Draft
Conversation
5 tasks
This is due to the recent version bump on `tokenizers` from 0.21.1 to 0.21.4
e302d54 to
9387804
Compare
As for Python the support is not experimental, but rather the default dtype for Intel HPU
6b2da2e to
b83102a
Compare
3cfde35 to
c19087e
Compare
This was referenced Feb 7, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
This PR adds experimental support for BF16 as a supported dtype on Metal, when the features
candleandmetalare enabled. Ascandlenatively 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 Metal, whilst stable for Intel HPUs under the
pythonfeature, as it runs with a Python-based backend. And, work in progress for CUDA which requires bumpingcandleto latest and updatingcandle-extensionsaccordingly.Additionally, this PR also updates the Rust version to 1.92.0 (latest stable) in
rust-toolchain.toml, and removeshalfas unused.Before submitting
instasnapshots?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.