version: "3.8"

services:
  bentoml:
    image: bentoml/bentoml:${BENTO_VERSION:-latest}
    container_name: bentoml
    restart: unless-stopped
    ports:
      - "${BENTO_PORT:-3000}:3000"
      - "${METRICS_PORT:-3001}:3001"
    volumes:
      - bentoml_home:/home/bentoml
      - bentoml_models:/home/bentoml/bentoml/models
    environment:
      - BENTOML_HOME=/home/bentoml/bentoml
      - BENTOML_PORT=3000
      - BENTOML_METRICS_PORT=3001
      - BENTOML_LOG_LEVEL=${LOG_LEVEL:-INFO}
    command: bentoml serve --host 0.0.0.0 --port 3000
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]

volumes:
  bentoml_home:
  bentoml_models: