diff --git a/infra/kube-vllm/deployment.yaml b/infra/kube-vllm/deployment.yaml index 9014954..c812d4d 100644 --- a/infra/kube-vllm/deployment.yaml +++ b/infra/kube-vllm/deployment.yaml @@ -7,6 +7,8 @@ metadata: app: vllm spec: replicas: 1 + strategy: + type: Recreate selector: matchLabels: app: vllm diff --git a/infra/kube-vllm/service.yaml b/infra/kube-vllm/service.yaml index 4bdc350..b97f202 100644 --- a/infra/kube-vllm/service.yaml +++ b/infra/kube-vllm/service.yaml @@ -23,7 +23,7 @@ spec: - nodePort: 31508 name: vllm-api port: 2701 - targetPort: 8000 + targetPort: 8080 selector: app: vllm-metrics type: LoadBalancer