[Quantization] dtype fix for GGUF + fix BnB tests

[DN6]

What does this PR do?

Single File loading for GGUF was running into errors after the refactor to load_model_dict_into_meta with dtypes not being set correctly leading to errors seen below
https://github.com/huggingface/diffusers/actions/runs/14072732421/job/39410111086#step:7:351

This PR fixes those issues by adding the update_torch_dtype method to the single file model
Additionally fix a couple of BnB tests that were affected by changes related to adding XPU support in the CI.

Fixes # (issue)

Before submitting

• This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case).
• Did you read the contributor guideline?
• Did you read our philosophy doc (important for complex PRs)?
• Was this discussed/approved via a GitHub issue or the forum? Please add a link to it if that's the case.
• Did you make sure to update the documentation with your changes? Here are the
  documentation guidelines, and
  here are tips on formatting docstrings.
• 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.

[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.

[sayakpaul]

Thanks! Lot simpler than expected change in single file 🥲