services:
  faster-qwen3-tts:
    image: faster-qwen3-tts-dgx-spark:v4
    container_name: faster-qwen3-tts
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - HF_TOKEN=${HF_TOKEN}
    ports:
      - "8020:8000"
    volumes:
      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-Base:/models/Qwen3-TTS:ro
      - /home/sparky/Docker/faster-qwen3-tts/config:/config:rw
      - /home/sparky/Projekte/TTS_Voices/speakers:/voices:ro
    command: >
      /bin/bash -c "
      python3 /config/generate_voices.py &&
      python3 /config/run_server.py
      --model /models/Qwen3-TTS
      --voices /config/voices.json
      --port 8000
      --max-seq-len 2048
      "
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - dgx_net

  faster-qwen3-tts-voicedesign:
    image: faster-qwen3-tts-dgx-spark:v4
    container_name: faster-qwen3-tts-voicedesign
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - HF_TOKEN=${HF_TOKEN}
    ports:
      - "8021:8000"
    volumes:
      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-VoiceDesign:/models/Qwen3-TTS-VoiceDesign:ro
      - /home/sparky/Docker/faster-qwen3-tts/config:/config:rw
    command: >
      /bin/bash -c "
      python3 /config/run_voicedesign_server.py
      --model /models/Qwen3-TTS-VoiceDesign
      --voices /config/voicedesign_voices.json
      --port 8000
      --max-seq-len 2048
      "
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - dgx_net

  qwen3-tts-streaming:
    image: qwen3-tts-streaming-dgx-spark:latest
    container_name: qwen3-tts-streaming
    restart: unless-stopped
    runtime: nvidia
    environment:
      - NVIDIA_VISIBLE_DEVICES=all
      - NVIDIA_DRIVER_CAPABILITIES=compute,utility
      - HF_TOKEN=${HF_TOKEN}
      - PYTHONUNBUFFERED=1
      - QWEN_TTS_MODEL=/models/Qwen3-TTS
      - QWEN_TTS_VOICES=/config/voices.json
      - QWEN_TTS_MAX_SEQ_LEN=4096
    ports:
      - "8023:8000"
    volumes:
      - /home/sparky/LLMs/vllm/Alibaba/Qwen3-TTS-12Hz-1.7B-Base:/models/Qwen3-TTS:ro
      - /home/sparky/Docker/faster-qwen3-tts/config:/config:rw
      - /home/sparky/Projekte/TTS_Voices/speakers:/voices:ro
    command: >
      /bin/bash -c "
      python3 /config/generate_voices.py &&
      python3 /config/run_server.py
      --model /models/Qwen3-TTS
      --voices /config/voices.json
      --port 8000
      --max-seq-len 4096
      "
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]
    networks:
      - dgx_net

networks:
  dgx_net:
    external: true