diff --git a/apps/base/customer1/openclaw/vllm-gemma.yaml b/apps/base/customer1/openclaw/vllm-gemma.yaml index 67c0409..11c3a05 100644 --- a/apps/base/customer1/openclaw/vllm-gemma.yaml +++ b/apps/base/customer1/openclaw/vllm-gemma.yaml @@ -32,8 +32,10 @@ spec: - "--dtype" - "bfloat16" - "--max-model-len" - - "32768" + - "8192" - "--trust-remote-code" + - "--gpu-memory-utilization" + - "0.95" ports: - containerPort: 8000 resources: