Fix group offloading for Flux2 VAE

[DN6]

What does this PR do?

Applying pipeline level group offloading to the Flux2 Autoencoder results in a device mismatch error because latents_bn_mean is moved to GPU in the pipeline but latents_bn_std is not.

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.

[asomoza]

@DN6 isn't this the same as #13299?

[DN6]

@asomoza Ah didn't see that. Closing in favour of #13299