services:
  llama-server:
    environment:
      NVIDIA_VISIBLE_DEVICES: "${LLAMA_SERVER_GPU_UUIDS:-all}"
      LLAMA_ARG_SPLIT_MODE: "${LLAMA_ARG_SPLIT_MODE:-none}"
      LLAMA_ARG_TENSOR_SPLIT: "${LLAMA_ARG_TENSOR_SPLIT:-}"
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              capabilities: [gpu]