services:
  vllm:
    image: ${VLLM_IMAGE:-vllm/vllm-openai:latest}
    container_name: ${VLLM_CONTAINER_NAME:-llm-vllm-text}
    restart: unless-stopped
    ipc: host
    ports:
      - "${VLLM_HOST_PORT:-8000}:8000"
    environment:
      HF_HOME: /root/.cache/huggingface
      HUGGING_FACE_HUB_TOKEN: ${HF_TOKEN:-}
    volumes:
      - ${HOST_MODELS_DIR:-/models}:/models
      - ${HOST_HF_CACHE_DIR:-/models/cache/huggingface}:/root/.cache/huggingface
    command:
      - --model
      - ${VLLM_MODEL_ID:-Qwen/Qwen3-4B-Instruct-2507}
      - --served-model-name
      - ${VLLM_SERVED_MODEL_NAME:-qwen3-4b-instruct}
      - --enable-lora
      - --max-loras
      - ${VLLM_MAX_LORAS:-1}
      - --lora-modules
      - ${VLLM_LORA_MODULES:-qwen3-4b-1c=/models/adapters/1c/qwen3-4b-1c-lora-v1}
      - --host
      - 0.0.0.0
      - --port
      - "8000"
      - --gpu-memory-utilization
      - ${VLLM_GPU_MEMORY_UTILIZATION:-0.90}
      - --max-model-len
      - ${VLLM_MAX_MODEL_LEN:-32768}
      - --dtype
      - ${VLLM_DTYPE:-auto}
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities:
                - gpu