Jiangyun ZhuandHongsheng Liu 1c8fcf436f [Perf] replace torch's conv with vLLM's conv to fix torch 2.9 performance regression (#982) ...

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
Co-authored-by: Hongsheng Liu <liuhongsheng4@huawei.com>

2026-01-28 10:41:33 +08:00

..

__init__.py

[Model] Add Wan2.2 I2V and TI2V pipeline support (#329)

2025-12-25 16:45:13 +08:00

pipeline_wan2_2_i2v.py

[NFC] Remove redundant torch.no_grad in models and pipelines (#854)

2026-01-27 12:36:54 +00:00

pipeline_wan2_2_ti2v.py

[NFC] Remove redundant torch.no_grad in models and pipelines (#854)

2026-01-27 12:36:54 +00:00

pipeline_wan2_2.py

[NFC] Remove redundant torch.no_grad in models and pipelines (#854)

2026-01-27 12:36:54 +00:00

wan2_2_transformer.py

[Perf] replace torch's conv with vLLM's conv to fix torch 2.9 performance regression (#982)

2026-01-28 10:41:33 +08:00