hxhhhlalalaandhyh_hh a715abd447 [NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU (#3140) ...

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

2026-05-13 17:14:42 +08:00

..

__init__.py

Enable Wan2.2-S2V modeling to vLLM-omni (#2751)

2026-05-06 08:03:48 +08:00

patch_diffusers.py

[BugFix] Probe __dict__ instead of hasattr when patching WanRMS_norm (#3400)

2026-05-07 11:54:16 +08:00

pipeline_wan2_2_i2v.py

[NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU (#3140)

2026-05-13 17:14:42 +08:00

pipeline_wan2_2_s2v.py

Enable Wan2.2-S2V modeling to vLLM-omni (#2751)

2026-05-06 08:03:48 +08:00

pipeline_wan2_2_ti2v.py

[NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU (#3140)

2026-05-13 17:14:42 +08:00

pipeline_wan2_2_vace.py

[NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU (#3140)

2026-05-13 17:14:42 +08:00

pipeline_wan2_2.py

[NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU (#3140)

2026-05-13 17:14:42 +08:00

scheduling_wan_euler.py

[Model] Adapt Wan2.2-I2V-A14B via LightX2V offline conversion path (#2134)

2026-04-13 14:20:04 +08:00

wan2_2_s2v_transformer.py

Enable Wan2.2-S2V modeling to vLLM-omni (#2751)

2026-05-06 08:03:48 +08:00

wan2_2_transformer.py

[NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU (#3140)

2026-05-13 17:14:42 +08:00

wan2_2_vace_transformer.py

[NPU][Quant] Add W8A8 MXFP8 online/offline quantization support for Wan2.2 T2V / I2V / TI2V inference on Ascend NPU (#3140)

2026-05-13 17:14:42 +08:00