version: 0.0.1
provider:
  name: aliyun
  region: cn-hangzhou


service: insight-poc-gpu

tags:
  owner: geek-fun

functions:
  insight_poc_fn:
    name: insight-poc-gpu-fn
    container:
      image: registry.cn-hangzhou.aliyuncs.com/serverless_devs/modelscope:ubuntu20.04-cuda11.3.0-py37-torch1.11.0-tf1.15.5-1.5.0
      cmd: "ollama run modelscope.cn/DeepSeek-R1-Distill-Qwen-1.5B-GGUF"
      port: 9000
    memory: 4096
    gpu: TESLA_16
    timeout: 900
    log: true
    network:
      vpc_id: vpc-bp1jpzq0807mrww7i8uko
      subnet_ids:
        - vsw-bp1tp32pxn8c3mm07e9s2
        - vsw-bp1gs2ggjq85apbf5yd9d
      security_group:
        name: insight-poc-gpu-fn-sg
        ingress:
          - TCP:0.0.0.0/0:80
          - TCP:0.0.0.0/0:443
          - TCP:0.0.0.0/0:22/22
          - ICMP:0.0.0.0/0:ALL
        egress:
          - ALL:0.0.0.0/0:ALL
    storage:
      nas:
        - mount_path: /mnt/nas
          storage_class: STANDARD_CAPACITY
    environment:
      OLLAMA_MODELS: /mnt/nas/models
      LLAMA_GPU_OVERHEAD: 0
      OLLAMA_HOST: http://0.0.0.0:11434
      OLLAMA_INTEL_GPU: false
      OLLAMA_KEEP_ALIVE: 2562047h47m16.854775807s
      OLLAMA_LOAD_TIMEOUT: 5m0s
      OLLAMA_MAX_LOADED_MODELS: 1
      OLLAMA_MAX_QUEUE: 1
      OLLAMA_MULTIUSER_CACHE: false
      OLLAMA_NOHISTORY: false
      OLLAMA_NOPRUNE: false
      OLLAMA_NUM_PARALLEL: 1
      OLLAMA_ORIGINS: [ * http://localhost https://localhost http://localhost:* https://localhost:* http://127.0.0.1 https://127.0.0.1 http://127.0.0.1:* https://127.0.0.1:* http://0.0.0.0 https://0.0.0.0 http://0.0.0.0:* https://0.0.0.0:* app://* file://* tauri://* vscode-webview://* ]
      OLLAMA_SCHED_SPREAD: fals