Arthur Erlich haylan
0 Followers · 0 Following
Repositories
12
 Projects Packages Public Activity Starred Repositories
2
haylan deleted branch fix-gpu-pin-and-render-group from haylan/LLM-Server 2026-09-06 19:35:32 +00:00
haylan pushed to main at haylan/LLM-Server 2026-09-06 19:35:32 +00:00
386a41200f Merge pull request 'Fix GPU pinned at 100% with two containers, flaky render group' (#47) from fix-gpu-pin-and-render-group into main
75033dacd7 fix: GPU pinned at 100% with two llama.cpp containers, flaky render group
Compare 2 commits »
haylan merged pull request haylan/LLM-Server#47 2026-09-06 19:35:32 +00:00
Fix GPU pinned at 100% with two containers, flaky render group
haylan created pull request haylan/LLM-Server#47 2026-09-06 19:33:54 +00:00
Fix GPU pinned at 100% with two containers, flaky render group
haylan pushed to fix-gpu-pin-and-render-group at haylan/LLM-Server 2026-09-06 19:33:43 +00:00
75033dacd7 fix: GPU pinned at 100% with two llama.cpp containers, flaky render group
haylan created branch fix-gpu-pin-and-render-group in haylan/LLM-Server 2026-09-06 19:33:43 +00:00
haylan commented on issue haylan/LLM-Server#5 2026-09-06 19:17:21 +00:00
Verify the stack on the real Radeon R9700 box (GPU passthrough + Lazytainer idle-stop)

Confirmed on real hardware. rocm-smi after normal use (llama-server + llama-server-fast both up):

VRAM% 98%   GPU% 100%   SCLK 3402Mhz   Power 101.0W   Temp 81.0°C
WARNING: AMD GPU device(s)…
haylan closed issue haylan/LLM-Server#43 2026-09-06 19:01:03 +00:00
scripts/switch-model.sh: swap GPU residency between Qwen and ComfyUI
haylan deleted branch comfyui-model-and-switch-script from haylan/LLM-Server 2026-09-06 19:01:03 +00:00
haylan pushed to main at haylan/LLM-Server 2026-09-06 19:01:03 +00:00
1ee2e76033 Merge pull request 'Downloader for Qwen-Image weights, switch-model.sh' (#46) from comfyui-model-and-switch-script into main
4b47a1769d feat: downloader for Qwen-Image weights, switch-model.sh script
Compare 2 commits »
haylan closed issue haylan/LLM-Server#42 2026-09-06 19:01:03 +00:00
Extend downloader for the diffusion model weights
haylan merged pull request haylan/LLM-Server#46 2026-09-06 19:01:02 +00:00
Downloader for Qwen-Image weights, switch-model.sh
haylan created pull request haylan/LLM-Server#46 2026-09-06 18:57:49 +00:00
Downloader for Qwen-Image weights, switch-model.sh
haylan pushed to comfyui-model-and-switch-script at haylan/LLM-Server 2026-09-06 18:57:40 +00:00
4b47a1769d feat: downloader for Qwen-Image weights, switch-model.sh script
haylan created branch comfyui-model-and-switch-script in haylan/LLM-Server 2026-09-06 18:57:40 +00:00
haylan deleted branch add-fast-model from haylan/LLM-Server 2026-09-06 18:39:33 +00:00
haylan pushed to main at haylan/LLM-Server 2026-09-06 18:39:33 +00:00
1932981f09 Merge pull request 'Add llama-server-fast: small non-thinking classifier/fast model' (#45) from add-fast-model into main
d984c10835 feat: add llama-server-fast, a small non-thinking classifier model
Compare 2 commits »
haylan closed issue haylan/LLM-Server#44 2026-09-06 18:39:31 +00:00
Add llama-server-fast: small non-thinking classifier/fast model for qwen-code Auto Mode
haylan merged pull request haylan/LLM-Server#45 2026-09-06 18:39:31 +00:00
Add llama-server-fast: small non-thinking classifier/fast model
haylan created pull request haylan/LLM-Server#45 2026-09-06 18:27:27 +00:00
Add llama-server-fast: small non-thinking classifier/fast model