BrainDrain/docker-compose.yml at main · HumbleBee14/BrainDrain · 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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
services:
  postgres:
    image: postgres:16-alpine
    ports:
      - "5432:5432"
    environment:
      POSTGRES_DB: platform
      POSTGRES_USER: platform
      POSTGRES_PASSWORD: platform_dev
    volumes:
      - postgres_data:/var/lib/postgresql/data
    shm_size: 256mb
    healthcheck:
      test: ["CMD-SHELL", "pg_isready -U platform"]
      interval: 5s
      timeout: 5s
      retries: 5
    cpus: 2
    mem_limit: 1g

  redis:
    image: redis:7-alpine
    ports:
      - "6379:6379"
    command: redis-server --appendonly yes --maxmemory 256mb --maxmemory-policy allkeys-lru
    volumes:
      - redis_data:/data
    healthcheck:
      test: ["CMD", "redis-cli", "ping"]
      interval: 5s
      timeout: 3s
      retries: 5
    cpus: 1
    mem_limit: 512m

  minio:
    image: minio/minio:latest
    ports:
      - "9000:9000"
      - "9001:9001"
    environment:
      MINIO_ROOT_USER: minioadmin
      MINIO_ROOT_PASSWORD: minioadmin
    command: server /data --console-address ":9001"
    volumes:
      - minio_data:/data
    healthcheck:
      test: ["CMD", "mc", "ready", "local"]
      interval: 5s
      timeout: 5s
      retries: 5
    cpus: 2
    mem_limit: 1g

  # vLLM inference server with LoRA adapter support
  # Requires NVIDIA GPU. Uncomment to enable model deployment.
  # vllm:
  #   image: vllm/vllm-openai:latest
  #   ports:
  #     - "8080:8000"
  #   environment:
  #     VLLM_API_KEY: ""
  #   command: >
  #     --model meta-llama/Llama-3.1-8B
  #     --enable-lora
  #     --max-lora-rank 64
  #     --max-loras 4
  #     --gpu-memory-utilization 0.85
  #     --max-model-len 4096
  #   volumes:
  #     - vllm_cache:/root/.cache/huggingface
  #     - minio_data:/data
  #   deploy:
  #     resources:
  #       reservations:
  #         devices:
  #           - driver: nvidia
  #             count: 1
  #             capabilities: [gpu]
  #   healthcheck:
  #     test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
  #     interval: 30s
  #     timeout: 10s
  #     retries: 5
  #     start_period: 120s

  # Create default bucket on startup
  minio-init:
    image: minio/mc:latest
    depends_on:
      minio:
        condition: service_healthy
    entrypoint: >
      /bin/sh -c "
      mc alias set local http://minio:9000 minioadmin minioadmin;
      mc mb local/platform-dev --ignore-existing;
      exit 0;
      "

volumes:
  postgres_data:
  redis_data:
  minio_data:
  # vllm_cache:

networks:
  default:
    name: platform-net
    external: true