Qwen3 大模型在阿里云容器服务上的极简部署教程

git lfs install
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/Qwen/Qwen3-8B
cd Qwen3-8B/
git lfs pull

ossutil mkdir oss://<your-bucket-name>/models/Qwen3-8B
ossutil cp -r ./Qwen3-8B oss://<your-bucket-name>/models/Qwen3-8B

apiVersion: v1
kind: Secret
metadata:
  name: oss-secret
stringData:
  akId: <your-oss-ak> # 配置用于访问OSS的AccessKey ID
  akSecret: <your-oss-sk> # 配置用于访问OSS的AccessKey Secret
---
apiVersion: v1
kind: PersistentVolume
metadata:
  name: llm-model
  labels:
    alicloud-pvname: llm-model
spec:
  capacity:
    storage: 30Gi 
  accessModes:
    - ReadOnlyMany
  persistentVolumeReclaimPolicy: Retain
  csi:
    driver: ossplugin.csi.alibabacloud.com
    volumeHandle: llm-model
    nodePublishSecretRef:
      name: oss-secret
      namespace: default
    volumeAttributes:
      bucket: <your-bucket-name> # bucket名称
      url: <your-bucket-endpoint> # Endpoint信息，如oss-cn-hangzhou-internal.aliyuncs.com
      otherOpts: "-o umask=022 -o max_stat_cache_size=0 -o allow_other"
      path: <your-model-path> # 本示例中为/models/Qwen3-8B/
---
apiVersion: v1
kind: PersistentVolumeClaim
metadata:
  name: llm-model
spec:
  accessModes:
    - ReadOnlyMany
  resources:
    requests:
      storage: 30Gi
  selector:
    matchLabels:
      alicloud-pvname: llm-model

apiVersion: apps/v1
kind: Deployment
metadata:
  labels:
    app: qwen3
  name: qwen3
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: qwen3
  template:
    metadata:
      labels:
        app: qwen3
        # for ACS Cluster
        # alibabacloud.com/compute-class: gpu
        # 指定GPU型号为example-model，请按实际情况填写，如T4
        # alibabacloud.com/gpu-model-series: "example-model"
    spec:
      volumes:
        - name: model
          persistentVolumeClaim:
            claimName: llm-model
      containers:
      - command:
        - sh
        - -c
        - vllm serve /models/Qwen3-8B/ --port 8000 --trust-remote-code --max-model-len 2048 --gpu-memory-utilization 0.98 
        image: kube-ai-registry.cn-shanghai.cr.aliyuncs.com/kube-ai/vllm:v0.8.4
        imagePullPolicy: IfNotPresent
        name: vllm
        ports:
        - containerPort: 8000
          name: restful
          protocol: TCP
        readinessProbe:
          tcpSocket:
            port: 8000
          initialDelaySeconds: 30
        resources:
          limits:
            nvidia.com/gpu: "1"
            cpu: 8
            memory: 16Gi
          requests:
            nvidia.com/gpu: "1"
            cpu: 8
            memory: 16Gi
        volumeMounts:
          - mountPath: /models/Qwen3-8B/
            name: model
---
apiVersion: v1
kind: Service
metadata:
  name: qwen3
spec:
  ports:
    - name: http
      port: 8000
      protocol: TCP
      targetPort: 8000
  selector:
    app: qwen3
  type: ClusterIP

kubectl port-forward svc/qwen3 8000:8000

Forwarding from 127.0.0.1:8000 -> 8000
Forwarding from [::1]:8000 -> 8000

curl -H "Content-Type: application/json" http://localhost:8000/v1/chat/completions -d '{"model": "/models/Qwen3-8B/", "messages": [{"role": "user", "content": "Say this is a test!"}], "max_tokens": 512, "temperature": 0.7, "top_p": 0.9, "seed": 10}'

{"id":"chatcmpl-3e472d9f449648718a483279062f4987","object":"chat.completion","created":1745980464,"model":"/models/Qwen3-8B/","choices":[{"index":0,"message":{"role":"assistant","reasoning_content":null,"content":"<think>\nOkay, the user said \"Say this is a test!\" and I need to respond. Let me think about how to approach this. First, I should acknowledge their message. Maybe start with a friendly greeting. Then, since they mentioned a test, perhaps they're testing my response capabilities. I should confirm that I'm here to help and offer assistance with anything they need. Keep it open-ended so they feel comfortable asking more. Also, make sure the tone is positive and encouraging. Let me put that together in a natural way.\n</think>\n\nHello! It's great to meet you. If you have any questions or need help with something, feel free to let me know. I'm here to assist! 😊","tool_calls":[]},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":14,"total_tokens":161,"completion_tokens":147,"prompt_tokens_details":null},"prompt_logprobs":null}

apiVersion: apps/v1
kind: Deployment
metadata:
  name: qwen3
spec:
  template:
    metadata:
      labels:
        app: qwen3
        # for ACS 算力
        alibabacloud.com/compute-class: gpu
        # 指定GPU型号为example-model，请按实际情况填写，如T4
        alibabacloud.com/gpu-model-series: "example-model"
    spec:
      containers:
      ...