hxhhhlalalaandhyh_hh 9dd36e3afd [NPU][Quant] Add W4A4 MXFP4 online & MXFP4 dual-scale online/offline quantization support for Wan2.2 T2V / I2V inference on Ascend NPU (#3578) ...

Signed-off-by: hyh_hh <huyinghong1@huawei.com>
Co-authored-by: hyh_hh <huyinghong1@huawei.com>

2026-05-20 06:21:29 +00:00

..

__init__.py

[Model] feat: FastGen DMD2-distilled Wan 2.1 pipelines (T2V, I2V) (#2749)

2026-04-20 21:21:43 +08:00

conftest.py

[Refactor] refactor wan2.2 diffuse && add ut (#2672)

2026-04-17 20:13:49 +08:00

test_create_transformer_quant.py

[NPU][Quant] Add W4A4 MXFP4 online & MXFP4 dual-scale online/offline quantization support for Wan2.2 T2V / I2V inference on Ascend NPU (#3578)

2026-05-20 06:21:29 +00:00

test_wan22_i2v_pipeline.py

[Enhancement]remove duplicate video preprocess in Wan2.2 pipeline (#2963)

2026-04-21 20:33:09 +08:00

test_wan22_pipeline_diffuse.py

[Refactor] refactor wan2.2 diffuse && add ut (#2672)

2026-04-17 20:13:49 +08:00

test_wan22_pipeline_helpers.py

[Refactor] refactor wan2.2 diffuse && add ut (#2672)

2026-04-17 20:13:49 +08:00

test_wan22_vace_pipeline.py

[Refactor] refactor wan2.2 diffuse && add ut (#2672)

2026-04-17 20:13:49 +08:00