id 0 | task 2879353 | stop processing: n_tokens = 5218, truncated = 0
llama-server | 11476.05.722.734 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.822 (> 0.100 thold), f_keep = 0.249
llama-server | 11476.05.723.557 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1057.148 MiB)
llama-server | 11476.06.345.204 I slot launch_slot_: id 0 | task 2879592 | processing task, is_child = 0
llama-server | 11476.09.994.139 I slot print_timing: id 0 | task 2879592 | n_gen = 156, tg = 51.61 t/s, tg_3s = 51.94 t/s
llama-server | 11476.13.021.998 I slot print_timing: id 0 | task 2879592 | n_gen = 330, tg = 54.55 t/s, tg_3s = 57.47 t/s
llama-server | 11476.16.056.470 I slot print_timing: id 0 | task 2879592 | n_gen = 532, tg = 58.57 t/s, tg_3s = 66.57 t/s
llama-server | 11476.19.072.017 I slot print_timing: id 0 | task 2879592 | n_gen = 730, tg = 60.34 t/s, tg_3s = 65.66 t/s
llama-server | 11476.22.120.959 I slot print_timing: id 0 | task 2879592 | n_gen = 936, tg = 61.80 t/s, tg_3s = 67.56 t/s
llama-server | 11476.25.171.004 I slot print_timing: id 0 | task 2879592 | n_gen = 1108, tg = 60.89 t/s, tg_3s = 56.39 t/s
llama-server | 11476.28.233.314 I slot print_timing: id 0 | task 2879592 | n_gen = 1305, tg = 61.39 t/s, tg_3s = 64.33 t/s
llama-server | 11476.31.297.579 I slot print_timing: id 0 | task 2879592 | n_gen = 1513, tg = 62.20 t/s, tg_3s = 67.88 t/s
llama-server | 11476.34.353.827 I slot print_timing: id 0 | task 2879592 | n_gen = 1755, tg = 64.10 t/s, tg_3s = 79.18 t/s
llama-server | 11476.35.724.960 W srv stop: cancel task, id_task = 2879592
llama-server | 11476.35.756.582 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688541723584
llama-server | 11476.35.757.056 I slot launch_slot_: id 1 | task 2879992 | processing task, is_child = 0
llama-server | 11476.35.757.060 I slot release: id 0 | task 2879592 | stop processing: n_tokens = 3444, truncated = 0
llama-server | 11476.40.797.317 I slot print_timing: id 1 | task 2879992 | n_gen = 165, tg = 53.94 t/s, tg_3s = 54.27 t/s
llama-server | 11476.43.816.965 I slot print_timing: id 1 | task 2879992 | n_gen = 354, tg = 58.25 t/s, tg_3s = 62.59 t/s
llama-server | 11476.46.841.805 I slot print_timing: id 1 | task 2879992 | n_gen = 544, tg = 59.77 t/s, tg_3s = 62.81 t/s
llama-server | 11476.49.867.931 I slot print_timing: id 1 | task 2879992 | n_gen = 698, tg = 57.55 t/s, tg_3s = 50.89 t/s
llama-server | 11476.52.905.835 I slot print_timing: id 1 | task 2879992 | n_gen = 940, tg = 61.98 t/s, tg_3s = 79.66 t/s
llama-server | 11476.54.677.483 I slot print_timing: id 1 | task 2879992 | prompt eval time = 1999.61 ms / 1577 tokens ( 1.27 ms per token, 788.65 tokens per second)
llama-server | 11476.54.677.486 I slot print_timing: id 1 | task 2879992 | eval time = 16920.55 ms / 1082 tokens ( 15.65 ms per token, 63.89 tokens per second)
llama-server | 11476.54.677.487 I slot print_timing: id 1 | task 2879992 | total time = 18920.16 ms / 2659 tokens
llama-server | 11476.54.677.487 I slot print_timing: id 1 | task 2879992 | graphs reused = 2788564
llama-server | 11476.54.677.514 I slot print_timing: id 1 | task 2879992 | draft acceptance = 0.74498 ( 853 accepted / 1145 generated), mean len = 4.72
llama-server | 11476.54.677.596 I slot release: id 1 | task 2879992 | stop processing: n_tokens = 2659, truncated = 0
llama-server | 11477.07.509.972 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.254 (> 0.100 thold), f_keep = 0.377
llama-server | 11477.07.510.464 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1218.816 MiB)
llama-server | 11477.07.998.449 I slot launch_slot_: id 0 | task 2880227 | processing task, is_child = 0
llama-server | 11477.07.998.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1106.681 MiB)
llama-server | 11477.12.232.879 I slot print_timing: id 0 | task 2880227 | prompt processing, n_tokens = 3818, progress = 1.00, t = 3.26 s / 1172.31 tokens per second
llama-server | 11477.15.446.857 I slot print_timing: id 0 | task 2880227 | n_gen = 158, tg = 51.62 t/s, tg_3s = 51.94 t/s
llama-server | 11477.18.491.148 I slot print_timing: id 0 | task 2880227 | n_gen = 345, tg = 56.52 t/s, tg_3s = 61.43 t/s
llama-server | 11477.21.516.359 I slot print_timing: id 0 | task 2880227 | n_gen = 507, tg = 55.54 t/s, tg_3s = 53.55 t/s
llama-server | 11477.24.574.964 I slot print_timing: id 0 | task 2880227 | n_gen = 680, tg = 55.79 t/s, tg_3s = 56.56 t/s
llama-server | 11477.27.636.441 I slot print_timing: id 0 | task 2880227 | n_gen = 850, tg = 55.74 t/s, tg_3s = 55.53 t/s
llama-server | 11477.30.692.494 I slot print_timing: id 0 | task 2880227 | n_gen = 1035, tg = 56.54 t/s, tg_3s = 60.54 t/s
llama-server | 11477.33.697.662 I slot print_timing: id 0 | task 2880227 | n_gen = 1240, tg = 58.19 t/s, tg_3s = 68.22 t/s
llama-server | 11477.36.705.023 I slot print_timing: id 0 | task 2880227 | n_gen = 1403, tg = 57.70 t/s, tg_3s = 54.20 t/s
llama-server | 11477.37.512.612 W srv stop: cancel task, id_task = 2880227
llama-server | 11477.37.582.097 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688630517648
llama-server | 11477.37.635.761 I slot launch_slot_: id 1 | task 2880578 | processing task, is_child = 0
llama-server | 11477.37.635.766 I slot release: id 0 | task 2880227 | stop processing: n_tokens = 6575, truncated = 0
llama-server | 11477.41.552.770 I slot print_timing: id 1 | task 2880578 | prompt processing, n_tokens = 3818, progress = 1.00, t = 3.44 s / 1109.88 tokens per second
llama-server | 11477.44.808.395 I slot print_timing: id 1 | task 2880578 | n_gen = 169, tg = 55.41 t/s, tg_3s = 55.73 t/s
llama-server | 11477.47.816.830 I slot print_timing: id 1 | task 2880578 | n_gen = 332, tg = 54.80 t/s, tg_3s = 54.18 t/s
llama-server | 11477.50.843.221 I slot print_timing: id 1 | task 2880578 | n_gen = 462, tg = 50.84 t/s, tg_3s = 42.96 t/s
llama-server | 11477.53.854.868 I slot print_timing: id 1 | task 2880578 | n_gen = 599, tg = 49.51 t/s, tg_3s = 45.49 t/s
llama-server | 11477.56.884.275 I slot print_timing: id 1 | task 2880578 | n_gen = 717, tg = 47.39 t/s, tg_3s = 38.95 t/s
llama-server | 11477.59.907.719 I slot print_timing: id 1 | task 2880578 | n_gen = 839, tg = 46.22 t/s, tg_3s = 40.35 t/s
llama-server | 11478.02.951.091 I slot print_timing: id 1 | task 2880578 | n_gen = 995, tg = 46.94 t/s, tg_3s = 51.26 t/s
llama-server | 11478.05.999.246 I slot print_timing: id 1 | task 2880578 | n_gen = 1159, tg = 47.81 t/s, tg_3s = 53.80 t/s
llama-server | 11478.09.035.183 I slot print_timing: id 1 | task 2880578 | n_gen = 1293, tg = 47.40 t/s, tg_3s = 44.14 t/s
llama-server | 11478.12.089.098 I slot print_timing: id 1 | task 2880578 | n_gen = 1423, tg = 46.91 t/s, tg_3s = 42.57 t/s
llama-server | 11478.15.124.065 I slot print_timing: id 1 | task 2880578 | n_gen = 1545, tg = 46.30 t/s, tg_3s = 40.20 t/s
llama-server | 11478.18.186.396 I slot print_timing: id 1 | task 2880578 | n_gen = 1717, tg = 47.13 t/s, tg_3s = 56.17 t/s
llama-server | 11478.21.243.469 I slot print_timing: id 1 | task 2880578 | n_gen = 1871, tg = 47.38 t/s, tg_3s = 50.37 t/s
llama-server | 11478.24.309.874 I slot print_timing: id 1 | task 2880578 | n_gen = 1997, tg = 46.93 t/s, tg_3s = 41.09 t/s
llama-server | 11478.27.358.089 I slot print_timing: id 1 | task 2880578 | n_gen = 2128, tg = 46.66 t/s, tg_3s = 42.98 t/s
llama-server | 11478.30.427.140 I slot print_timing: id 1 | task 2880578 | n_gen = 2253, tg = 46.29 t/s, tg_3s = 40.73 t/s
llama-server | 11478.33.436.251 I slot print_timing: id 1 | task 2880578 | n_gen = 2459, tg = 47.58 t/s, tg_3s = 68.46 t/s
llama-server | 11478.35.280.079 I slot print_timing: id 1 | task 2880578 | prompt eval time = 4140.35 ms / 3822 tokens ( 1.08 ms per token, 923.11 tokens per second)
llama-server | 11478.35.280.082 I slot print_timing: id 1 | task 2880578 | eval time = 53503.70 ms / 2602 tokens ( 20.57 ms per token, 48.61 tokens per second)
llama-server | 11478.35.280.082 I slot print_timing: id 1 | task 2880578 | total time = 57644.05 ms / 6424 tokens
llama-server | 11478.35.280.083 I slot print_timing: id 1 | task 2880578 | graphs reused = 2789595
llama-server | 11478.35.280.086 I slot print_timing: id 1 | task 2880578 | draft acceptance = 0.53997 ( 1898 accepted / 3515 generated), mean len = 3.70
llama-server | 11478.35.280.243 I slot release: id 1 | task 2880578 | stop processing: n_tokens = 7715, truncated = 0
llama-server | 11478.35.390.692 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.826 (> 0.100 thold), f_keep = 0.197
llama-server | 11478.36.304.162 I slot launch_slot_: id 0 | task 2881287 | processing task, is_child = 0
llama-server | 11478.40.552.221 I slot print_timing: id 0 | task 2881287 | n_gen = 221, tg = 73.04 t/s, tg_3s = 73.37 t/s
llama-server | 11478.43.576.907 I slot print_timing: id 0 | task 2881287 | n_gen = 447, tg = 73.88 t/s, tg_3s = 74.72 t/s
llama-server | 11478.46.601.436 I slot print_timing: id 0 | task 2881287 | n_gen = 692, tg = 76.26 t/s, tg_3s = 81.00 t/s
llama-server | 11478.47.410.091 I slot print_timing: id 0 | task 2881287 | prompt eval time = 605.46 ms / 278 tokens ( 2.18 ms per token, 459.16 tokens per second)
llama-server | 11478.47.410.094 I slot print_timing: id 0 | task 2881287 | eval time = 9869.73 ms / 753 tokens ( 13.12 ms per token, 76.19 tokens per second)
llama-server | 11478.47.410.095 I slot print_timing: id 0 | task 2881287 | total time = 10475.19 ms / 1031 tokens
llama-server | 11478.47.410.095 I slot print_timing: id 0 | task 2881287 | graphs reused = 2789728
