Remove references to torchao's AffineQuantizedTensor - #45321
Open
andrewor14 wants to merge 2 commits into
Open
andrewor14 wants to merge 2 commits into
andrewor14 wants to merge 2 commits into
Conversation
Contributor
Author
|
Hi @SunMarc can you help review this? |
Contributor
|
also cc @MekkCyber |
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 transformers before then. Test Plan: ``` python -m pytest -s -v tests/quantization/torchao_integration/test_torchao.py ```
jerryzh168
approved these changes
Apr 8, 2026
andrewor14
added a commit
to andrewor14/peft
that referenced
this pull request
Apr 8, 2026
**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 peft before then. Similar to: - huggingface/diffusers#13405 - huggingface/transformers#45321 **Test Plan:** CI
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: torchao_integration |
|
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. |
SunMarc
enabled auto-merge
April 9, 2026 13:24
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Apr 9, 2026
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Apr 9, 2026
github-merge-queue
Bot
removed this pull request from the merge queue due to failed status checks
Apr 9, 2026
6 tasks
guarin
pushed a commit
to guarin/transformers
that referenced
this pull request
Aug 5, 2026
…7797) torchao removed the torchao/dtypes package (AffineQuantizedTensor and the Layout classes). This updates the transformers torchao integration to stop importing from torchao.dtypes so it no longer crashes against current torchao, mirroring the approach in transformers huggingface#45321. Changes: - integrations/torchao.py: drop the `_quantization_type` helper and its `from torchao.dtypes import AffineQuantizedTensor` isinstance branch; `_linear_extra_repr` now detects quantized weights inline via `isinstance(self.weight, TorchAOBaseTensor)` (from torchao.utils). - tests/quantization/torchao_integration/test_torchao.py: replace the `from torchao.dtypes import AffineQuantizedTensor` import with `from torchao.utils import TorchAOBaseTensor` and update the isinstance assertions accordingly. - docs/source/en/quantization/torchao.md: remove the MarlinSparseLayout ("int4-weight-only-24sparse") examples and migrate the Int4CPULayout example to `Int4WeightOnlyConfig(int4_packing_format=PLAIN_INT32)`. Test plan: - `python -c "import transformers.integrations.torchao"` imports cleanly. - `RUN_SLOW=1 pytest tests/quantization/torchao_integration/test_torchao.py`: all 18 TorchAOBaseTensor isinstance / FqnToConfig tests pass. The 3 remaining failures (test_int4wo_quant, test_int4wo_offload, test_serialization_accelerator_*_Int4WeightOnlyConfig) are pre-existing generation-output text comparisons pinned to torchao int4 kernel numerics on the test hardware, unrelated to this change. Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This branch has not been deployed
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
5 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 transformers before then.
Test Plan: