diff --git a/apps/base/customer1/openclaw/vllm-l4.yaml b/apps/base/customer1/openclaw/vllm-l4.yaml index 0d2a545..6c0a00c 100644 --- a/apps/base/customer1/openclaw/vllm-l4.yaml +++ b/apps/base/customer1/openclaw/vllm-l4.yaml @@ -34,8 +34,8 @@ spec: - --host=0.0.0.0 - --port=8000 - --tensor-parallel-size=1 - - --gpu-memory-utilization=0.90 - - --max-model-len=16384 + - --gpu-memory-utilization=0.95 + - --max-model-len=32768 - --enable-auto-tool-choice - --trust-remote-code - --dtype=auto