diff --git a/vllm/vllm-deployment.yaml b/vllm/vllm-deployment.yaml index 42cbc9a..d5461cf 100644 --- a/vllm/vllm-deployment.yaml +++ b/vllm/vllm-deployment.yaml @@ -39,7 +39,7 @@ spec: "--trust-remote-code", "--port=8000", "--dtype=half", - "--tensor-parallel-size=1"] + "--tensor-parallel-size=2"] ports: - containerPort: 8000 name: http