llama-server | 11478.47.410.099 I slot print_timing: id 0 | task 2881287 | draft acceptance = 0.89781 ( 615 accepted / 685 generated), mean len = 5.49
llama-server | 11478.47.410.191 I slot release: id 0 | task 2881287 | stop processing: n_tokens = 2322, truncated = 0
llama-server | 11478.55.754.858 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.559
llama-server | 11478.55.755.521 I slot launch_slot_: id 0 | task 2881427 | processing task, is_child = 0
llama-server | 11479.01.833.010 I slot print_timing: id 0 | task 2881427 | n_gen = 165, tg = 53.79 t/s, tg_3s = 54.12 t/s
llama-server | 11479.04.842.052 I slot print_timing: id 0 | task 2881427 | n_gen = 319, tg = 52.49 t/s, tg_3s = 51.18 t/s
llama-server | 11479.07.879.867 I slot print_timing: id 0 | task 2881427 | n_gen = 483, tg = 52.99 t/s, tg_3s = 53.99 t/s
llama-server | 11479.10.932.729 I slot print_timing: id 0 | task 2881427 | n_gen = 682, tg = 56.06 t/s, tg_3s = 65.18 t/s
llama-server | 11479.13.986.799 I slot print_timing: id 0 | task 2881427 | n_gen = 923, tg = 60.65 t/s, tg_3s = 78.91 t/s
llama-server | 11479.15.893.459 I slot print_timing: id 0 | task 2881427 | prompt eval time = 3028.07 ms / 2906 tokens ( 1.04 ms per token, 959.69 tokens per second)
llama-server | 11479.15.893.462 I slot print_timing: id 0 | task 2881427 | eval time = 17109.22 ms / 1076 tokens ( 15.92 ms per token, 62.83 tokens per second)
llama-server | 11479.15.893.463 I slot print_timing: id 0 | task 2881427 | total time = 20137.30 ms / 3982 tokens
llama-server | 11479.15.893.464 I slot print_timing: id 0 | task 2881427 | graphs reused = 2789959
llama-server | 11479.15.893.467 I slot print_timing: id 0 | task 2881427 | draft acceptance = 0.71102 ( 839 accepted / 1180 generated), mean len = 4.56
llama-server | 11479.15.893.612 I slot release: id 0 | task 2881427 | stop processing: n_tokens = 5273, truncated = 0
llama-server | 11479.16.006.627 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.830 (> 0.100 thold), f_keep = 0.246
llama-server | 11479.16.007.160 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1114.727 MiB)
llama-server | 11479.16.735.662 I slot launch_slot_: id 0 | task 2881668 | processing task, is_child = 0
llama-server | 11479.20.414.210 I slot print_timing: id 0 | task 2881668 | n_gen = 201, tg = 65.15 t/s, tg_3s = 65.47 t/s
llama-server | 11479.23.426.528 I slot print_timing: id 0 | task 2881668 | n_gen = 417, tg = 68.40 t/s, tg_3s = 71.71 t/s
llama-server | 11479.25.587.210 I slot print_timing: id 0 | task 2881668 | prompt eval time = 608.38 ms / 270 tokens ( 2.25 ms per token, 443.80 tokens per second)
llama-server | 11479.25.587.214 I slot print_timing: id 0 | task 2881668 | eval time = 8242.66 ms / 596 tokens ( 13.85 ms per token, 72.19 tokens per second)
llama-server | 11479.25.587.214 I slot print_timing: id 0 | task 2881668 | total time = 8851.04 ms / 866 tokens
llama-server | 11479.25.587.215 I slot print_timing: id 0 | task 2881668 | graphs reused = 2790071
llama-server | 11479.25.587.218 I slot print_timing: id 0 | task 2881668 | draft acceptance = 0.83478 ( 480 accepted / 575 generated), mean len = 5.17
llama-server | 11479.25.587.307 I slot release: id 0 | task 2881668 | stop processing: n_tokens = 2157, truncated = 0
llama-server | 11479.30.823.964 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.601
llama-server | 11479.30.824.629 I slot launch_slot_: id 0 | task 2881786 | processing task, is_child = 0
llama-server | 11479.36.834.241 I slot print_timing: id 0 | task 2881786 | n_gen = 163, tg = 53.73 t/s, tg_3s = 54.05 t/s
llama-server | 11479.39.849.979 I slot print_timing: id 0 | task 2881786 | n_gen = 315, tg = 52.06 t/s, tg_3s = 50.40 t/s
llama-server | 11479.42.892.655 I slot print_timing: id 0 | task 2881786 | n_gen = 458, tg = 50.37 t/s, tg_3s = 47.00 t/s
llama-server | 11479.45.964.972 I slot print_timing: id 0 | task 2881786 | n_gen = 594, tg = 48.82 t/s, tg_3s = 44.27 t/s
llama-server | 11479.49.003.616 I slot print_timing: id 0 | task 2881786 | n_gen = 751, tg = 49.39 t/s, tg_3s = 51.67 t/s
llama-server | 11479.52.074.643 I slot print_timing: id 0 | task 2881786 | n_gen = 940, tg = 51.44 t/s, tg_3s = 61.54 t/s
llama-server | 11479.55.141.092 I slot print_timing: id 0 | task 2881786 | n_gen = 1172, tg = 54.92 t/s, tg_3s = 75.66 t/s
llama-server | 11479.57.125.931 I slot print_timing: id 0 | task 2881786 | prompt eval time = 2993.71 ms / 2906 tokens ( 1.03 ms per token, 970.70 tokens per second)
llama-server | 11479.57.125.934 I slot print_timing: id 0 | task 2881786 | eval time = 23306.93 ms / 1323 tokens ( 17.63 ms per token, 56.72 tokens per second)
llama-server | 11479.57.125.935 I slot print_timing: id 0 | task 2881786 | total time = 26300.64 ms / 4229 tokens
llama-server | 11479.57.125.935 I slot print_timing: id 0 | task 2881786 | graphs reused = 2790376
llama-server | 11479.57.125.938 I slot print_timing: id 0 | task 2881786 | draft acceptance = 0.65016 ( 1011 accepted / 1555 generated), mean len = 4.25
llama-server | 11479.57.126.091 I slot release: id 0 | task 2881786 | stop processing: n_tokens = 5520, truncated = 0
llama-server | 11479.57.257.734 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.825 (> 0.100 thold), f_keep = 0.235
llama-server | 11479.57.824.410 I slot launch_slot_: id 0 | task 2882102 | processing task, is_child = 0
llama-server | 11480.01.466.403 I slot print_timing: id 0 | task 2882102 | n_gen = 152, tg = 50.25 t/s, tg_3s = 50.57 t/s
llama-server | 11480.04.473.432 I slot print_timing: id 0 | task 2882102 | n_gen = 310, tg = 51.39 t/s, tg_3s = 52.54 t/s
llama-server | 11480.07.535.874 I slot print_timing: id 0 | task 2882102 | n_gen = 474, tg = 52.12 t/s, tg_3s = 53.55 t/s
llama-server | 11480.10.552.052 I slot print_timing: id 0 | task 2882102 | n_gen = 634, tg = 52.35 t/s, tg_3s = 53.05 t/s
llama-server | 11480.13.579.349 I slot print_timing: id 0 | task 2882102 | n_gen = 829, tg = 54.77 t/s, tg_3s = 64.41 t/s
llama-server | 11480.16.605.340 I slot print_timing: id 0 | task 2882102 | n_gen = 997, tg = 54.89 t/s, tg_3s = 55.52 t/s
llama-server | 11480.19.616.626 I slot print_timing: id 0 | task 2882102 | n_gen = 1141, tg = 53.89 t/s, tg_3s = 47.82 t/s
llama-server | 11480.22.660.799 I slot print_timing: id 0 | task 2882102 | n_gen = 1356, tg = 55.99 t/s, tg_3s = 70.63 t/s
llama-server | 11480.25.716.112 I slot print_timing: id 0 | task 2882102 | n_gen = 1588, tg = 58.23 t/s, tg_3s = 75.93 t/s
llama-server | 11480.27.260.499 W srv stop: cancel task, id_task = 2882102
llama-server | 11480.27.304.833 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688731120295
llama-server | 11480.27.305.239 I slot launch_slot_: id 1 | task 2882506 | processing task, is_child = 0
llama-server | 11480.27.305.242 I slot release: id 0 | task 2882102 | stop processing: n_tokens = 3263, truncated = 0
llama-server | 11480.32.253.803 I slot print_timing: id 1 | task 2882506 | n_gen = 143, tg = 46.57 t/s, tg_3s = 46.90 t/s
llama-server | 11480.35.295.596 I slot print_timing: id 1 | task 2882506 | n_gen = 282, tg = 46.14 t/s, tg_3s = 45.70 t/s
llama-server | 11480.38.295.955 I slot print_timing: id 1 | task 2882506 | n_gen = 421, tg = 46.20 t/s, tg_3s = 46.33 t/s
llama-server | 11480.41.368.470 I slot print_timing: id 1 | task 2882506 | n_gen = 587, tg = 48.18 t/s, tg_3s = 54.03 t/s
llama-server | 11480.44.424.560 I slot print_timing: id 1 | task 2882506 | n_gen = 743, tg = 48.75 t/s, tg_3s = 51.05 t/s
llama-server | 11480.47.432.166 I slot print_timing: id 1 | task 2882506 | n_gen = 896, tg = 49.10 t/s, tg_3s = 50.87 t/s
llama-server | 11480.50.488.516 I slot print_timing: id 1 | task 2882506 | n_gen = 1013, tg = 47.55 t/s, tg_3s = 38.28 t/s
llama-server | 11480.53.498.458 I slot print_timing: id 1 | task 2882506 | n_gen = 1172, tg = 48.20 t/s, tg_3s = 52.82 t/s
llama-server | 11480.56.518.163 I slot print_timing: id 1 | task 2882506 | n_gen = 1355, tg = 49.57 t/s, tg_3s = 60.60 t/s
llama-server | 11480.59.521.147 I slot print_timing: id 1 | task 2882506 | n_gen = 1497, tg = 49.35 t/s, tg_3s = 47.29 t/s
llama-server | 11481.02.584.790 I slot print_timing: id 1 | task 2882506 | n_gen = 1642, tg = 49.16 t/s, tg_3s = 47.33 t/s
llama-server | 11481.05.586.808 I slot print_timing: id 1 | task 2882506 | n_gen = 1796, tg = 49.34 t/s, tg_3s = 51.30 t/s
llama-server | 11481.08.618.273 I slot print_timing: id 1 | task 2882506 | n_gen = 1946, tg = 49.35 t/s, tg_3s = 49.48 t/s
llama-server | 11481.11.644.650 I slot print_timing: id 1 | task 2882506 | n_gen = 2100, tg = 49.46 t/s, tg_3s = 50.89 t/s
llama-server | 11481.14.659.797 I slot print_timing: id 1 | task 2882506 | n_gen = 2267, tg = 49.85 t/s, tg_3s = 55.39 t/s
llama-server | 11481.17.696.792 I slot print_timing: id 1 | task 2882506 | n_gen = 2425, tg = 49.99 t/s, tg_3s = 52.03 t/s
llama-server | 11481.20.716.324 I slot print_timing: id 1 | task 2882506 | n_gen = 2574, tg = 49.95 t/s, tg_3s = 49.35 t/s
llama-server | 11481.23.762.251 I slot print_timing: id 1 | task 2882506 | n_gen = 2761, tg = 50.59 t/s, tg_3s = 61.39 t/s
llama-server | 11481.26.803.689 I slot print_timing: id 1 | task 2882506 | n_gen = 2898, tg = 50.30 t/s, tg_3s = 45.04 t/s
llama-server | 11481.29.837.173 I slot print_timing: id 1 | task 2882506 | n_gen = 3061, tg = 50.47 t/s, tg_3s = 53.73 t/s
llama-server | 11481.32.883.727 I slot print_timing: id 1 | task 2882506 | n_gen = 3217, tg = 50.50 t/s, tg_3s = 51.21 t/s
llama-server | 11481.35.924.283 I slot print_timing: id 1 | task 2882506 | n_gen = 3331, tg = 49.91 t/s, tg_3s = 37.49 t/s
llama-server | 11481.38.981.450 I slot print_timing: id 1 | task 2882506 | n_gen = 3467, tg = 49.67 t/s, tg_3s = 44.49 t/s
llama-server | 11481.42.040.375 I slot print_timing: id 1 | task 2882506 | n_gen = 3623, tg = 49.73 t/s, tg_3s = 51.00 t/s
llama-server | 11481.45.077.217 I slot print_timing: id 1 | task 2882506 | n_gen = 3739, tg = 49.27 t/s, tg_3s = 38.20 t/s
llama-server | 11481.48.133.244 I slot print_timing: id 1 | task 2882506 | n_gen = 3882, tg = 49.17 t/s, tg_3s = 46.79 t/s
llama-server | 11481.51.189.628 I slot print_timing: id 1 | task 2882506 | n_gen = 4068, tg = 49.61 t/s, tg_3s = 60.86 t/s
llama-server | 11481.54.260.083 I slot print_timing: id 1 | task 2882506 | n_gen = 4242, tg = 49.86 t/s, tg_3s = 56.67 t/s
llama-server | 11481.57.310.174 I slot print_timing: id 1 | task 2882506 | n_gen = 4382, tg = 49.72 t/s, tg_3s = 45.90 t/s
llama-server | 11482.00.310.860 I slot print_timing: id 1 | task 2882506 | n_gen = 4537, tg = 49.79 t/s, tg_3s = 51.65 t/s
llama-server | 11482.03.315.520 I slot print_timing: id 1 | task 2882506 | n_gen = 4722, tg = 50.16 t/s, tg_3s = 61.57 t/s
llama-server | 11482.06.324.855 I slot print_timing: id 1 | task 2882506 | n_gen = 4915, tg = 50.60 t/s, tg_3s = 64.13 t/s
llama-server | 11482.09.399.746 I slot print_timing: id 1 | task 2882506 | n_gen = 5077, tg = 50.66 t/s, tg_3s = 52.68 t/s
llama-server | 11482.12.412.329 I slot print_timing: id 1 | task 2882506 | n_gen = 5236, tg = 50.72 t/s, tg_3s = 52.78 t/s
llama-server | 11482.15.430.838 I slot print_timing: id 1 | task 2882506 | n_gen = 5437, tg = 51.17 t/s, tg_3s = 66.59 t/s
llama-server | 11482.18.500.959 I slot print_timing: id 1 | task 2882506 | n_gen = 5585, tg = 51.09 t/s, tg_3s = 48.21 t/s
llama-server | 11482.21.517.048 I slot print_timing: id 1 | task 2882506 | n_gen = 5717, tg = 50.89 t/s, tg_3s = 43.77 t/s
llama-server | 11482.24.588.111 I slot print_timing: id 1 | task 2882506 | n_gen = 5857, tg = 50.75 t/s, tg_3s = 45.59 t/s
llama-server | 11482.27.604.371 I slot print_timing: id 1 | task 2882506 | n_gen = 6000, tg = 50.67 t/s, tg_3s = 47.41 t/s
llama-server | 11482.30.643.034 I slot print_timing: id 1 | task 2882506 | n_gen = 6238, tg = 51.36 t/s, tg_3s = 78.32 t/s
llama-server | 11482.31.323.717 I slot print_timing: id 1 | task 2882506 | prompt eval time = 1899.35 ms / 1572 tokens ( 1.21 ms per token, 827.65 tokens per second)
llama-server | 11482.31.323.721 I slot print_timing: id 1 | task 2882506 | eval time = 122118.87 ms / 6291 tokens ( 19.41 ms per token, 51.51 tokens per second)
llama-server | 11482.31.323.722 I slot print_timing: id 1 | task 2882506 | total time = 124018.22 ms / 7863 tokens
llama-server | 11482.31.323.723 I slot print_timing: id 1 | task 2882506 | graphs reused = 2792389
llama-server | 11482.31.323.725 I slot print_timing: id 1 | task 2882506 | draft acceptance = 0.56486 ( 4646 accepted / 8225 generated), mean len = 3.82
llama-server | 11482.31.323.814 I slot release: id 1 | task 2882506 | stop processing: n_tokens = 7863, truncated = 0
llama-server | 11482.41.020.944 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.249 (> 0.100 thold), f_keep = 0.397
llama-server | 11482.41.021.531 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1136.585 MiB)
llama-server | 11482.41.518.347 I slot launch_slot_: id 0 | task 2884157 | processing task, is_child = 0
llama-server | 11482.41.518.966 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1129.816 MiB)
llama-server | 11482.45.877.994 I slot print_timing: id 0 | task 2884157 | prompt processing, n_tokens = 3915, progress = 1.00, t = 3.23 s / 1211.84 tokens per second
llama-server | 11482.49.071.417 I slot print_timing: id 0 | task 2884157 | n_gen = 169, tg = 55.13 t/s, tg_3s = 55.45 t/s
llama-server | 11482.52.112.894 I slot print_timing: id 0 | task 2884157 | n_gen = 312, tg = 51.08 t/s, tg_3s = 47.02 t/s
llama-server | 11482.55.155.386 I slot print_timing: id 0 | task 2884157 | n_gen = 463, tg = 50.60 t/s, tg_3s = 49.63 t/s
llama-server | 11482.58.191.381 I slot print_timing: id 0 | task 2884157 | n_gen = 613, tg = 50.30 t/s, tg_3s = 49.41 t/s
llama-server | 11483.01.248.484 I slot print_timing: id 0 | task 2884157 | n_gen = 755, tg = 49.53 t/s, tg_3s = 46.45 t/s
llama-server | 11483.04.297.906 I slot print_timing: id 0 | task 2884157 | n_gen = 919, tg = 50.24 t/s, tg_3s = 53.78 t/s
llama-server | 11483.07.301.593 I slot print_timing: id 0 | task 2884157 | n_gen = 1111, tg = 52.17 t/s, tg_3s = 63.92 t/s
llama-server | 11483.10.307.511 I slot print_timing: id 0 | task 2884157 | n_gen = 1281, tg = 52.71 t/s, tg_3s = 56.56 t/s
llama-server | 11483.11.023.273 W srv stop: cancel task, id_task = 2884157
llama-server | 11483.11.042.021 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 688967163866
llama-server | 11483.11.096.494 I slot launch_slot_: id 1 | task 2884506 | processing task, is_child = 0
llama-server | 11483.11.096.499 I slot release: id 0 | task 2884157 | stop processing: n_tokens = 6551, truncated = 0
llama-server | 11483.15.677.279 I slot print_timing: id 1 | task 2884506 | prompt processing, n_tokens = 3403, progress = 0.90, t = 4.17 s / 815.43 tokens per second
llama-server | 11483.16.299.912 I slot print_timing: id 1 | task 2884506 | prompt processing, n_tokens = 3915, progress = 1.00, t = 4.72 s / 829.07 tokens per second
llama-server | 11483.19.491.307 I slot print_timing: id 1 | task 2884506 | n_gen = 170, tg = 55.62 t/s, tg_3s = 55.95 t/s
llama-server | 11483.22.511.836 I slot print_timing: id 1 | task 2884506 | n_gen = 315, tg = 51.83 t/s, tg_3s = 48.00 t/s
llama-server | 11483.25.527.041 I slot print_timing: id 1 | task 2884506 | n_gen = 463, tg = 50.91 t/s, tg_3s = 49.08 t/s
llama-server | 11483.28.560.054 I slot print_timing: id 1 | task 2884506 | n_gen = 604, tg = 49.81 t/s, tg_3s = 46.49 t/s
llama-server | 11483.31.580.907 I slot print_timing: id 1 | task 2884506 | n_gen = 744, tg = 49.11 t/s, tg_3s = 46.34 t/s
llama-server | 11483.34.626.986 I slot print_timing: id 1 | task 2884506 | n_gen = 892, tg = 49.03 t/s, tg_3s = 48.59 t/s
llama-server | 11483.37.657.125 I slot print_timing: id 1 | task 2884506 | n_gen = 1037, tg = 48.86 t/s, tg_3s = 47.85 t/s
llama-server | 11483.40.705.875 I slot print_timing: id 1 | task 2884506 | n_gen = 1173, tg = 48.32 t/s, tg_3s = 44.61 t/s
llama-server | 11483.43.764.683 I slot print_timing: id 1 | task 2884506 | n_gen = 1326, tg = 48.51 t/s, tg_3s = 50.02 t/s
llama-server | 11483.46.800.902 I slot print_timing: id 1 | task 2884506 | n_gen = 1451, tg = 47.78 t/s, tg_3s = 41.17 t/s
llama-server | 11483.49.849.919 I slot print_timing: id 1 | task 2884506 | n_gen = 1568, tg = 46.92 t/s, tg_3s = 38.37 t/s
llama-server | 11483.52.898.784 I slot print_timing: id 1 | task 2884506 | n_gen = 1707, tg = 46.81 t/s, tg_3s = 45.59 t/s
llama-server | 11483.55.901.850 I slot print_timing: id 1 | task 2884506 | n_gen = 1858, tg = 47.07 t/s, tg_3s = 50.28 t/s
llama-server | 11483.58.910.012 I slot print_timing: id 1 | task 2884506 | n_gen = 2031, tg = 47.81 t/s, tg_3s = 57.51 t/s
llama-server | 11484.01.933.857 I slot print_timing: id 1 | task 2884506 | n_gen = 2168, tg = 47.65 t/s, tg_3s = 45.31 t/s
llama-server | 11484.04.942.539 I slot print_timing: id 1 | task 2884506 | n_gen = 2309, tg = 47.60 t/s, tg_3s = 46.86 t/s
llama-server | 11484.07.973.083 I slot print_timing: id 1 | task 2884506 | n_gen = 2482, tg = 48.16 t/s, tg_3s = 57.09 t/s
llama-server | 11484.11.004.212 I slot print_timing: id 1 | task 2884506 | n_gen = 2644, tg = 48.45 t/s, tg_3s = 53.45 t/s
llama-server | 11484.14.029.692 I slot print_timing: id 1 | task 2884506 | n_gen = 2814, tg = 48.86 t/s, tg_3s = 56.19 t/s
llama-server | 11484.17.067.659 I slot print_timing: id 1 | task 2884506 | n_gen = 2994, tg = 49.38 t/s, tg_3s = 59.25 t/s
llama-server | 11484.20.120.635 I slot print_timing: id 1 | task 2884506 | n_gen = 3215, tg = 50.48 t/s, tg_3s = 72.39 t/s
llama-server | 11484.23.172.112 I slot print_timing: id 1 | task 2884506 | n_gen = 3433, tg = 51.44 t/s, tg_3s = 71.44 t/s
llama-server | 11484.25.435.249 I slot print_timing: id 1 | task 2884506 | prompt eval time = 5356.30 ms / 3919 tokens ( 1.37 ms per token, 731.66 tokens per second)
llama-server | 11484.25.435.252 I slot print_timing: id 1 | task 2884506 | eval time = 68982.16 ms / 3600 tokens ( 19.17 ms per token, 52.17 tokens per second)
llama-server | 11484.25.435.253 I slot print_timing: id 1 | task 2884506 | total time = 74338.46 ms / 7519 tokens
llama-server | 11484.25.435.254 I slot print_timing: id 1 | task 2884506 | graphs reused = 2793610
llama-server | 11484.25.435.257 I slot print_timing: id 1 | task 2884506 | draft acceptance = 0.60067 ( 2700 accepted / 4495 generated), mean len = 4.00
llama-server | 11484.25.435.490 I slot release: id 1 | task 2884506 | stop processing: n_tokens = 8810, truncated = 0
llama-server | 11484.25.599.448 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.818 (> 0.100 thold), f_keep = 0.198
llama-server | 11484.26.239.019 I slot launch_slot_: id 0 | task 2885411 | processing task, is_child = 0
llama-server | 11484.30.554.577 I slot print_timing: id 0 | task 2885411 | n_gen = 154, tg = 50.88 t/s, tg_3s = 51.20 t/s
llama-server | 11484.33.589.810 I slot print_timing: id 0 | task 2885411 | n_gen = 349, tg = 57.59 t/s, tg_3s = 64.25 t/s
llama-server | 11484.36.638.292 I slot print_timing: id 0 | task 2885411 | n_gen = 555, tg = 60.94 t/s, tg_3s = 67.57 t/s
