Felladrin commited on
Commit
547ea18
·
verified ·
1 Parent(s): 482fec8

Set `--cache-ram` argument

Browse files
Files changed (1) hide show
  1. Dockerfile +1 -1
Dockerfile CHANGED
@@ -12,4 +12,4 @@ ADD --chown=user https://huggingface.co/Intel/Qwen3-Coder-30B-A3B-Instruct-gguf-
12
 
13
  EXPOSE 7860
14
 
15
- CMD ["--port", "7860", "--no-mmap", "--flash-attn", "on", "--fit", "on", "--ctx-size", "8192", "--samplers", "min_p", "--min-p", "0.005", "--backend-sampling", "--webui-mcp-proxy", "-m", "/app/model.gguf", "--chat-template-kwargs", "{ \"enable_thinking\": false }", "--no-mmproj"]
 
12
 
13
  EXPOSE 7860
14
 
15
+ CMD ["--port", "7860", "--no-mmap", "--flash-attn", "on", "--fit", "on", "--ctx-size", "8192", "--cache-ram", " 768", "--samplers", "min_p", "--min-p", "0.005", "--backend-sampling", "--webui-mcp-proxy", "-m", "/app/model.gguf", "--chat-template-kwargs", "{ \"enable_thinking\": false }", "--no-mmproj"]