docker-compose.yml

version: '3.8'

services:
  deepcoder-api:
    build:
      context: .
      dockerfile: Dockerfile
    container_name: deepcoder-model
    ports:
      - "8000:8000"
    environment:
      - MODEL_NAME=ai/deepcoder-preview
      - MODEL_VARIANT=14B-Q4_K_M
      - HUGGINGFACE_HUB_CACHE=/app/cache
      - CUDA_VISIBLE_DEVICES=0
    volumes:
      - ./models:/app/models
      - ./cache:/app/cache
      - ./logs:/app/logs
    restart: unless-stopped
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 40s

  nginx:
    image: nginx:alpine
    container_name: deepcoder-nginx
    ports:
      - "80:80"
      - "443:443"
    volumes:
      - ./nginx.conf:/etc/nginx/nginx.conf
      - ./ssl:/etc/nginx/ssl
    depends_on:
      - deepcoder-api
    restart: unless-stopped

volumes:
  models:
  cache:
  logs: