andrewor14 24b4c259fb Remove references to torchao's AffineQuantizedTensor (#13405) ...

**Summary:** TorchAO recently deprecated AffineQuantizedTensor
and related classes (https://github.com/pytorch/ao/issues/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

Co-authored-by: Sayak Paul <spsayakpaul@gmail.com>

2026-04-06 20:41:26 +02:00

..

bnb

Remove 8bit device restriction (#12972)

2026-01-14 20:33:30 +05:30

gguf

[WIP]Add Wan2.2 Animate Pipeline (Continuation of #12442 by tolgacangoz) (#12526)

2025-11-12 16:52:31 -10:00

modelopt

[Quantization] Add TRT-ModelOpt as a Backend (#11173)

2025-09-03 10:14:52 +05:30

quanto

[CI] Remove big accelerator requirements from Quanto Tests (#12266)

2025-09-03 08:29:31 +05:30

torchao

Remove references to torchao's AffineQuantizedTensor (#13405)

2026-04-06 20:41:26 +02:00

__init__.py

[Tests] improve quantization tests by additionally measuring the inference memory savings (#11021)

2025-03-10 21:42:24 +05:30

test_pipeline_level_quantization.py

[quant] allow components_to_quantize to be a non-list for single components (#12234)

2025-09-10 09:47:08 -10:00

test_torch_compile_utils.py

[Refactor] Move testing utils out of src (#12238)

2025-08-28 19:53:02 +05:30

utils.py

[Refactor] Move testing utils out of src (#12238)

2025-08-28 19:53:02 +05:30