docker-compose.yml

version: '3.8'

services:
  helion-inference:
    build:
      context: .
      dockerfile: Dockerfile
      args:
        - CUDA_VERSION=12.1.1
    image: helion:2.5-rnd
    container_name: helion-inference-server
    
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    
    environment:
      - MODEL_PATH=/models/helion
      - MODEL_NAME=DeepXR/Helion-2.5-Rnd
      - PORT=8000
      - HOST=0.0.0.0
      - TENSOR_PARALLEL_SIZE=2
      - MAX_MODEL_LEN=131072
      - GPU_MEMORY_UTILIZATION=0.95
      - CUDA_VISIBLE_DEVICES=0,1
      - WORKERS=1
      
      # Optional: HuggingFace token for private models
      # - HF_TOKEN=your_token_here
      
      # Logging
      - LOG_LEVEL=info
      - LOG_FILE=/app/logs/helion.log
    
    volumes:
      - ./models:/models:ro
      - ./logs:/app/logs
      - ./cache:/app/cache
      - ./inference:/app/inference:ro
      - ./model_config.yaml:/app/model_config.yaml:ro
    
    ports:
      - "8000:8000"
      - "8001:8001"  # Metrics
      - "8002:8002"  # Admin
    
    healthcheck:
      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
      interval: 30s
      timeout: 10s
      retries: 3
      start_period: 120s
    
    restart: unless-stopped
    
    networks:
      - helion-network
    
    logging:
      driver: "json-file"
      options:
        max-size: "100m"
        max-file: "10"

  prometheus:
    image: prom/prometheus:latest
    container_name: helion-prometheus
    
    volumes:
      - ./monitoring/prometheus.yml:/etc/prometheus/prometheus.yml:ro
      - prometheus-data:/prometheus
    
    ports:
      - "9090:9090"
    
    command:
      - '--config.file=/etc/prometheus/prometheus.yml'
      - '--storage.tsdb.path=/prometheus'
      - '--web.console.libraries=/usr/share/prometheus/console_libraries'
      - '--web.console.templates=/usr/share/prometheus/consoles'
    
    networks:
      - helion-network
    
    restart: unless-stopped

  grafana:
    image: grafana/grafana:latest
    container_name: helion-grafana
    
    environment:
      - GF_SECURITY_ADMIN_PASSWORD=admin
      - GF_USERS_ALLOW_SIGN_UP=false
    
    volumes:
      - grafana-data:/var/lib/grafana
      - ./monitoring/grafana/dashboards:/etc/grafana/provisioning/dashboards:ro
      - ./monitoring/grafana/datasources:/etc/grafana/provisioning/datasources:ro
    
    ports:
      - "3000:3000"
    
    networks:
      - helion-network
    
    depends_on:
      - prometheus
    
    restart: unless-stopped

  nginx:
    image: nginx:alpine
    container_name: helion-nginx
    
    volumes:
      - ./nginx/nginx.conf:/etc/nginx/nginx.conf:ro
      - ./nginx/ssl:/etc/nginx/ssl:ro
    
    ports:
      - "80:80"
      - "443:443"
    
    networks:
      - helion-network
    
    depends_on:
      - helion-inference
    
    restart: unless-stopped

  redis:
    image: redis:7-alpine
    container_name: helion-redis
    
    command: redis-server --appendonly yes
    
    volumes:
      - redis-data:/data
    
    ports:
      - "6379:6379"
    
    networks:
      - helion-network
    
    restart: unless-stopped

networks:
  helion-network:
    driver: bridge
    ipam:
      config:
        - subnet: 172.28.0.0/16

volumes:
  prometheus-data:
    driver: local
  grafana-data:
    driver: local
  redis-data:
    driver: local