基于Knative快速部署DeepSeek-R1

apiVersion: serving.knative.dev/v1
kind: Service
metadata:
  labels:
    release: deepseek
  name: deepseek
  namespace: default
spec:
  template:
    metadata:
      annotations:
        k8s.aliyun.com/eci-use-specs : "ecs.gn7i-c8g1.2xlarge" // GPU 规格 A10
        autoscaling.knative.dev/min-scale: "1"
      labels:
        release: deepseek
        alibabacloud.com/eci: "true" 
    spec:
      containers:
      - command:
          - /bin/sh
          - -c
        args:
          - vllm serve deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B --max_model_len 2048
        image: registry.cn-hangzhou.aliyuncs.com/knative-sample/vllm-openai:v0.7.1
        imagePullPolicy: IfNotPresent
        name: vllm-container
        env:
        - name: HF_HUB_ENABLE_HF_TRANSFER
          value: "0"
        ports:
          - containerPort: 8000
        readinessProbe:
          httpGet:
            path: /health
            port: 8000
          initialDelaySeconds: 60
          periodSeconds: 5
        resources:
          limits:
            nvidia.com/gpu: "1"
          requests:
            nvidia.com/gpu: "1"
        volumeMounts:
          - mountPath: /root/.cache/huggingface
            name: cache-volume
          - name: shm
            mountPath: /dev/shm
      volumes:
        - name: cache-volume
          emptyDir: {}
        - name: shm
          emptyDir:
            medium: Memory
            sizeLimit: 2Gi

curl -H "Host:  deepseek.default.example.com" -H "Content-Type: application/json" http://deepseek.knative.top/v1/chat/completions -d '{"model": "deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B", "messages": [{"role": "user", "content": "介绍一下DeepSeek-R1"}]}'

{"id":"chatcmpl-07d99924-b998-4f39-9ec9-01dfb4ece8a0","object":"chat.completion","created":1739003758,"model":"deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B","choices":[{"index":0,"message":{"role":"assistant","reasoning_content":null,"content":"<think>\n\n</think>\n\nDeepSeek-R1 是一个大语言模型，由深度求索公司开发，旨在支持对话和语言理解任务。以下是关于DeepSeek-R1的一些关键信息：\n\n1. **架构与技术**：\n   - **语言处理**：DeepSeek-R1 作为大语言模型，主要功能包括文本生成、理解、对话等。\n   - **自学习能力**：通过大量文本数据进行训练，提升其自然语言处理能力。\n\n2. **应用场景**：\n   - **聊天机器人**：在制造业、医疗、教育等领域用于辅助 Humans进行对话。\n   - **内容生成**：擅长生成高质量的文本 content，用于新闻报道、营销资料等。\n\n3. **技术特点**：\n   - **高效计算**：相比轻量级模型，DeepSeek-R1 更高效，适合实时响应。\n   - **模块化设计**：模型基于模块化架构，便于扩展和优化。\n\n4. **用户评估**：\n   - **使用场景**：适合特定行业的企业需求。\n   - **评价标准**：基于技术准确性和应用场景评估。\n\n5. **特点与优势**：\n   - **性能 superior**：在多个自然语言处理任务中表现优异。\n   - **实用性**：能够解决实际工作场所中的语言处理需求。\n\n6. **未来发展**：\n   - **技术更新**：模型持续优化，关注更多应用领域，如自动驾驶和其他伦理问题。\n\n总结而言，DeepSeek-R1 是一个功能强大且符合特定行业需求的大语言模型，旨在通过高效的人工智能服务于实际应用场景。","tool_calls":[]},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":8,"total_tokens":337,"completion_tokens":329,"prompt_tokens_details":null},"prompt_logprobs":null}

apiVersion: serving.knative.dev/v1
kind: Service
metadata:
  name: chatgpt-next-web
spec:
  template:
    spec:
      containers:
      - name: chatgpt-next-web
        image: registry.cn-hangzhou.aliyuncs.com/knative-sample/chatgpt-next-web:v2.15.8
        ports:
        - containerPort: 3000
        readinessProbe:
          tcpSocket:
            port: 3000
          initialDelaySeconds: 60
          periodSeconds: 5
        env:
        - name: HOSTNAME
          value: '0.0.0.0'
  # 替换为你的 OpenAI API 地址

8.211.157.198 chatgpt-next-web.default.example.com # 网关IP和域名请以您的实际数据为准。