llama-server | 11484.39.698.294 I slot print_timing: id 0 | task 2885411 | n_gen = 799, tg = 65.67 t/s, tg_3s = 79.74 t/s
llama-server | 11484.41.516.506 I slot print_timing: id 0 | task 2885411 | prompt eval time = 584.29 ms / 293 tokens ( 1.99 ms per token, 501.46 tokens per second)
llama-server | 11484.41.516.510 I slot print_timing: id 0 | task 2885411 | eval time = 13969.27 ms / 946 tokens ( 14.78 ms per token, 67.65 tokens per second)
llama-server | 11484.41.516.510 I slot print_timing: id 0 | task 2885411 | total time = 14553.56 ms / 1239 tokens
llama-server | 11484.41.516.511 I slot print_timing: id 0 | task 2885411 | graphs reused = 2793795
llama-server | 11484.41.516.515 I slot print_timing: id 0 | task 2885411 | draft acceptance = 0.80000 ( 756 accepted / 945 generated), mean len = 5.00
llama-server | 11484.41.516.636 I slot release: id 0 | task 2885411 | stop processing: n_tokens = 2530, truncated = 0
llama-server | 11484.46.114.684 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.260 (> 0.100 thold), f_keep = 0.513
llama-server | 11484.46.115.323 I slot launch_slot_: id 0 | task 2885603 | processing task, is_child = 0
llama-server | 11484.49.776.849 I slot print_timing: id 0 | task 2885603 | prompt processing, n_tokens = 3702, progress = 1.00, t = 3.20 s / 1156.69 tokens per second
llama-server | 11484.52.940.691 I slot print_timing: id 0 | task 2885603 | n_gen = 186, tg = 61.26 t/s, tg_3s = 61.59 t/s
llama-server | 11484.56.006.040 I slot print_timing: id 0 | task 2885603 | n_gen = 356, tg = 58.34 t/s, tg_3s = 55.46 t/s
llama-server | 11484.59.020.084 I slot print_timing: id 0 | task 2885603 | n_gen = 504, tg = 55.28 t/s, tg_3s = 49.10 t/s
llama-server | 11485.02.041.005 I slot print_timing: id 0 | task 2885603 | n_gen = 668, tg = 55.03 t/s, tg_3s = 54.29 t/s
llama-server | 11485.05.056.693 I slot print_timing: id 0 | task 2885603 | n_gen = 832, tg = 54.90 t/s, tg_3s = 54.38 t/s
llama-server | 11485.08.086.171 I slot print_timing: id 0 | task 2885603 | n_gen = 979, tg = 53.84 t/s, tg_3s = 48.52 t/s
llama-server | 11485.11.096.027 I slot print_timing: id 0 | task 2885603 | n_gen = 1127, tg = 53.18 t/s, tg_3s = 49.17 t/s
llama-server | 11485.14.128.753 I slot print_timing: id 0 | task 2885603 | n_gen = 1285, tg = 53.04 t/s, tg_3s = 52.10 t/s
llama-server | 11485.16.117.720 W srv stop: cancel task, id_task = 2885603
llama-server | 11485.16.125.628 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 689081275542
llama-server | 11485.16.126.016 I slot launch_slot_: id 1 | task 2885964 | processing task, is_child = 0
llama-server | 11485.16.126.020 I slot release: id 0 | task 2885603 | stop processing: n_tokens = 6407, truncated = 0
llama-server | 11485.20.608.581 I slot print_timing: id 1 | task 2885964 | prompt processing, n_tokens = 4482, progress = 0.90, t = 4.23 s / 1059.93 tokens per second
llama-server | 11485.21.192.445 I slot print_timing: id 1 | task 2885964 | prompt processing, n_tokens = 4994, progress = 1.00, t = 4.57 s / 1091.64 tokens per second
llama-server | 11485.24.407.167 I slot print_timing: id 1 | task 2885964 | n_gen = 164, tg = 53.62 t/s, tg_3s = 53.94 t/s
llama-server | 11485.27.420.873 I slot print_timing: id 1 | task 2885964 | n_gen = 329, tg = 54.18 t/s, tg_3s = 54.75 t/s
llama-server | 11485.30.455.595 I slot print_timing: id 1 | task 2885964 | n_gen = 488, tg = 53.58 t/s, tg_3s = 52.39 t/s
llama-server | 11485.33.487.609 I slot print_timing: id 1 | task 2885964 | n_gen = 643, tg = 52.97 t/s, tg_3s = 51.12 t/s
llama-server | 11485.36.504.651 I slot print_timing: id 1 | task 2885964 | n_gen = 782, tg = 51.59 t/s, tg_3s = 46.07 t/s
llama-server | 11485.39.550.092 I slot print_timing: id 1 | task 2885964 | n_gen = 954, tg = 52.41 t/s, tg_3s = 56.48 t/s
llama-server | 11485.42.583.324 I slot print_timing: id 1 | task 2885964 | n_gen = 1139, tg = 53.64 t/s, tg_3s = 60.99 t/s
llama-server | 11485.45.633.907 I slot print_timing: id 1 | task 2885964 | n_gen = 1320, tg = 54.35 t/s, tg_3s = 59.33 t/s
llama-server | 11485.48.699.912 I slot print_timing: id 1 | task 2885964 | n_gen = 1533, tg = 56.05 t/s, tg_3s = 69.47 t/s
llama-server | 11485.50.468.393 I slot print_timing: id 1 | task 2885964 | prompt eval time = 5240.86 ms / 4998 tokens ( 1.05 ms per token, 953.66 tokens per second)
llama-server | 11485.50.468.396 I slot print_timing: id 1 | task 2885964 | eval time = 29101.25 ms / 1669 tokens ( 17.45 ms per token, 57.32 tokens per second)
llama-server | 11485.50.468.397 I slot print_timing: id 1 | task 2885964 | total time = 34342.11 ms / 6667 tokens
llama-server | 11485.50.468.398 I slot print_timing: id 1 | task 2885964 | graphs reused = 2794518
llama-server | 11485.50.468.401 I slot print_timing: id 1 | task 2885964 | draft acceptance = 0.67330 ( 1286 accepted / 1910 generated), mean len = 4.37
llama-server | 11485.50.468.619 I slot release: id 1 | task 2885964 | stop processing: n_tokens = 6666, truncated = 0
llama-server | 11485.50.583.851 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.835 (> 0.100 thold), f_keep = 0.202
llama-server | 11485.50.584.772 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1168.604 MiB)
llama-server | 11485.51.213.119 I slot launch_slot_: id 0 | task 2886353 | processing task, is_child = 0
llama-server | 11485.51.213.704 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1132.875 MiB)
llama-server | 11485.55.618.864 I slot print_timing: id 0 | task 2886353 | n_gen = 187, tg = 61.97 t/s, tg_3s = 62.30 t/s
llama-server | 11485.58.637.795 I slot print_timing: id 0 | task 2886353 | n_gen = 432, tg = 71.59 t/s, tg_3s = 81.15 t/s
llama-server | 11486.00.875.735 I slot print_timing: id 0 | task 2886353 | prompt eval time = 593.05 ms / 261 tokens ( 2.27 ms per token, 440.10 tokens per second)
llama-server | 11486.00.875.739 I slot print_timing: id 0 | task 2886353 | eval time = 8258.41 ms / 615 tokens ( 13.45 ms per token, 74.35 tokens per second)
llama-server | 11486.00.875.740 I slot print_timing: id 0 | task 2886353 | total time = 8851.47 ms / 876 tokens
llama-server | 11486.00.875.741 I slot print_timing: id 0 | task 2886353 | graphs reused = 2794628
llama-server | 11486.00.875.744 I slot print_timing: id 0 | task 2886353 | draft acceptance = 0.88673 ( 501 accepted / 565 generated), mean len = 5.43
llama-server | 11486.00.875.836 I slot release: id 0 | task 2886353 | stop processing: n_tokens = 2167, truncated = 0
llama-server | 11486.06.353.334 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.253 (> 0.100 thold), f_keep = 0.599
llama-server | 11486.06.353.977 I slot launch_slot_: id 0 | task 2886469 | processing task, is_child = 0
llama-server | 11486.10.096.151 I slot print_timing: id 0 | task 2886469 | prompt processing, n_tokens = 3832, progress = 1.00, t = 3.28 s / 1168.35 tokens per second
llama-server | 11486.13.312.357 I slot print_timing: id 0 | task 2886469 | n_gen = 175, tg = 57.02 t/s, tg_3s = 57.35 t/s
llama-server | 11486.16.363.485 I slot print_timing: id 0 | task 2886469 | n_gen = 322, tg = 52.60 t/s, tg_3s = 48.18 t/s
llama-server | 11486.19.406.909 I slot print_timing: id 0 | task 2886469 | n_gen = 484, tg = 52.81 t/s, tg_3s = 53.23 t/s
llama-server | 11486.22.417.198 I slot print_timing: id 0 | task 2886469 | n_gen = 652, tg = 53.55 t/s, tg_3s = 55.81 t/s
llama-server | 11486.25.420.781 I slot print_timing: id 0 | task 2886469 | n_gen = 816, tg = 53.76 t/s, tg_3s = 54.60 t/s
llama-server | 11486.28.493.350 I slot print_timing: id 0 | task 2886469 | n_gen = 1009, tg = 55.29 t/s, tg_3s = 62.81 t/s
llama-server | 11486.31.526.768 I slot print_timing: id 0 | task 2886469 | n_gen = 1221, tg = 57.37 t/s, tg_3s = 69.89 t/s
llama-server | 11486.34.543.988 I slot print_timing: id 0 | task 2886469 | n_gen = 1375, tg = 56.58 t/s, tg_3s = 51.04 t/s
llama-server | 11486.36.355.644 W srv stop: cancel task, id_task = 2886469
llama-server | 11486.36.379.587 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 689166308671
llama-server | 11486.36.379.935 I slot launch_slot_: id 1 | task 2886830 | processing task, is_child = 0
llama-server | 11486.36.379.939 I slot release: id 0 | task 2886469 | stop processing: n_tokens = 6646, truncated = 0
llama-server | 11486.40.995.839 I slot print_timing: id 1 | task 2886830 | prompt processing, n_tokens = 4612, progress = 0.90, t = 4.25 s / 1086.02 tokens per second
llama-server | 11486.41.587.515 I slot print_timing: id 1 | task 2886830 | prompt processing, n_tokens = 5124, progress = 1.00, t = 4.71 s / 1086.77 tokens per second
llama-server | 11486.44.760.408 I slot print_timing: id 1 | task 2886830 | n_gen = 175, tg = 57.29 t/s, tg_3s = 57.61 t/s
llama-server | 11486.47.792.692 I slot print_timing: id 1 | task 2886830 | n_gen = 313, tg = 51.40 t/s, tg_3s = 45.51 t/s
llama-server | 11486.50.816.165 I slot print_timing: id 1 | task 2886830 | n_gen = 475, tg = 52.13 t/s, tg_3s = 53.58 t/s
llama-server | 11486.53.863.475 I slot print_timing: id 1 | task 2886830 | n_gen = 626, tg = 51.48 t/s, tg_3s = 49.55 t/s
llama-server | 11486.56.898.897 I slot print_timing: id 1 | task 2886830 | n_gen = 773, tg = 50.87 t/s, tg_3s = 48.43 t/s
llama-server | 11486.59.943.830 I slot print_timing: id 1 | task 2886830 | n_gen = 930, tg = 50.99 t/s, tg_3s = 51.56 t/s
llama-server | 11487.03.002.378 I slot print_timing: id 1 | task 2886830 | n_gen = 1091, tg = 51.22 t/s, tg_3s = 52.64 t/s
llama-server | 11487.06.045.309 I slot print_timing: id 1 | task 2886830 | n_gen = 1274, tg = 52.34 t/s, tg_3s = 60.14 t/s
llama-server | 11487.09.103.679 I slot print_timing: id 1 | task 2886830 | n_gen = 1418, tg = 51.75 t/s, tg_3s = 47.08 t/s
