compose-vLLM.yaml aktualisiert

2026-07-10 18:35:06 +00:00 · 2026-07-10 18:35:06 +00:00 · 038f30bd6c
parent 21984763cf
commit 038f30bd6c
1 changed files with 2 additions and 2 deletions
--- a/compose-vLLM.yaml
+++ b/compose-vLLM.yaml
@ -29,7 +29,7 @@ services:
      --model Qwen/Qwen2.5-7B-Instruct-AWQ
      --host 0.0.0.0
      --port 8000
-      --gpu-memory-utilization 0.75
-      --max-model-len 16384
+      --gpu-memory-utilization 0.85
+      --max-model-len 65536
      --enable-auto-tool-choice
      --tool-call-parser hermes