Ju Hoon Park 0e95aa853e [From Single File] support from_single_file method for WanVACE3DTransformer (#11807) ...

* add `WandVACETransformer3DModel` in`SINGLE_FILE_LOADABLE_CLASSES`

* add rename keys for `VACE`

add rename keys for `VACE`

* fix typo

Sincere thanks to @nitinmukesh 🙇‍♂️

* support for `1.3B VACE` model

Sincere thanks to @nitinmukesh again🙇‍♂️

* update

* update

* Apply style fixes

---------

Co-authored-by: Dhruv Nair <dhruv.nair@gmail.com>
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>

2025-07-02 05:55:36 +02:00

..

bnb

reset deterministic in tearDownClass (#11785)

2025-07-01 10:06:54 +05:30

gguf

[From Single File] support from_single_file method for WanVACE3DTransformer (#11807)

2025-07-02 05:55:36 +02:00

quanto

enable group_offload cases and quanto cases on XPU (#11405)

2025-04-28 06:37:16 +05:30

torchao

TorchAO compile + offloading tests (#11697)

2025-06-27 18:31:57 +05:30

__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

fix invalid component handling behaviour in PipelineQuantizationConfig (#11750)

2025-06-20 07:54:12 +05:30

test_torch_compile_utils.py

TorchAO compile + offloading tests (#11697)

2025-06-27 18:31:57 +05:30

utils.py

enable 2 test cases on XPU (#11332)

2025-04-17 13:27:41 -10:00