This repository was archived by the owner on May 11, 2025. It is now read-only.
[core] Fix quantization issues with transformers==4.36.0
#249
Conversation
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
4 tasks
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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Outdated suggestions cannot be applied.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?
The recent transformers release that included a cache refactor: huggingface/transformers#26681 broke some internal assumptions in autoawq about the shapes of attention masks and input embeddings.
This PR fixes this issue by simply updating
layer_kwargsthanks to theprepare_inputs_for_generationmethod that automatically takes care of updating the inputs and attention masks in the correct format (should be also compatible with previous versions)cc @casper-hansen @TheBloke