bitsandbytes: upgrade and enable CUDA Graphs for 4bit by default

[matthewdouglas]

What does this PR do?

This PR sets the new minimum requirement for bitsandbytes to the most recent release, v0.45.0. from v0.43.0.

CUDA Graphs support for 4bit was enabled in v0.44.0, and as such this PR additionally turns this on by default for bitsandbytes-nf4 and bitsandbytes-fp4 quantization options.

The v0.45.0 release brings H100 compatibility for 8bit along with significant performance improvements.

Additionally, there are minor documentation changes, as well as some cleanup in Linear8bitLt and Linear4bit.

Fixes #2467, #780, #504

Before submitting

• [x] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• [x] Did you read the contributor guideline, Pull Request section?
• [ ] Was this discussed/approved via a Github issue or the forum? Please add a link to it if that's the case.
• [x] Did you make sure to update the documentation with your changes? Here are the documentation guidelines, and here are tips on formatting docstrings.
• [x] Did you write any new necessary tests?

Who can review?

Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR.

@OlivierDehaene @Narsil

cc: @Titus-von-Koeller

[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.

[matthewdouglas]

For reference, vLLM has upgraded to 0.45.0 and some benchmarks are located here.

[Narsil]

Hey I took a part of this PR (you are co-author) and merged it.

I took only the dep + removing the cuda graph. If some other changes are important, you create a new PR or modify this one, but please motivate them carefully.

[Narsil]

Closing tentatively feel free to reopen.