企业级LLM推理部署新范式：基于ACK的DeepSeek蒸馏模型生产环境落地指南

# 确认是否已安装git-lfs插件
# 如未安装可执行yum install git-lfs 或 apt install git-lfs安装
git lfs install
# clone DeepSeek-R1-Distill-Qwen-7B项目
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B.git
# 下载模型文件
cd DeepSeek-R1-Distill-Qwen-7B/
git lfs pull

# 创建目录
ossutil mkdir oss://<your-bucket-name>/models/DeepSeek-R1-Distill-Qwen-7B
# 上传文件
ossutil cp -r ./DeepSeek-R1-Distill-Qwen-7B oss://<your-bucket-name>/models/DeepSeek-R1-Distill-Qwen-7B

arena serve kserve \  
     --name=deepseek \  
     --image=kube-ai-registry.cn-shanghai.cr.aliyuncs.com/kube-ai/vllm:v0.6.6 \
     --gpus=1 \ 
     --cpu=4 \   
     --memory=12Gi \ 
     --data=llm-model:/model/DeepSeek-R1-Distill-Qwen-7B \  
     "vllm serve /model/DeepSeek-R1-Distill-Qwen-7B --port 8080 --trust-remote-code --served-model-name deepseek-r1 --max-model-len 32768 --gpu-memory-utilization 0.95 --enforce-eager"

inferenceservice.serving.kserve.io/deepseek created
INFO[0003] The Job deepseek has been submitted successfully
INFO[0003] You can run `arena serve get deepseek --type kserve -n default` to check the job status

arena serve get deepseek

Name:       deepseek
Namespace:  default
Type:       KServe
Version:    1
Desired:    1
Available:  1
Age:        3m
Address:    http://deepseek-default.example.com
Port:       :80
GPU:        1


Instances:
NAME                                 STATUS   AGE  READY  RESTARTS  GPU  NODE
----                                 ------   ---  -----  --------  ---  ---- 
deepseek-predictor-7cd4d568fd-fznfg  Running  3m   1/1    0         1    cn-beijing.172.16.1.77

# 获取Nginx ingress的IP地址。
NGINX_INGRESS_IP=$(kubectl -n kube-system get svc nginx-ingress-lb -ojsonpath='{.status.loadBalancer.ingress[0].ip}')
# 获取Inference Service的Hostname。SERVICE_HOSTNAME=$(kubectl get inferenceservice deepseek -o jsonpath='{.status.url}' | cut -d "/" -f 3)
# 发送请求访问推理服务。
curl -H "Host: $SERVICE_HOSTNAME" -H "Content-Type: application/json" http://$NGINX_INGRESS_IP:80/v1/chat/completions -d '{"model": "deepseek-r1", "messages": [{"role": "user", "content": "Say this is a test!"}], "max_tokens": 512, "temperature": 0.7, "top_p": 0.9, "seed": 10}'

{"id":"chatcmpl-0fe3044126252c994d470e84807d4a0a","object":"chat.completion","created":1738828016,"model":"deepseek-r1","choices":[{"index":0,"message":{"role":"assistant","content":"<think>\n\n</think>\n\nIt seems like you're testing or sharing some information. How can I assist you further? If you have any questions or need help with something, feel free to ask!","tool_calls":[]},"logprobs":null,"finish_reason":"stop","stop_reason":null}],"usage":{"prompt_tokens":9,"total_tokens":48,"completion_tokens":39,"prompt_tokens_details":null},"prompt_logprobs":null}

arena serve kserve \ 
   --name=deepseek \  
   --image=kube-ai-registry.cn-shanghai.cr.aliyuncs.com/kube-ai/vllm:v0.6.6 \ 
   --gpus=1 \   
   --cpu=4 \  
   --memory=12Gi \  
   --enable-prometheus=true \ 
   --data=llm-model:/model/DeepSeek-R1-Distill-Qwen-7B \  
   "vllm serve /model/DeepSeek-R1-Distill-Qwen-7B --port 8080 --trust-remote-code --served-model-name deepseek-r1 --max-model-len 32768 --gpu-memory-utilization 0.95 --enforce-eager"

arena serve kserve \ 
    --name=deepseek \   
    --image=kube-ai-registry.cn-shanghai.cr.aliyuncs.com/kube-ai/vllm:v0.6.6 \
    --gpus=1 \  
    --cpu=4 \ 
    --memory=12Gi \   
    --scale-metric=DCGM_CUSTOM_PROCESS_SM_UTIL \   
    --scale-target=80 \  
    --min-replicas=1 \  
    --max-replicas=2 \   
    --data=llm-model:/model/DeepSeek-R1-Distill-Qwen-7B \ 
    "vllm serve /model/DeepSeek-R1-Distill-Qwen-7B --port 8080 --trust-remote-code --served-model-name deepseek-r1 --max-model-len 32768 --gpu-memory-utilization 0.95 --enforce-eager"