diff --git a/apps/base/customer1/openclaw/vllm-gemma.yaml b/apps/base/customer1/openclaw/vllm-gemma.yaml index 6ad0445..b1b8654 100644 --- a/apps/base/customer1/openclaw/vllm-gemma.yaml +++ b/apps/base/customer1/openclaw/vllm-gemma.yaml @@ -36,16 +36,12 @@ spec: - --host=0.0.0.0 - --port=8000 - --tensor-parallel-size=1 - - --gpu-memory-utilization=0.95 # ← Critical: lower than default 0.90 - - --max-model-len=24576 # Start conservative (you can raise to 32768 later) + - --gpu-memory-utilization=0.95 + - --max-model-len=24576 - --enable-auto-tool-choice - --trust-remote-code - --dtype=auto - - --tool-call-parser=pythonic - - --reasoning-parser=qwen3 - --enable-prefix-caching - - --enable-chunked-prefill - - --kv-cache-dtype=fp8 ##- --limit-mm-per-prompt='{"image"=1, "video"=0}' # Optional: limit vision if not heavily using images yet ports: - containerPort: 8000