llama-server | 11487.12.178.728 I slot print_timing: id 1 | task 2886830 | n_gen = 1607, tg = 52.73 t/s, tg_3s = 61.46 t/s
llama-server | 11487.15.234.373 I slot print_timing: id 1 | task 2886830 | n_gen = 1780, tg = 53.09 t/s, tg_3s = 56.62 t/s
llama-server | 11487.18.302.628 I slot print_timing: id 1 | task 2886830 | n_gen = 1933, tg = 52.82 t/s, tg_3s = 49.87 t/s
llama-server | 11487.21.312.808 I slot print_timing: id 1 | task 2886830 | n_gen = 2142, tg = 54.08 t/s, tg_3s = 69.43 t/s
llama-server | 11487.24.329.126 I slot print_timing: id 1 | task 2886830 | n_gen = 2367, tg = 55.53 t/s, tg_3s = 74.59 t/s
llama-server | 11487.25.790.217 I slot print_timing: id 1 | task 2886830 | prompt eval time = 5342.90 ms / 5128 tokens ( 1.04 ms per token, 959.78 tokens per second)
llama-server | 11487.25.790.220 I slot print_timing: id 1 | task 2886830 | eval time = 44067.11 ms / 2477 tokens ( 17.80 ms per token, 56.19 tokens per second)
llama-server | 11487.25.790.221 I slot print_timing: id 1 | task 2886830 | total time = 49410.01 ms / 7605 tokens
llama-server | 11487.25.790.221 I slot print_timing: id 1 | task 2886830 | graphs reused = 2795545
llama-server | 11487.25.790.224 I slot print_timing: id 1 | task 2886830 | draft acceptance = 0.65823 ( 1899 accepted / 2885 generated), mean len = 4.29
llama-server | 11487.25.790.398 I slot release: id 1 | task 2886830 | stop processing: n_tokens = 7604, truncated = 0
llama-server | 11487.25.907.869 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.832 (> 0.100 thold), f_keep = 0.195
llama-server | 11487.25.908.797 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1170.799 MiB)
llama-server | 11487.26.606.120 I slot launch_slot_: id 0 | task 2887414 | processing task, is_child = 0
llama-server | 11487.26.606.749 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1097.817 MiB)
llama-server | 11487.31.125.691 I slot print_timing: id 0 | task 2887414 | n_gen = 178, tg = 58.07 t/s, tg_3s = 58.39 t/s
llama-server | 11487.34.133.753 I slot print_timing: id 0 | task 2887414 | n_gen = 340, tg = 55.98 t/s, tg_3s = 53.86 t/s
llama-server | 11487.37.157.746 I slot print_timing: id 0 | task 2887414 | n_gen = 579, tg = 63.66 t/s, tg_3s = 79.03 t/s
llama-server | 11487.39.897.869 I slot print_timing: id 0 | task 2887414 | prompt eval time = 856.66 ms / 267 tokens ( 3.21 ms per token, 311.67 tokens per second)
llama-server | 11487.39.897.873 I slot print_timing: id 0 | task 2887414 | eval time = 11820.23 ms / 800 tokens ( 14.79 ms per token, 67.60 tokens per second)
llama-server | 11487.39.897.873 I slot print_timing: id 0 | task 2887414 | total time = 12676.89 ms / 1067 tokens
llama-server | 11487.39.897.874 I slot print_timing: id 0 | task 2887414 | graphs reused = 2795704
llama-server | 11487.39.897.877 I slot print_timing: id 0 | task 2887414 | draft acceptance = 0.78037 ( 636 accepted / 815 generated), mean len = 4.90
llama-server | 11487.39.897.973 I slot release: id 0 | task 2887414 | stop processing: n_tokens = 2358, truncated = 0
llama-server | 11487.46.657.363 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.550
llama-server | 11487.46.657.920 I slot launch_slot_: id 0 | task 2887580 | processing task, is_child = 0
llama-server | 11487.50.486.439 I slot print_timing: id 0 | task 2887580 | prompt processing, n_tokens = 3967, progress = 1.00, t = 3.38 s / 1172.35 tokens per second
llama-server | 11487.53.702.090 I slot print_timing: id 0 | task 2887580 | n_gen = 138, tg = 44.75 t/s, tg_3s = 45.08 t/s
llama-server | 11487.56.732.778 I slot print_timing: id 0 | task 2887580 | n_gen = 297, tg = 48.59 t/s, tg_3s = 52.46 t/s
llama-server | 11487.59.793.387 I slot print_timing: id 0 | task 2887580 | n_gen = 467, tg = 50.91 t/s, tg_3s = 55.54 t/s
llama-server | 11488.02.802.443 I slot print_timing: id 0 | task 2887580 | n_gen = 613, tg = 50.32 t/s, tg_3s = 48.52 t/s
llama-server | 11488.05.871.643 I slot print_timing: id 0 | task 2887580 | n_gen = 783, tg = 51.34 t/s, tg_3s = 55.39 t/s
llama-server | 11488.08.879.429 I slot print_timing: id 0 | task 2887580 | n_gen = 1000, tg = 54.77 t/s, tg_3s = 72.15 t/s
llama-server | 11488.11.887.052 I slot print_timing: id 0 | task 2887580 | n_gen = 1165, tg = 54.79 t/s, tg_3s = 54.86 t/s
llama-server | 11488.14.912.967 I slot print_timing: id 0 | task 2887580 | n_gen = 1408, tg = 57.97 t/s, tg_3s = 80.31 t/s
llama-server | 11488.15.503.591 I slot print_timing: id 0 | task 2887580 | prompt eval time = 3982.39 ms / 3971 tokens ( 1.00 ms per token, 997.14 tokens per second)
llama-server | 11488.15.503.595 I slot print_timing: id 0 | task 2887580 | eval time = 24862.73 ms / 1455 tokens ( 17.10 ms per token, 58.48 tokens per second)
llama-server | 11488.15.503.595 I slot print_timing: id 0 | task 2887580 | total time = 28845.12 ms / 5426 tokens
llama-server | 11488.15.503.596 I slot print_timing: id 0 | task 2887580 | graphs reused = 2796035
llama-server | 11488.15.503.599 I slot print_timing: id 0 | task 2887580 | draft acceptance = 0.66095 ( 1117 accepted / 1690 generated), mean len = 4.30
llama-server | 11488.15.503.769 I slot release: id 0 | task 2887580 | stop processing: n_tokens = 6718, truncated = 0
llama-server | 11488.15.634.330 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.835 (> 0.100 thold), f_keep = 0.193
llama-server | 11488.15.634.911 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 976.562 MiB)
llama-server | 11488.16.328.717 I slot launch_slot_: id 0 | task 2887923 | processing task, is_child = 0
llama-server | 11488.19.933.335 I slot print_timing: id 0 | task 2887923 | n_gen = 198, tg = 65.59 t/s, tg_3s = 65.92 t/s
llama-server | 11488.22.951.421 I slot print_timing: id 0 | task 2887923 | n_gen = 446, tg = 73.90 t/s, tg_3s = 82.17 t/s
llama-server | 11488.25.194.739 I slot print_timing: id 0 | task 2887923 | prompt eval time = 600.53 ms / 261 tokens ( 2.30 ms per token, 434.61 tokens per second)
llama-server | 11488.25.194.742 I slot print_timing: id 0 | task 2887923 | eval time = 8264.71 ms / 631 tokens ( 13.12 ms per token, 76.23 tokens per second)
llama-server | 11488.25.194.743 I slot print_timing: id 0 | task 2887923 | total time = 8865.25 ms / 892 tokens
llama-server | 11488.25.194.743 I slot print_timing: id 0 | task 2887923 | graphs reused = 2796147
llama-server | 11488.25.194.746 I slot print_timing: id 0 | task 2887923 | draft acceptance = 0.89565 ( 515 accepted / 575 generated), mean len = 5.48
llama-server | 11488.25.194.847 I slot release: id 0 | task 2887923 | stop processing: n_tokens = 2183, truncated = 0
llama-server | 11488.31.649.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.246 (> 0.100 thold), f_keep = 0.594
llama-server | 11488.31.649.658 I slot launch_slot_: id 0 | task 2888041 | processing task, is_child = 0
llama-server | 11488.35.553.983 I slot print_timing: id 0 | task 2888041 | prompt processing, n_tokens = 3967, progress = 1.00, t = 3.46 s / 1146.82 tokens per second
llama-server | 11488.38.778.987 I slot print_timing: id 0 | task 2888041 | n_gen = 164, tg = 53.20 t/s, tg_3s = 53.52 t/s
llama-server | 11488.41.804.166 I slot print_timing: id 0 | task 2888041 | n_gen = 311, tg = 50.91 t/s, tg_3s = 48.59 t/s
llama-server | 11488.44.866.516 I slot print_timing: id 0 | task 2888041 | n_gen = 503, tg = 54.85 t/s, tg_3s = 62.70 t/s
llama-server | 11488.47.936.690 I slot print_timing: id 0 | task 2888041 | n_gen = 648, tg = 52.94 t/s, tg_3s = 47.23 t/s
llama-server | 11488.50.988.241 I slot print_timing: id 0 | task 2888041 | n_gen = 814, tg = 53.23 t/s, tg_3s = 54.40 t/s
llama-server | 11488.53.999.508 I slot print_timing: id 0 | task 2888041 | n_gen = 1006, tg = 54.96 t/s, tg_3s = 63.76 t/s
llama-server | 11488.57.021.184 I slot print_timing: id 0 | task 2888041 | n_gen = 1198, tg = 56.18 t/s, tg_3s = 63.54 t/s
llama-server | 11489.00.045.435 I slot print_timing: id 0 | task 2888041 | n_gen = 1417, tg = 58.20 t/s, tg_3s = 72.41 t/s
llama-server | 11489.01.294.615 I slot print_timing: id 0 | task 2888041 | prompt eval time = 4064.63 ms / 3971 tokens ( 1.02 ms per token, 976.96 tokens per second)
llama-server | 11489.01.294.619 I slot print_timing: id 0 | task 2888041 | eval time = 25579.76 ms / 1517 tokens ( 16.87 ms per token, 59.27 tokens per second)
llama-server | 11489.01.294.619 I slot print_timing: id 0 | task 2888041 | total time = 29644.40 ms / 5488 tokens
llama-server | 11489.01.294.620 I slot print_timing: id 0 | task 2888041 | graphs reused = 2796490
llama-server | 11489.01.294.632 I slot print_timing: id 0 | task 2888041 | draft acceptance = 0.66686 ( 1167 accepted / 1750 generated), mean len = 4.33
llama-server | 11489.01.294.794 I slot release: id 0 | task 2888041 | stop processing: n_tokens = 6780, truncated = 0
llama-server | 11489.01.407.365 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.836 (> 0.100 thold), f_keep = 0.191
llama-server | 11489.01.408.094 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1132.077 MiB)
llama-server | 11489.02.061.567 I slot launch_slot_: id 0 | task 2888396 | processing task, is_child = 0
llama-server | 11489.05.636.792 I slot print_timing: id 0 | task 2888396 | n_gen = 184, tg = 61.00 t/s, tg_3s = 61.33 t/s
llama-server | 11489.08.652.678 I slot print_timing: id 0 | task 2888396 | n_gen = 373, tg = 61.84 t/s, tg_3s = 62.67 t/s
llama-server | 11489.11.674.724 I slot print_timing: id 0 | task 2888396 | n_gen = 611, tg = 67.49 t/s, tg_3s = 78.75 t/s
