What would you like to be added:

https://github.com/run-ai/runai-model-streamer is a library helps to load tensors from source to the GPU memory directly, we may integrate with this project to accelerate model loading from s3 like object store.

part of #119

Why is this needed:

Completion requirements:

This enhancement requires the following artifacts:

• Design doc
• API change
• Docs update

The artifacts should be linked in subsequent comments.