Remove references to torchao's AffineQuantizedTensor#13405
Merged
sayakpaul merged 2 commits intohuggingface:mainfrom Apr 6, 2026
Merged
Remove references to torchao's AffineQuantizedTensor#13405sayakpaul merged 2 commits intohuggingface:mainfrom
sayakpaul merged 2 commits intohuggingface:mainfrom
Conversation
**Summary:** TorchAO recently deprecated AffineQuantizedTensor and related classes (pytorch/ao#2752). These will be removed in the next release. We should remove references of these classes in diffusers before then. **Test Plan:** python -m pytest -s -v tests/quantization/torchao/test_torchao.py
Contributor
Author
|
Hi @sayakpaul can you help review this? |
sayakpaul
reviewed
Apr 4, 2026
Comment on lines
136
to
142
| def _linear_extra_repr(self): | ||
| weight = _quantization_type(self.weight) | ||
| from torchao.utils import TorchAOBaseTensor | ||
|
|
||
| weight = self.weight.__class__.__name__ if isinstance(self.weight, TorchAOBaseTensor) else None | ||
| if weight is None: | ||
| return f"in_features={self.weight.shape[1]}, out_features={self.weight.shape[0]}, weight=None" | ||
| else: |
Contributor
Author
There was a problem hiding this comment.
Yeah should be, all new tensor subclasses are TorchAOBaseTensor
There was a problem hiding this comment.
There was a problem hiding this comment.
seems OK to make this function public as well
|
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. |
jerryzh168
approved these changes
Apr 6, 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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary: TorchAO recently deprecated AffineQuantizedTensor and related classes (pytorch/ao#2752). These will be removed in the next release. We should remove references of these classes in diffusers before then.
Test Plan:
python -m pytest -s -v tests/quantization/torchao/test_torchao.py