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
    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"
          env:
            - name: HF_HUB_OFFLINE
              value: "1"
            - name: NVIDIA_VISIBLE_DEVICES
              value: all
            - name: NVIDIA_DRIVER_CAPABILITIES
              value: all
          ports:
            - containerPort: 8000
              hostPort: 8000
          volumeMounts:
            - name: model
              mountPath: /model
            - name: dshm
              mountPath: /dev/shm
      volumes:
        - name: model
          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
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: xinference
  namespace: llm
  labels:
    app: xinference
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: xinference
  template:
    metadata:
      labels:
        app: xinference
    spec:
      nodeName: prod102
      enableServiceLinks: false
      containers:
        - name: xinference
          image: xprobe/xinference:latest
          imagePullPolicy: IfNotPresent
          command: ["xinference-local", "-H", "0.0.0.0", "--log-level", "info"]
          env:
            - name: XINFERENCE_HOME
              value: /data
            - name: XINFERENCE_MODEL_SRC
              value: modelscope
            - name: NVIDIA_VISIBLE_DEVICES
              value: all
            - name: NVIDIA_DRIVER_CAPABILITIES
              value: all
          ports:
            - containerPort: 9997
              hostPort: 9997
          volumeMounts:
            - name: data
              mountPath: /data
      volumes:
        - name: data
          hostPath:
            path: /usr/cluster/dify/xinference
            type: DirectoryOrCreate
---
apiVersion: v1
kind: Service
metadata:
  name: xinference
  namespace: llm
spec:
  selector:
    app: xinference
  ports:
    - name: p9997
      port: 9997
      targetPort: 9997
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: new-api
  namespace: llm
  labels:
    app: new-api
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: new-api
  template:
    metadata:
      labels:
        app: new-api
    spec:
      nodeName: prod102
      enableServiceLinks: false
      containers:
        - name: new-api
          image: calciumion/new-api:latest
          imagePullPolicy: IfNotPresent
          command: ["/new-api"]
          args: ["--log-dir", "/app/logs"]
          ports:
            - containerPort: 3000
              hostPort: 3000
          volumeMounts:
            - name: data
              mountPath: /data
            - name: logs
              mountPath: /app/logs
      volumes:
        - name: data
          hostPath:
            path: /opt/new-api/data
            type: DirectoryOrCreate
        - name: logs
          hostPath:
            path: /opt/new-api/logs
            type: DirectoryOrCreate
---
apiVersion: v1
kind: Service
metadata:
  name: new-api
  namespace: llm
spec:
  selector:
    app: new-api
  ports:
    - name: p3000
      port: 3000
      targetPort: 3000
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: nav
  namespace: llm
  labels:
    app: nav
spec:
  replicas: 1
  strategy:
    type: Recreate
  selector:
    matchLabels:
      app: nav
  template:
    metadata:
      labels:
        app: nav
    spec:
      nodeName: prod102
      containers:
        - name: nav
          image: nginx:latest
          imagePullPolicy: IfNotPresent
          command: ["/docker-entrypoint.sh"]
          args: ["nginx", "-g", "daemon off;"]
          ports:
            - containerPort: 80
              hostPort: 8090
          volumeMounts:
            - name: html
              mountPath: /usr/share/nginx/html
      volumes:
        - name: html
          hostPath:
            path: /usr/cluster/llm-nav
            type: DirectoryOrCreate
---
apiVersion: v1
kind: Service
metadata:
  name: nav
  namespace: llm
spec:
  selector:
    app: nav
  ports:
    - name: p80
      port: 80
      targetPort: 80