dial in vllm

2026-04-20 02:04:04 +00:00 · 2026-04-20 02:04:04 +00:00 · 46f576dcda
commit 46f576dcda
parent 7c72d229ac
1 changed files with 0 additions and 1 deletions
--- a/apps/base/customer1/openclaw/vllm-gemma.yaml
+++ b/apps/base/customer1/openclaw/vllm-gemma.yaml
@ -40,7 +40,6 @@ spec:
            - --max-model-len=24576                  # Start conservative (you can raise to 32768 later)
            - --max-num-batched-tokens=8192
            - --max-num-seqs=8                        # Lower for single-user / low-concurrency
-            - --enforce-eager                        # Disables CUDA graphs → big memory saver at startup
            - --disable-custom-all-reduce
            - --enable-auto-tool-choice 
            - --trust-remote-code