make big model inference compatible with torch.compile

[SunMarc]

What does this PR do ?

This PR makes big model inference compatible with torch.compile. To do that, we need to fix send_to_device.

In pytorch 2.2.1, hasattr is not implemented for TupleVariable, so we get an error in is_namedtuple function. I tried a few methods to not use hasattr but I didn't manage to make it work (e.g. try except block). If we bypass the is_namedtuple function, compile works fine. In pytorch nightly (future 2.4), this is implemented but we hit another error ( breaking changes ... ). So, I need to investigate more.

Fixes #2592
Draft for now to not forget

EDIT: Feel free to try this PR. It should work for the latest torch. However, it doesn't support namedtuple.

[HuggingFaceDocBuilderDev]

The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.

[Aknifejackzhmolong]

Hi, I've hit the exact same error. Any news on this?