Voxtral Realtime: enable bf16 for Metal backend with quantization#18358
Merged
manuelcandales merged 1 commit intorelease/1.2from Mar 20, 2026
Merged
Voxtral Realtime: enable bf16 for Metal backend with quantization#18358manuelcandales merged 1 commit intorelease/1.2from
manuelcandales merged 1 commit intorelease/1.2from
Conversation
…7845) The Metal AOTI backend already handles bf16 correctly (fp32 attention masks, fp32 RoPE upcast, dtype-agnostic KV caches and SDPA). Enable --dtype bf16 as the default recipe for Metal CI and update all documentation to recommend bf16 with fpa4w quantization. (cherry picked from commit 202c6af)
This was referenced Mar 20, 2026
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18358
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 143 PendingAs of commit aadf80e with merge base 8c0a60b ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
manuelcandales
approved these changes
Mar 20, 2026
pytorchbot
temporarily deployed
to
upload-benchmark-results
GitHub Actions
Inactive
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
3 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The Metal AOTI backend already handles bf16 correctly (fp32 attention
masks, fp32 RoPE upcast, dtype-agnostic KV caches and SDPA). Enable
--dtype bf16 as the default recipe for Metal CI and update all
documentation to recommend bf16 with fpa4w quantization.