vllm-render.yaml

apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm-render
  labels:
    app: vllm-render
spec:
  replicas: 1
  selector:
    matchLabels:
      app: vllm-render
  template:
    metadata:
      labels:
        app: vllm-render
    spec:
      containers:
      - name: vllm-render
        image: ${VLLM_RENDER_IMAGE}
        imagePullPolicy: IfNotPresent
        command: ["vllm", "launch", "render"]
        args: ["${MODEL_NAME}", "--port=${VLLM_RENDER_PORT}"]
        # For gated models, inject HF_TOKEN via a Secret reference:
        # env:
        # - name: HF_TOKEN
        #   valueFrom:
        #     secretKeyRef:
        #       name: hf-token
        #       key: token
        ports:
        - name: render-http
          containerPort: ${VLLM_RENDER_PORT}
        startupProbe:
          httpGet:
            path: /health
            port: ${VLLM_RENDER_PORT}
          initialDelaySeconds: 2
          periodSeconds: 1
          failureThreshold: 600
          timeoutSeconds: 1
        livenessProbe:
          httpGet:
            path: /health
            port: ${VLLM_RENDER_PORT}
          periodSeconds: 10
          failureThreshold: 5
          timeoutSeconds: 1
        readinessProbe:
          httpGet:
            path: /health
            port: ${VLLM_RENDER_PORT}
          periodSeconds: 5
          failureThreshold: 1
          timeoutSeconds: 1
        volumeMounts:
        - name: model-cache
          mountPath: /root/.cache/huggingface
      volumes:
      - name: model-cache
        emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
  name: vllm-render
  labels:
    app: vllm-render
spec:
  selector:
    app: vllm-render
  ports:
  - name: http
    protocol: TCP
    port: ${VLLM_RENDER_PORT}
    targetPort: ${VLLM_RENDER_PORT}
  type: ClusterIP