haylan/LLM-Server
1
0 Fork 0
Code Issues 4 Pull Requests Actions Packages Projects Releases Wiki Activity

chore(env): reduced LLAMA_CACHE_RAM value in .env.example

Browse Source
This commit is contained in:
haylan committed 2026-10-31 18:49:30 +01:00
1 parent 8927e440aa
commit c25e7e835f
1 file changed
+1 -1
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+1 -1
View File
@@ -5,7 +5,7 @@ LLAMA_MODEL_FILE=Qwen3.8-27B-UD-Q4_K_XL.gguf
LLAMA_GPU_LAYERS=999
LLAMA_CTX_SIZE=262144
LLAMA_PARALLEL=2
LLAMA_CACHE_RAM=24576
LLAMA_CACHE_RAM=8192
LLAMA_KV_CACHE_TYPE=q8_0
# Blank = speculative decoding off; see docs/architecture.md#llama-server