Real-Time-Multi-Model-AI-Pipeline/docker-compose.yml at main · jayshah1819/Real-Time-Multi-Model-AI-Pipeline · 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
version: '3'
services:
  triton:
    image: nvcr.io/nvidia/tritonserver:23.09-py3
    command: tritonserver --model-repository=/models
    ports:
      - "8000:8000"  # HTTP
      - "8001:8001"  # gRPC
      - "8002:8002"  # Metrics
    volumes:
      - ./triton_models:/models
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

  pipeline:
    build:
      context: .
      dockerfile: Dockerfile
    volumes:
      - .:/workspace
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
    depends_on:
      - triton
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]