apiVersion: apps/v1
kind: Deployment
metadata:
  name: vllm
  namespace: llm
  labels:
    app: vllm
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: vllm
  template:
    metadata:
      labels:
        app: vllm
      annotations:
        llm.local/compose-service: "vllm"
    spec:
      nodeName: prod102
      enableServiceLinks: false
      hostAliases:
        - ip: 10.0.1.47
          hostnames: ["host.docker.internal"]
      containers:
        - name: vllm
          image: docker.m.daocloud.io/vllm/vllm-openai:latest
          imagePullPolicy: IfNotPresent
          command:
            - "vllm"
            - "serve"
          args:
            - "/model"
            - "--trust-remote-code"
            - "--dtype"
            - "bfloat16"
            - "--tensor-parallel-size"
            - "1"
            - "--enable-auto-tool-choice"
            - "--tool-call-parser"
            - "qwen3_xml"
            - "--reasoning-parser"
            - "qwen3"
            - "--max-model-len"
            - "65536"
            - "--gpu-memory-utilization"
            - "0.70"
            - "--max-num-seqs"
            - "8"
            - "--served-model-name"
            - "qwen3.6-27b"
            - "--enable-prefix-caching"
            - "--host"
            - "0.0.0.0"
            - "--port"
            - "8000"
          envFrom:
            - secretRef:
                name: vllm-env
          ports:
            - containerPort: 8000
              hostPort: 8000
              protocol: TCP
          startupProbe:
            httpGet:
              path: /health
              port: 8000
            periodSeconds: 10
            failureThreshold: 36
          livenessProbe:
            httpGet:
              path: /health
              port: 8000
            initialDelaySeconds: 120
            periodSeconds: 10
            failureThreshold: 5
          readinessProbe:
            httpGet:
              path: /health
              port: 8000
            initialDelaySeconds: 60
            periodSeconds: 5
            failureThreshold: 3
          volumeMounts:
            - name: vol0
              mountPath: "/model"
            - name: dshm
              mountPath: "/dev/shm"
      volumes:
        - name: vol0
          hostPath:
            path: "/models/Qwen3.6-27B"
            type: Directory
        - name: dshm
          emptyDir:
            medium: Memory
            sizeLimit: 8Gi
---
apiVersion: v1
kind: Service
metadata:
  name: vllm
  namespace: llm
spec:
  selector:
    app: vllm
  ports:
    - name: p8000
      port: 8000
      targetPort: 8000
      protocol: TCP