name: followup-audio-asr
services:
  asr:
    image: ${ASR_IMAGE:?Run build-image.sh and init-env.py first}
    pull_policy: never
    container_name: followup-audio-asr
    restart: unless-stopped
    stop_grace_period: 660s
    init: true
    ports:
      - "127.0.0.1:8001:8000"
    environment:
      CUDA_VISIBLE_DEVICES: "0"
      VLLM_API_KEY: ${ASR_API_KEY:?Initialize the private .env first}
      HF_HUB_OFFLINE: "1"
      TRANSFORMERS_OFFLINE: "1"
      HF_HUB_DISABLE_TELEMETRY: "1"
      DO_NOT_TRACK: "1"
      VLLM_NO_USAGE_STATS: "1"
      OMP_NUM_THREADS: "4"
    volumes:
      - /home/www/qwen-vllm/asr/models/Qwen3-ASR-1.7B:/model:ro
    shm_size: "2gb"
    cap_drop: [ALL]
    security_opt: [no-new-privileges:true]
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              device_ids: ["1"]
              capabilities: [gpu]
    command:
      - /model
      - --served-model-name
      - Qwen/Qwen3-ASR-1.7B
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --dtype
      - bfloat16
      - --tensor-parallel-size
      - "1"
      - --gpu-memory-utilization
      - ${ASR_GPU_MEMORY_UTILIZATION:-0.15}
      - --max-num-seqs
      - "1"
      - --max-model-len
      - "32768"
      - --max-num-batched-tokens
      - "4096"
      - --shutdown-timeout
      - "600"
      - --enforce-eager
      - --no-enable-log-requests
    healthcheck:
      test: [CMD, python3, -c, "import urllib.request; urllib.request.urlopen('http://127.0.0.1:8000/health', timeout=5).read()"]
      interval: 20s
      timeout: 8s
      start_period: 180s
      retries: 6
    logging:
      driver: json-file
      options:
        max-size: "10m"
        max-file: "3"