miniLLM/docker-compose.yml at master · Micuks/miniLLM · 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: "3.8"

services:
  hf-serve:
    build:
      context: .
      dockerfile: Dockerfile
    ports:
      - "8000:8000"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    environment:
      - NVIDIA_VISIBLE_DEVICES=all

  vllm-serve:
    build:
      context: .
      dockerfile: Dockerfile.vllm
    ports:
      - "8001:8001"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    environment:
      - MODEL_NAME_OR_PATH=Qwen/Qwen2.5-7B-Instruct
      - MAX_MODEL_LEN=2048
      - GPU_MEMORY_UTILIZATION=0.90
      - NVIDIA_VISIBLE_DEVICES=all
    volumes:
      - ${HF_HOME:-~/.cache/huggingface}:/root/.cache/huggingface

  prometheus:
    image: prom/prometheus:latest
    ports:
      - "9090:9090"
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
    depends_on:
      - hf-serve
      - vllm-serve

  grafana:
    image: grafana/grafana:latest
    ports:
      - "3000:3000"
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
    volumes:
      - ./monitoring/grafana-dashboard.json:/var/lib/grafana/dashboards/minillm.json:ro
    depends_on:
      - prometheus