fix oom

2026-04-21 03:03:59 +00:00 · 2026-04-21 03:03:59 +00:00 · bd09ea4958
commit bd09ea4958
parent 2207a8a5c7
1 changed files with 4 additions and 1 deletions
--- a/apps/base/customer1/openclaw/vllm-l4.yaml
+++ b/apps/base/customer1/openclaw/vllm-l4.yaml
@ -38,7 +38,10 @@ spec:
            - --port=8000
            - --tensor-parallel-size=1
            - --gpu-memory-utilization=0.95
-            - --max-model-len=32768
+            - --max-model-len=16384
+            - --max-num-batched-tokens=2048
+            - --max-num-seqs=128
+            - --enable-chunked-prefill
            - --enable-auto-tool-choice 
            - --trust-remote-code
            - --dtype=auto