def arctic_inference_plugin()

in arctic_inference/vllm/plugin.py [0:0]

• 19 lines of code
• 6 McCabe index (conditional complexity)

def arctic_inference_plugin():
    if not envs.ARCTIC_INFERENCE_ENABLED:
        print("\x1b[35;1mArctic Inference plugin is disabled. To enable, set "
              "ARCTIC_INFERENCE_ENABLED=1.\x1b[0m", file=sys.stderr)
        return

    if not envs.ARCTIC_INFERENCE_SKIP_VERSION_CHECK:
        compatible_version = get_compatible_vllm_version()
        if vllm.__version__ != compatible_version:
            raise RuntimeError(
                f"Arctic Inference plugin requires vllm=={compatible_version} "
                f"but found vllm=={vllm.__version__}!")
    
    if not envs.ARCTIC_INFERENCE_SKIP_PLATFORM_CHECK:
        if not vllm.platforms.current_platform.is_cuda():
            raise RuntimeError(
                f"Arctic Inference plugin requires the cuda platform!")

    print("\x1b[36;1mArctic Inference plugin is enabled!\x1b[0m",
          file=sys.stderr)

    # Lazy import to avoid potential errors when the plugin is disabled.
    from .patches import apply_arctic_patches
    apply_arctic_patches()