Fix: Resolve #3060, preload_module_classes is lost for nested modules

[wejoncy]

What does this PR do?

We ran into this issue when try to load VPTQ models by multiple devices, the VQLinear layer has embending as its sub-module. This function should move all constant buffers/parameters to the corresponding devices from Meta device.
So add_hook_to_module should pass preload_module_classes to the next recursive calling for the nested modules.

https://github.com/microsoft/VPTQ/blob/ac7258f461e214ca705f5895513f314576750528/vptq/layers/vqlinear.py#L160C18-L160C18

This PR is to fix #3060

• Big modeling: @SunMarc

[SunMarc]

LGTM ! Thanks for fixing ! Could you share which specific issue you where having ? Also if you can implement a test, it would be nice but not needed to merged this PR. You can fix the CI with make style

[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.

[muellerzr]

agreed with Marc, some more details to this issue and adding a test is needed.

[wejoncy]

Hi @muellerzr and @SunMarc Thanks for your review. I have briefly described the issue in overview of this PR.
And I will try to construct such a test case.

[muellerzr]

@wejoncy can you do make style; make quality? It'll fix the quality failure

[muellerzr]

Looks great to me, and fantastic test. Let's just fixup that quality then good to merge!