services:
  glados-tts-cpu:
    image: xerotacovix/glados-ladosp-tts:cpu
    container_name: glados-tts-cpu
    ports:
      - "10201:10200"
    volumes:
      - glados_model_cache:/data
      - glados_hf_cache:/root/.cache/huggingface
      - glados_nltk_data:/root/nltk_data
    environment:
      - MODEL_DIR=/data
      - URI=tcp://0.0.0.0:10200
      - DEVICE=cpu
    restart: unless-stopped

  glados-tts-cuda:
    image: xerotacovix/glados-ladosp-tts:cuda
    container_name: glados-tts-cuda
    ports:
      - "10200:10200"
    volumes:
      - glados_model_cache:/data
      - glados_hf_cache:/root/.cache/huggingface
      - glados_nltk_data:/root/nltk_data
    environment:
      - MODEL_DIR=/data
      - URI=tcp://0.0.0.0:10200
      - DEVICE=cuda
      - HALF=true
      - PRELOAD=true
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: 1
              capabilities: [gpu]
    restart: unless-stopped

  glados-tts-rocm:
    image: xerotacovix/glados-ladosp-tts:rocm
    container_name: glados-tts-rocm
    ports:
      - "10202:10200"
    environment:
      - MODEL_DIR=/data
      - URI=tcp://0.0.0.0:10200
      - DEVICE=rocm
      - HALF=true
      - PRELOAD=true
      - MIOPEN_FIND_MODE=1
      - MIOPEN_DEBUG_CONV_GEMM=0
    devices:
      - /dev/kfd
      - /dev/dri
    volumes:
      - glados_model_cache:/data
      - glados_hf_cache:/root/.cache/huggingface
      - glados_nltk_data:/root/nltk_data
      - glados_miopen_cache:/root/.cache/miopen
    restart: unless-stopped

volumes:
  glados_model_cache:
  glados_hf_cache:
  glados_nltk_data:
  glados_miopen_cache: