fastchat-docker/docker-compose.yml at master · forcemeter/fastchat-docker · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
version: "3.9"

services:
  # Worker 控制器，实现Worker 的分布式调度
  fastchat-controller:
    image: fastchat:latest
    ports:
      - "21001:21001"
      - "7861:7861"
    entrypoint: ["python3.9", "-m", "fastchat.serve.controller", "--host", "0.0.0.0", "--port", "21001"]
    depends_on:
      - fastchat-worker-qwen
      - fastchat-worker-baichuan

  # WebUI
  fastchat-webui:
    image: fastchat:latest
    ports:
      - "7860:7860"
    depends_on:
      fastchat-controller:
        condition: service_started
    entrypoint: ["python3.9", "-m", "fastchat.serve.gradio_web_server_multi", "--model-list-mode", "reload", "--controller-url", "http://fastchat-controller:21001", "--host", "0.0.0.0", "--port", "7860"]

  # OpenAi 兼容接口
  fastchat-api-server:
    image: fastchat:latest
    ports:
      - "8000:8000"
    depends_on:
      - fastchat-controller
    entrypoint: ["python3.9", "-m", "fastchat.serve.openai_api_server", "--controller-address", "http://fastchat-controller:21001", "--host", "0.0.0.0", "--port", "8000"]

  #千问
  fastchat-worker-qwen:
    volumes:
      - /files/huggingface:/files/huggingface
    image: fastchat:latest
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['1']
              capabilities: [gpu]
    entrypoint: ["python3.9", "-m", "fastchat.serve.model_worker", "--model-names=Qwen-7B-Chat", "--model-path=/files/huggingface/Qwen-7B-Chat", "--worker-address=http://fastchat-worker-qwen:21002", "--controller-address=http://fastchat-controller:21001", "--host=0.0.0.0", "--port=21002", "--device=cuda", "--gpus=0", "--num-gpus=1", "--max-gpu-memory=22GB"]

  #百川
  fastchat-worker-baichuan:
    volumes:
      - /files/huggingface:/files/huggingface
    image: fastchat:latest
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ['2', '3']
              capabilities: [gpu]
    entrypoint: ["python3.9", "-m", "fastchat.serve.model_worker", "--model-names=Baichuan-13B-Chat", "--model-path=/files/huggingface/Baichuan-13B-Chat", "--worker-address=http://fastchat-worker-baichuan:21003", "--controller-address=http://fastchat-controller:21001", "--host=0.0.0.0", "--port=21003", "--device=cuda", "--num-gpus=2", "--max-gpu-memory=24GB"]