Conversation
|
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. |
Contributor
|
View the CircleCI Test Summary for this PR: https://huggingface.co/spaces/transformers-community/circle-ci-viz?pr=43145&sha=3cc7ed |
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: diffllama, falcon, falcon_mamba, gpt_neo, gptj, kyutai_speech_to_text, mimi, moshi, nemotron |
SangbumChoi
pushed a commit
to SangbumChoi/transformers
that referenced
this pull request
Jan 23, 2026
* fix regression * fix * fix * fix --------- Co-authored-by: Mohamed Mekkouri <93391238+MekkCyber@users.noreply.github.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
This PR fixes an issue with
configandquantization_config. Since we don't propagate thequantization_configinto subconfig, we don't cast the tensors to the correct dtype when using flash attn. However, I prefer not to propagate this information for now. Instead, we just set _is_quantized flag. In the past, we were using_pre_quantization_dtype.Fixes #43001
Regression caused by https://github.com/huggingface/transformers/pull/42882/files