services:
  qwen3-tts:
    image: vllm/vllm-omni:latest-aarch64
    container_name: qwen3-tts
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - VLLM_LOGGING_LEVEL=INFO
      - HF_HOME=/root/.cache/huggingface
    ports:
      - "8091:8091"
    volumes:
      - /home/guru/vllm/data/root:/root
      - ./deploy/qwen3_tts.yaml:/deploy/qwen3_tts.yaml:ro
      - ./entrypoint.sh:/entrypoint.sh:ro
    command: ["/bin/bash", "/entrypoint.sh"]
    restart: unless-stopped
    healthcheck:
      test: ["CMD", "curl", "-sf", "http://localhost:8091/health"]
      interval: 30s
      timeout: 10s
      retries: 5
      start_period: 120s