llama-server | 11489.12.392.438 I slot print_timing: id 0 | task 2888396 | prompt eval time = 574.80 ms / 259 tokens ( 2.22 ms per token, 450.59 tokens per second)
llama-server | 11489.12.392.442 I slot print_timing: id 0 | task 2888396 | eval time = 9755.54 ms / 666 tokens ( 14.67 ms per token, 68.17 tokens per second)
llama-server | 11489.12.392.443 I slot print_timing: id 0 | task 2888396 | total time = 10330.35 ms / 925 tokens
llama-server | 11489.12.392.443 I slot print_timing: id 0 | task 2888396 | graphs reused = 2796623
llama-server | 11489.12.392.447 I slot print_timing: id 0 | task 2888396 | draft acceptance = 0.77794 ( 529 accepted / 680 generated), mean len = 4.89
llama-server | 11489.12.392.541 I slot release: id 0 | task 2888396 | stop processing: n_tokens = 2216, truncated = 0
llama-server | 11489.21.605.059 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.585
llama-server | 11489.21.605.706 I slot launch_slot_: id 0 | task 2888535 | processing task, is_child = 0
llama-server | 11489.27.618.377 I slot print_timing: id 0 | task 2888535 | n_gen = 162, tg = 53.15 t/s, tg_3s = 53.48 t/s
llama-server | 11489.30.640.109 I slot print_timing: id 0 | task 2888535 | n_gen = 324, tg = 53.38 t/s, tg_3s = 53.61 t/s
llama-server | 11489.33.677.442 I slot print_timing: id 0 | task 2888535 | n_gen = 492, tg = 54.03 t/s, tg_3s = 55.31 t/s
llama-server | 11489.36.727.402 I slot print_timing: id 0 | task 2888535 | n_gen = 714, tg = 58.74 t/s, tg_3s = 72.79 t/s
llama-server | 11489.38.247.230 I slot print_timing: id 0 | task 2888535 | prompt eval time = 2983.06 ms / 2904 tokens ( 1.03 ms per token, 973.50 tokens per second)
llama-server | 11489.38.247.234 I slot print_timing: id 0 | task 2888535 | eval time = 13657.76 ms / 831 tokens ( 16.46 ms per token, 60.77 tokens per second)
llama-server | 11489.38.247.234 I slot print_timing: id 0 | task 2888535 | total time = 16640.82 ms / 3735 tokens
llama-server | 11489.38.247.235 I slot print_timing: id 0 | task 2888535 | graphs reused = 2796808
llama-server | 11489.38.247.238 I slot print_timing: id 0 | task 2888535 | draft acceptance = 0.67831 ( 641 accepted / 945 generated), mean len = 4.39
llama-server | 11489.38.247.381 I slot release: id 0 | task 2888535 | stop processing: n_tokens = 5026, truncated = 0
llama-server | 11489.38.372.094 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.830 (> 0.100 thold), f_keep = 0.258
llama-server | 11489.38.372.750 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1207.206 MiB)
llama-server | 11489.38.991.712 I slot launch_slot_: id 0 | task 2888729 | processing task, is_child = 0
llama-server | 11489.42.618.797 I slot print_timing: id 0 | task 2888729 | n_gen = 131, tg = 42.64 t/s, tg_3s = 42.96 t/s
llama-server | 11489.45.680.759 I slot print_timing: id 0 | task 2888729 | n_gen = 289, tg = 47.13 t/s, tg_3s = 51.60 t/s
llama-server | 11489.48.732.718 I slot print_timing: id 0 | task 2888729 | n_gen = 449, tg = 48.89 t/s, tg_3s = 52.43 t/s
llama-server | 11489.51.737.079 I slot print_timing: id 0 | task 2888729 | n_gen = 586, tg = 48.08 t/s, tg_3s = 45.60 t/s
llama-server | 11489.54.797.809 I slot print_timing: id 0 | task 2888729 | n_gen = 741, tg = 48.59 t/s, tg_3s = 50.64 t/s
llama-server | 11489.57.815.693 I slot print_timing: id 0 | task 2888729 | n_gen = 917, tg = 50.20 t/s, tg_3s = 58.32 t/s
llama-server | 11490.00.836.046 I slot print_timing: id 0 | task 2888729 | n_gen = 1068, tg = 50.17 t/s, tg_3s = 49.99 t/s
llama-server | 11490.03.836.077 I slot print_timing: id 0 | task 2888729 | n_gen = 1204, tg = 49.58 t/s, tg_3s = 45.33 t/s
llama-server | 11490.06.866.216 I slot print_timing: id 0 | task 2888729 | n_gen = 1355, tg = 49.60 t/s, tg_3s = 49.83 t/s
llama-server | 11490.08.374.496 W srv stop: cancel task, id_task = 2888729
llama-server | 11490.08.442.468 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 689261630451
llama-server | 11490.08.497.987 I slot launch_slot_: id 1 | task 2889136 | processing task, is_child = 0
llama-server | 11490.08.497.991 I slot release: id 0 | task 2888729 | stop processing: n_tokens = 2995, truncated = 0
llama-server | 11490.12.142.434 I slot print_timing: id 1 | task 2889136 | n_gen = 136, tg = 43.98 t/s, tg_3s = 44.30 t/s
llama-server | 11490.15.196.701 I slot print_timing: id 1 | task 2889136 | n_gen = 305, tg = 49.64 t/s, tg_3s = 55.33 t/s
llama-server | 11490.18.267.617 I slot print_timing: id 1 | task 2889136 | n_gen = 492, tg = 53.40 t/s, tg_3s = 60.89 t/s
llama-server | 11490.21.284.961 I slot print_timing: id 1 | task 2889136 | n_gen = 713, tg = 58.30 t/s, tg_3s = 73.24 t/s
llama-server | 11490.24.291.254 I slot print_timing: id 1 | task 2889136 | n_gen = 881, tg = 57.83 t/s, tg_3s = 55.88 t/s
llama-server | 11490.27.304.187 I slot print_timing: id 1 | task 2889136 | n_gen = 1112, tg = 60.94 t/s, tg_3s = 76.67 t/s
llama-server | 11490.29.058.969 I slot print_timing: id 1 | task 2889136 | prompt eval time = 574.69 ms / 270 tokens ( 2.13 ms per token, 469.82 tokens per second)
llama-server | 11490.29.058.973 I slot print_timing: id 1 | task 2889136 | eval time = 19986.02 ms / 1251 tokens ( 15.99 ms per token, 62.54 tokens per second)
llama-server | 11490.29.058.973 I slot print_timing: id 1 | task 2889136 | total time = 20560.71 ms / 1521 tokens
llama-server | 11490.29.058.974 I slot print_timing: id 1 | task 2889136 | graphs reused = 2797473
llama-server | 11490.29.058.977 I slot print_timing: id 1 | task 2889136 | draft acceptance = 0.71575 ( 977 accepted / 1365 generated), mean len = 4.58
llama-server | 11490.29.059.066 I slot release: id 1 | task 2889136 | stop processing: n_tokens = 2812, truncated = 0
llama-server | 11490.36.839.824 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.213 (> 0.100 thold), f_keep = 0.433
llama-server | 11490.37.278.549 I slot launch_slot_: id 0 | task 2889413 | processing task, is_child = 0
llama-server | 11490.41.794.472 I slot print_timing: id 0 | task 2889413 | prompt processing, n_tokens = 4096, progress = 0.88, t = 3.52 s / 1162.97 tokens per second
llama-server | 11490.42.005.597 I slot print_timing: id 0 | task 2889413 | prompt processing, n_tokens = 4281, progress = 0.92, t = 4.09 s / 1046.33 tokens per second
llama-server | 11490.42.564.753 I slot print_timing: id 0 | task 2889413 | prompt processing, n_tokens = 4793, progress = 1.00, t = 4.41 s / 1088.01 tokens per second
llama-server | 11490.45.702.616 I slot print_timing: id 0 | task 2889413 | n_gen = 174, tg = 57.65 t/s, tg_3s = 57.98 t/s
llama-server | 11490.48.765.595 I slot print_timing: id 0 | task 2889413 | n_gen = 364, tg = 59.86 t/s, tg_3s = 62.03 t/s
llama-server | 11490.51.818.761 I slot print_timing: id 0 | task 2889413 | n_gen = 553, tg = 60.55 t/s, tg_3s = 61.90 t/s
llama-server | 11490.54.819.049 I slot print_timing: id 0 | task 2889413 | n_gen = 738, tg = 60.82 t/s, tg_3s = 61.66 t/s
llama-server | 11490.57.821.682 I slot print_timing: id 0 | task 2889413 | n_gen = 892, tg = 58.93 t/s, tg_3s = 51.29 t/s
llama-server | 11491.00.881.327 I slot print_timing: id 0 | task 2889413 | n_gen = 1026, tg = 56.38 t/s, tg_3s = 43.80 t/s
llama-server | 11491.03.897.296 I slot print_timing: id 0 | task 2889413 | n_gen = 1195, tg = 56.33 t/s, tg_3s = 56.04 t/s
llama-server | 11491.06.842.749 W srv stop: cancel task, id_task = 2889413
llama-server | 11491.06.844.846 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 689444899119
llama-server | 11491.06.887.764 I slot launch_slot_: id 1 | task 2889749 | processing task, is_child = 0
llama-server | 11491.06.887.769 I slot release: id 0 | task 2889413 | stop processing: n_tokens = 7450, truncated = 0
llama-server | 11491.10.996.500 I slot print_timing: id 1 | task 2889749 | prompt processing, n_tokens = 4096, progress = 0.88, t = 3.45 s / 1187.13 tokens per second
llama-server | 11491.11.230.967 I slot print_timing: id 1 | task 2889749 | prompt processing, n_tokens = 4281, progress = 0.92, t = 4.12 s / 1039.41 tokens per second
llama-server | 11491.11.813.300 I slot print_timing: id 1 | task 2889749 | prompt processing, n_tokens = 4793, progress = 1.00, t = 4.44 s / 1078.96 tokens per second
llama-server | 11491.15.073.614 I slot print_timing: id 1 | task 2889749 | n_gen = 162, tg = 52.43 t/s, tg_3s = 52.75 t/s
llama-server | 11491.18.137.454 I slot print_timing: id 1 | task 2889749 | n_gen = 344, tg = 55.91 t/s, tg_3s = 59.40 t/s
llama-server | 11491.21.185.029 I slot print_timing: id 1 | task 2889749 | n_gen = 488, tg = 53.04 t/s, tg_3s = 47.25 t/s
llama-server | 11491.24.254.931 I slot print_timing: id 1 | task 2889749 | n_gen = 657, tg = 53.54 t/s, tg_3s = 55.05 t/s
llama-server | 11491.27.330.299 I slot print_timing: id 1 | task 2889749 | n_gen = 824, tg = 53.69 t/s, tg_3s = 54.30 t/s
llama-server | 11491.30.398.776 I slot print_timing: id 1 | task 2889749 | n_gen = 1002, tg = 54.41 t/s, tg_3s = 58.01 t/s
llama-server | 11491.33.413.052 I slot print_timing: id 1 | task 2889749 | n_gen = 1186, tg = 55.35 t/s, tg_3s = 61.04 t/s
llama-server | 11491.36.428.738 I slot print_timing: id 1 | task 2889749 | n_gen = 1383, tg = 56.58 t/s, tg_3s = 65.33 t/s
llama-server | 11491.39.430.910 I slot print_timing: id 1 | task 2889749 | n_gen = 1562, tg = 56.91 t/s, tg_3s = 59.62 t/s
llama-server | 11491.42.456.485 I slot print_timing: id 1 | task 2889749 | n_gen = 1789, tg = 58.71 t/s, tg_3s = 75.03 t/s
llama-server | 11491.43.790.162 I slot print_timing: id 1 | task 2889749 | prompt eval time = 5114.54 ms / 4797 tokens ( 1.07 ms per token, 937.91 tokens per second)
llama-server | 11491.43.790.166 I slot print_timing: id 1 | task 2889749 | eval time = 31787.59 ms / 1890 tokens ( 16.83 ms per token, 59.43 tokens per second)
llama-server | 11491.43.790.166 I slot print_timing: id 1 | task 2889749 | total time = 36902.13 ms / 6687 tokens
llama-server | 11491.43.790.167 I slot print_timing: id 1 | task 2889749 | graphs reused = 2798200
llama-server | 11491.43.790.170 I slot print_timing: id 1 | task 2889749 | draft acceptance = 0.71525 ( 1477 accepted / 2065 generated), mean len = 4.58
llama-server | 11491.43.790.369 I slot release: id 1 | task 2889749 | stop processing: n_tokens = 7979, truncated = 0
llama-server | 11491.43.901.734 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.174
llama-server | 11491.43.902.629 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1127.289 MiB)
llama-server | 11491.44.655.518 I slot launch_slot_: id 0 | task 2890169 | processing task, is_child = 0
llama-server | 11491.48.901.415 I slot print_timing: id 0 | task 2890169 | n_gen = 191, tg = 63.30 t/s, tg_3s = 63.63 t/s
llama-server | 11491.51.912.632 I slot print_timing: id 0 | task 2890169 | n_gen = 412, tg = 68.36 t/s, tg_3s = 73.39 t/s
llama-server | 11491.54.512.339 I slot print_timing: id 0 | task 2890169 | prompt eval time = 594.77 ms / 264 tokens ( 2.25 ms per token, 443.87 tokens per second)
llama-server | 11491.54.512.344 I slot print_timing: id 0 | task 2890169 | eval time = 8612.40 ms / 623 tokens ( 13.85 ms per token, 72.22 tokens per second)
llama-server | 11491.54.512.344 I slot print_timing: id 0 | task 2890169 | total time = 9207.17 ms / 887 tokens
llama-server | 11491.54.512.345 I slot print_timing: id 0 | task 2890169 | graphs reused = 2798317
llama-server | 11491.54.512.348 I slot print_timing: id 0 | task 2890169 | draft acceptance = 0.83667 ( 502 accepted / 600 generated), mean len = 5.18
llama-server | 11491.54.512.437 I slot release: id 0 | task 2890169 | stop processing: n_tokens = 2178, truncated = 0
llama-server | 11492.01.948.296 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.596
llama-server | 11492.01.948.910 I slot launch_slot_: id 0 | task 2890292 | processing task, is_child = 0
llama-server | 11492.07.912.815 I slot print_timing: id 0 | task 2890292 | n_gen = 154, tg = 50.60 t/s, tg_3s = 50.93 t/s
llama-server | 11492.10.936.396 I slot print_timing: id 0 | task 2890292 | n_gen = 306, tg = 50.44 t/s, tg_3s = 50.27 t/s
llama-server | 11492.13.968.700 I slot print_timing: id 0 | task 2890292 | n_gen = 453, tg = 49.78 t/s, tg_3s = 48.48 t/s
llama-server | 11492.17.004.772 I slot print_timing: id 0 | task 2890292 | n_gen = 641, tg = 52.82 t/s, tg_3s = 61.92 t/s
llama-server | 11492.20.067.917 I slot print_timing: id 0 | task 2890292 | n_gen = 879, tg = 57.84 t/s, tg_3s = 77.70 t/s
llama-server | 11492.20.502.938 I slot print_timing: id 0 | task 2890292 | prompt eval time = 2939.56 ms / 2906 tokens ( 1.01 ms per token, 988.58 tokens per second)
llama-server | 11492.20.502.941 I slot print_timing: id 0 | task 2890292 | eval time = 15613.89 ms / 913 tokens ( 17.12 ms per token, 58.41 tokens per second)
llama-server | 11492.20.502.942 I slot print_timing: id 0 | task 2890292 | total time = 18553.45 ms / 3819 tokens
llama-server | 11492.20.502.942 I slot print_timing: id 0 | task 2890292 | graphs reused = 2798529
llama-server | 11492.20.502.945 I slot print_timing: id 0 | task 2890292 | draft acceptance = 0.64444 ( 696 accepted / 1080 generated), mean len = 4.22
llama-server | 11492.20.503.100 I slot release: id 0 | task 2890292 | stop processing: n_tokens = 5110, truncated = 0
llama-server | 11492.20.633.815 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.823 (> 0.100 thold), f_keep = 0.254
llama-server | 11492.20.634.481 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 965.547 MiB)
llama-server | 11492.21.375.134 I slot launch_slot_: id 0 | task 2890513 | processing task, is_child = 0
llama-server | 11492.24.980.444 I slot print_timing: id 0 | task 2890513 | n_gen = 190, tg = 62.91 t/s, tg_3s = 63.24 t/s
llama-server | 11492.27.980.983 I slot print_timing: id 0 | task 2890513 | n_gen = 343, tg = 56.96 t/s, tg_3s = 50.99 t/s
llama-server | 11492.30.999.974 I slot print_timing: id 0 | task 2890513 | n_gen = 552, tg = 61.06 t/s, tg_3s = 69.23 t/s
llama-server | 11492.34.023.335 I slot print_timing: id 0 | task 2890513 | n_gen = 749, tg = 62.09 t/s, tg_3s = 65.16 t/s
llama-server | 11492.37.054.151 I slot print_timing: id 0 | task 2890513 | n_gen = 994, tg = 65.86 t/s, tg_3s = 80.84 t/s
llama-server | 11492.38.707.390 I slot print_timing: id 0 | task 2890513 | prompt eval time = 600.39 ms / 284 tokens ( 2.11 ms per token, 473.03 tokens per second)
llama-server | 11492.38.707.399 I slot print_timing: id 0 | task 2890513 | eval time = 16731.09 ms / 1127 tokens ( 14.86 ms per token, 67.30 tokens per second)
llama-server | 11492.38.707.400 I slot print_timing: id 0 | task 2890513 | total time = 17331.48 ms / 1411 tokens
llama-server | 11492.38.707.401 I slot print_timing: id 0 | task 2890513 | graphs reused = 2798757
llama-server | 11492.38.707.406 I slot print_timing: id 0 | task 2890513 | draft acceptance = 0.76652 ( 893 accepted / 1165 generated), mean len = 4.83
llama-server | 11492.38.707.494 I slot release: id 0 | task 2890513 | stop processing: n_tokens = 2702, truncated = 0
llama-server | 11492.47.015.039 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.309 (> 0.100 thold), f_keep = 0.480
llama-server | 11492.47.015.575 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1135.236 MiB)
llama-server | 11492.47.627.712 I slot launch_slot_: id 0 | task 2890749 | processing task, is_child = 0
llama-server | 11492.53.732.111 I slot print_timing: id 0 | task 2890749 | n_gen = 160, tg = 52.30 t/s, tg_3s = 52.62 t/s
llama-server | 11492.56.734.461 I slot print_timing: id 0 | task 2890749 | n_gen = 299, tg = 49.32 t/s, tg_3s = 46.30 t/s
llama-server | 11492.59.762.058 I slot print_timing: id 0 | task 2890749 | n_gen = 451, tg = 49.61 t/s, tg_3s = 50.20 t/s
llama-server | 11493.02.784.391 I slot print_timing: id 0 | task 2890749 | n_gen = 601, tg = 49.62 t/s, tg_3s = 49.63 t/s
llama-server | 11493.05.833.367 I slot print_timing: id 0 | task 2890749 | n_gen = 787, tg = 51.91 t/s, tg_3s = 61.00 t/s
llama-server | 11493.08.895.182 I slot print_timing: id 0 | task 2890749 | n_gen = 1019, tg = 55.92 t/s, tg_3s = 75.77 t/s
llama-server | 11493.09.330.584 I slot print_timing: id 0 | task 2890749 | prompt eval time = 3063.54 ms / 2908 tokens ( 1.05 ms per token, 949.23 tokens per second)
llama-server | 11493.09.330.587 I slot print_timing: id 0 | task 2890749 | eval time = 18638.81 ms / 1051 tokens ( 17.75 ms per token, 56.33 tokens per second)
llama-server | 11493.09.330.588 I slot print_timing: id 0 | task 2890749 | total time = 21702.35 ms / 3959 tokens
llama-server | 11493.09.330.589 I slot print_timing: id 0 | task 2890749 | graphs reused = 2799010
llama-server | 11493.09.330.592 I slot print_timing: id 0 | task 2890749 | draft acceptance = 0.61395 ( 792 accepted / 1290 generated), mean len = 4.07
llama-server | 11493.09.330.749 I slot release: id 0 | task 2890749 | stop processing: n_tokens = 5250, truncated = 0
llama-server | 11493.09.441.184 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.821 (> 0.100 thold), f_keep = 0.247
llama-server | 11493.09.441.879 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 996.735 MiB)
llama-server | 11493.10.145.393 I slot launch_slot_: id 0 | task 2891012 | processing task, is_child = 0
llama-server | 11493.14.498.759 I slot print_timing: id 0 | task 2891012 | n_gen = 200, tg = 64.99 t/s, tg_3s = 65.31 t/s
llama-server | 11493.17.499.464 I slot print_timing: id 0 | task 2891012 | n_gen = 372, tg = 61.19 t/s, tg_3s = 57.32 t/s
llama-server | 11493.20.505.747 I slot print_timing: id 0 | task 2891012 | n_gen = 562, tg = 61.86 t/s, tg_3s = 63.20 t/s
llama-server | 11493.23.530.264 I slot print_timing: id 0 | task 2891012 | n_gen = 803, tg = 66.32 t/s, tg_3s = 79.68 t/s
llama-server | 11493.25.915.099 I slot print_timing: id 0 | task 2891012 | prompt eval time = 1290.95 ms / 288 tokens ( 4.48 ms per token, 223.09 tokens per second)
llama-server | 11493.25.915.102 I slot print_timing: id 0 | task 2891012 | eval time = 14478.24 ms / 997 tokens ( 14.54 ms per token, 68.79 tokens per second)
llama-server | 11493.25.915.103 I slot print_timing: id 0 | task 2891012 | total time = 15769.19 ms / 1285 tokens
llama-server | 11493.25.915.103 I slot print_timing: id 0 | task 2891012 | graphs reused = 2799207
llama-server | 11493.25.915.106 I slot print_timing: id 0 | task 2891012 | draft acceptance = 0.78614 ( 794 accepted / 1010 generated), mean len = 4.93
llama-server | 11493.25.915.194 I slot release: id 0 | task 2891012 | stop processing: n_tokens = 2576, truncated = 0
llama-server | 11493.32.227.559 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.357 (> 0.100 thold), f_keep = 0.503
llama-server | 11493.32.228.225 I slot launch_slot_: id 0 | task 2891217 | processing task, is_child = 0
llama-server | 11493.37.749.163 I slot print_timing: id 0 | task 2891217 | n_gen = 172, tg = 56.63 t/s, tg_3s = 56.96 t/s
llama-server | 11493.40.766.246 I slot print_timing: id 0 | task 2891217 | n_gen = 328, tg = 54.17 t/s, tg_3s = 51.71 t/s
llama-server | 11493.43.787.465 I slot print_timing: id 0 | task 2891217 | n_gen = 479, tg = 52.77 t/s, tg_3s = 49.98 t/s
llama-server | 11493.46.803.206 I slot print_timing: id 0 | task 2891217 | n_gen = 642, tg = 53.09 t/s, tg_3s = 54.05 t/s
