compose-vLLM.yaml aktualisiert

2026-07-10 18:25:28 +00:00 · 2026-07-10 18:25:28 +00:00 · 21984763cf
parent 6fee84f4a0
commit 21984763cf
1 changed files with 2 additions and 2 deletions
--- a/compose-vLLM.yaml
+++ b/compose-vLLM.yaml
@ -26,10 +26,10 @@ services:
              capabilities: [gpu]

    command: >
-      --model Qwen/Qwen2.5-14B-Instruct-AWQ
+      --model Qwen/Qwen2.5-7B-Instruct-AWQ
      --host 0.0.0.0
      --port 8000
-      --gpu-memory-utilization 0.9
+      --gpu-memory-utilization 0.75
      --max-model-len 16384
      --enable-auto-tool-choice
      --tool-call-parser hermes