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

..

tools

[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

__init__.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

component_config.py

fix: do not apply FP8 quant config to vision/audio encoders for pre-quantized checkpoints (#2702)

2026-04-14 13:52:32 +00:00

factory.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

gguf_config.py

[Core] Unified quantization framework (#1764)

2026-03-24 18:56:55 +08:00

inc_config.py

[AutoRound] Support Qwen Omni W4A16 quantization model (#2670)

2026-04-22 19:54:45 +08:00

int8_config.py

[Core] Unified quantization framework (#1764)

2026-03-24 18:56:55 +08:00

mxfp4_config.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

mxfp8_config.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