llama-server | 11493.49.849.543 I slot print_timing: id 0 | task 2891217 | n_gen = 818, tg = 54.04 t/s, tg_3s = 57.77 t/s
llama-server | 11493.52.904.362 I slot print_timing: id 0 | task 2891217 | n_gen = 1058, tg = 58.16 t/s, tg_3s = 78.56 t/s
llama-server | 11493.54.503.755 I slot print_timing: id 0 | task 2891217 | prompt eval time = 2500.86 ms / 2336 tokens ( 1.07 ms per token, 934.08 tokens per second)
llama-server | 11493.54.503.758 I slot print_timing: id 0 | task 2891217 | eval time = 19774.02 ms / 1187 tokens ( 16.67 ms per token, 59.98 tokens per second)
llama-server | 11493.54.503.759 I slot print_timing: id 0 | task 2891217 | total time = 22274.88 ms / 3523 tokens
llama-server | 11493.54.503.759 I slot print_timing: id 0 | task 2891217 | graphs reused = 2799476
llama-server | 11493.54.503.770 I slot print_timing: id 0 | task 2891217 | draft acceptance = 0.66569 ( 912 accepted / 1370 generated), mean len = 4.33
llama-server | 11493.54.503.939 I slot release: id 0 | task 2891217 | stop processing: n_tokens = 4814, truncated = 0
llama-server | 11493.54.613.521 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.849 (> 0.100 thold), f_keep = 0.269
llama-server | 11493.55.128.405 I slot launch_slot_: id 0 | task 2891495 | processing task, is_child = 0
llama-server | 11493.58.708.777 I slot print_timing: id 0 | task 2891495 | n_gen = 183, tg = 60.62 t/s, tg_3s = 60.95 t/s
llama-server | 11494.01.718.272 I slot print_timing: id 0 | task 2891495 | n_gen = 402, tg = 66.70 t/s, tg_3s = 72.77 t/s
llama-server | 11494.04.735.074 I slot print_timing: id 0 | task 2891495 | n_gen = 617, tg = 68.23 t/s, tg_3s = 71.27 t/s
llama-server | 11494.07.617.327 I slot print_timing: id 0 | task 2891495 | prompt eval time = 577.80 ms / 236 tokens ( 2.45 ms per token, 408.45 tokens per second)
llama-server | 11494.07.617.331 I slot print_timing: id 0 | task 2891495 | eval time = 11910.61 ms / 853 tokens ( 13.98 ms per token, 71.53 tokens per second)
llama-server | 11494.07.617.332 I slot print_timing: id 0 | task 2891495 | total time = 12488.41 ms / 1089 tokens
llama-server | 11494.07.617.332 I slot print_timing: id 0 | task 2891495 | graphs reused = 2799637
llama-server | 11494.07.617.335 I slot print_timing: id 0 | task 2891495 | draft acceptance = 0.82651 ( 686 accepted / 830 generated), mean len = 5.13
llama-server | 11494.07.617.422 I slot release: id 0 | task 2891495 | stop processing: n_tokens = 2380, truncated = 0
llama-server | 11494.12.405.080 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.259 (> 0.100 thold), f_keep = 0.545
llama-server | 11494.12.405.729 I slot launch_slot_: id 0 | task 2891664 | processing task, is_child = 0
llama-server | 11494.16.086.436 I slot print_timing: id 0 | task 2891664 | prompt processing, n_tokens = 3718, progress = 1.00, t = 3.23 s / 1149.41 tokens per second
llama-server | 11494.19.316.641 I slot print_timing: id 0 | task 2891664 | n_gen = 178, tg = 57.61 t/s, tg_3s = 57.93 t/s
llama-server | 11494.22.354.496 I slot print_timing: id 0 | task 2891664 | n_gen = 341, tg = 55.64 t/s, tg_3s = 53.66 t/s
llama-server | 11494.25.416.404 I slot print_timing: id 0 | task 2891664 | n_gen = 512, tg = 55.71 t/s, tg_3s = 55.85 t/s
llama-server | 11494.28.416.533 I slot print_timing: id 0 | task 2891664 | n_gen = 692, tg = 56.77 t/s, tg_3s = 60.00 t/s
llama-server | 11494.31.473.720 I slot print_timing: id 0 | task 2891664 | n_gen = 855, tg = 56.08 t/s, tg_3s = 53.32 t/s
llama-server | 11494.34.480.045 I slot print_timing: id 0 | task 2891664 | n_gen = 1027, tg = 56.26 t/s, tg_3s = 57.21 t/s
llama-server | 11494.37.485.940 I slot print_timing: id 0 | task 2891664 | n_gen = 1187, tg = 55.83 t/s, tg_3s = 53.23 t/s
llama-server | 11494.40.489.484 I slot print_timing: id 0 | task 2891664 | n_gen = 1366, tg = 56.30 t/s, tg_3s = 59.60 t/s
llama-server | 11494.42.407.796 W srv stop: cancel task, id_task = 2891664
llama-server | 11494.42.473.713 I slot get_availabl: id 1 | task -1 | selected slot by LRU, t_last = 689519630422
llama-server | 11494.42.523.557 I slot launch_slot_: id 1 | task 2892028 | processing task, is_child = 0
llama-server | 11494.42.523.562 I slot release: id 0 | task 2891664 | stop processing: n_tokens = 6469, truncated = 0
llama-server | 11494.46.414.508 I slot print_timing: id 1 | task 2892028 | prompt processing, n_tokens = 3206, progress = 0.90, t = 3.65 s / 878.56 tokens per second
llama-server | 11494.47.015.689 I slot print_timing: id 1 | task 2892028 | prompt processing, n_tokens = 3718, progress = 1.00, t = 4.02 s / 925.28 tokens per second
llama-server | 11494.50.195.164 I slot print_timing: id 1 | task 2892028 | n_gen = 163, tg = 53.33 t/s, tg_3s = 53.65 t/s
llama-server | 11494.53.221.686 I slot print_timing: id 1 | task 2892028 | n_gen = 328, tg = 53.92 t/s, tg_3s = 54.52 t/s
llama-server | 11494.56.237.349 I slot print_timing: id 1 | task 2892028 | n_gen = 488, tg = 53.63 t/s, tg_3s = 53.06 t/s
llama-server | 11494.59.274.767 I slot print_timing: id 1 | task 2892028 | n_gen = 643, tg = 52.98 t/s, tg_3s = 51.03 t/s
llama-server | 11495.02.324.290 I slot print_timing: id 1 | task 2892028 | n_gen = 833, tg = 54.86 t/s, tg_3s = 62.30 t/s
llama-server | 11495.05.353.395 I slot print_timing: id 1 | task 2892028 | n_gen = 987, tg = 54.19 t/s, tg_3s = 50.84 t/s
llama-server | 11495.08.404.840 I slot print_timing: id 1 | task 2892028 | n_gen = 1156, tg = 54.36 t/s, tg_3s = 55.38 t/s
llama-server | 11495.11.446.128 I slot print_timing: id 1 | task 2892028 | n_gen = 1318, tg = 54.22 t/s, tg_3s = 53.27 t/s
llama-server | 11495.14.502.210 I slot print_timing: id 1 | task 2892028 | n_gen = 1460, tg = 53.36 t/s, tg_3s = 46.46 t/s
llama-server | 11495.17.561.619 I slot print_timing: id 1 | task 2892028 | n_gen = 1595, tg = 52.43 t/s, tg_3s = 44.13 t/s
llama-server | 11495.20.602.012 I slot print_timing: id 1 | task 2892028 | n_gen = 1719, tg = 51.37 t/s, tg_3s = 40.78 t/s
llama-server | 11495.23.668.282 I slot print_timing: id 1 | task 2892028 | n_gen = 1866, tg = 51.08 t/s, tg_3s = 47.94 t/s
llama-server | 11495.26.721.330 I slot print_timing: id 1 | task 2892028 | n_gen = 2009, tg = 50.75 t/s, tg_3s = 46.84 t/s
llama-server | 11495.29.794.523 I slot print_timing: id 1 | task 2892028 | n_gen = 2169, tg = 50.85 t/s, tg_3s = 52.06 t/s
llama-server | 11495.32.812.673 I slot print_timing: id 1 | task 2892028 | n_gen = 2379, tg = 52.09 t/s, tg_3s = 69.58 t/s
llama-server | 11495.35.876.559 I slot print_timing: id 1 | task 2892028 | n_gen = 2547, tg = 52.26 t/s, tg_3s = 54.83 t/s
llama-server | 11495.38.879.448 I slot print_timing: id 1 | task 2892028 | n_gen = 2676, tg = 51.72 t/s, tg_3s = 42.96 t/s
llama-server | 11495.41.894.429 I slot print_timing: id 1 | task 2892028 | n_gen = 2871, tg = 52.43 t/s, tg_3s = 64.68 t/s
llama-server | 11495.44.969.386 I slot print_timing: id 1 | task 2892028 | n_gen = 3018, tg = 52.19 t/s, tg_3s = 47.81 t/s
llama-server | 11495.47.990.543 I slot print_timing: id 1 | task 2892028 | n_gen = 3247, tg = 53.36 t/s, tg_3s = 75.80 t/s
llama-server | 11495.48.991.967 I slot print_timing: id 1 | task 2892028 | prompt eval time = 4633.53 ms / 3722 tokens ( 1.24 ms per token, 803.28 tokens per second)
llama-server | 11495.48.991.970 I slot print_timing: id 1 | task 2892028 | eval time = 61834.60 ms / 3320 tokens ( 18.63 ms per token, 53.68 tokens per second)
llama-server | 11495.48.991.971 I slot print_timing: id 1 | task 2892028 | total time = 66468.13 ms / 7042 tokens
llama-server | 11495.48.991.972 I slot print_timing: id 1 | task 2892028 | graphs reused = 2800784
llama-server | 11495.48.991.974 I slot print_timing: id 1 | task 2892028 | draft acceptance = 0.62052 ( 2510 accepted / 4045 generated), mean len = 4.10
llama-server | 11495.48.992.139 I slot release: id 1 | task 2892028 | stop processing: n_tokens = 8333, truncated = 0
llama-server | 11495.49.144.297 I slot get_availabl: id 0 | task -1 | selected slot by LCP similarity, f_sim_best = 0.834 (> 0.100 thold), f_keep = 0.200
llama-server | 11495.49.703.555 I slot launch_slot_: id 0 | task 2892843 | processing task, is_child = 0
llama-server | 11495.49.704.254 W srv alloc: - making room for prompt cache entry, removing oldest entry (size = 1137.649 MiB)
llama-server | 11495.54.617.673 I slot print_timing: id 0 | task 2892843 | n_gen = 201, tg = 65.89 t/s, tg_3s = 66.21 t/s
llama-server | 11495.57.627.602 I slot print_timing: id 0 | task 2892843 | n_gen = 415, tg = 68.48 t/s, tg_3s = 71.10 t/s
llama-server | 11496.00.647.164 I slot print_timing: id 0 | task 2892843 | n_gen = 638, tg = 70.27 t/s, tg_3s = 73.85 t/s
llama-server | 11496.02.529.701 I slot print_timing: id 0 | task 2892843 | prompt eval time = 1023.34 ms / 264 tokens ( 3.88 ms per token, 257.98 tokens per second)
llama-server | 11496.02.529.704 I slot print_timing: id 0 | task 2892843 | eval time = 10947.48 ms / 788 tokens ( 13.91 ms per token, 71.89 tokens per second)
llama-server | 11496.02.529.705 I slot print_timing: id 0 | task 2892843 | total time = 11970.81 ms / 1052 tokens
llama-server | 11496.02.529.706 I slot print_timing: id 0 | task 2892843 | graphs reused = 2800931
llama-server | 11496.02.529.708 I slot print_timing: id 0 | task 2892843 | draft acceptance = 0.84238 ( 636 accepted / 755 generated), mean len = 5.21
llama-server | 11496.02.529.798 I slot release: id 0 | task 2892843 | stop processing: n_tokens = 2343, truncated = 0
Reference in new issue View Git Blame Copy Permalink