ModuleWrapperBase around a model object to enable serving at scale.
Create a Servable from either (LM, LOCATION) or (LOCATION,)
Parameters
*args¶ – A model class and path to the asset file (url or local file path) OR
a singular path to a torchscript asset which can be loaded without the
model class definition.
download_path¶ (Optional[Path]) – Optional url to download a model from.
To analyze traffic and optimize your experience, we serve cookies on this site. By clicking or navigating, you agree to allow our usage of cookies. Read PyTorch Lightning's Privacy Policy.