Add experimental BF16 support for Metal and CUDA

[alvarobartt]

What does this PR do?

This PR adds experimental support for BF16 as a supported dtype on both Metal and CUDA, when the features metal and cuda are enabled, respectively. As candle natively supports BF16, and some recent models as https://huggingface.co/voyageai/voyage-4-nano (and all the other Voyage AI embedding models) default to BF16; support has been introduced to support such cases.

Warning

Support for BF16 is still experimental on both Metal and CUDA, whilst stable for Intel HPUs under the python feature, as it runs with a Python-based backend.

Additionally, this PR also updates the Rust version to 1.92.0 (latest stable) in rust-toolchain.toml, and removes the half crate as a dependency.

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?
• 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.
• Did you write any new necessary tests? If applicable, did you include or update the insta snapshots?

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.