William Lin 13583f5ffb [Model] Remove RMSNorm's forward_native hardcode from Wan (#339)

2025-04-14 16:46:43 -07:00

..

inference_hunyuan_hf_quantization.sh

adding hunyuan hf (support lora finetuning); unified hunyuan hf inference with quantization (#135)

2025-01-13 19:47:42 -08:00

inference_hunyuan_hf.sh

adding hunyuan hf (support lora finetuning); unified hunyuan hf inference with quantization (#135)

2025-01-13 19:47:42 -08:00

inference_hunyuan_STA.sh

Added multi-GPU support for Hunyuan STA (#211)

2025-02-21 14:16:28 -08:00

inference_hunyuan.sh

Added multi-GPU support for Hunyuan STA (#211)

2025-02-21 14:16:28 -08:00

inference_mochi_hf.sh

adding hunyuan hf (support lora finetuning); unified hunyuan hf inference with quantization (#135)

2025-01-13 19:47:42 -08:00

inference_stepvideo_STA.sh

[Feat] Add STA for StepVideo (#200)

2025-02-20 11:33:58 -08:00

inference_stepvideo.sh

[Feat] Add STA for StepVideo (#200)

2025-02-20 11:33:58 -08:00

v1_inference_hunyuan_STA.sh

Add torch sdpa backend to ssim test (#316)

2025-04-07 13:50:46 -07:00

v1_inference_hunyuan.sh

Add torch sdpa backend to ssim test (#316)

2025-04-07 13:50:46 -07:00

v1_inference_wan_i2v.sh

[Model] Remove RMSNorm's forward_native hardcode from Wan (#339)

2025-04-14 16:46:43 -07:00

v1_inference_wan.sh

[Model] Remove RMSNorm's forward_native hardcode from Wan (#339)

2025-04-14 16:46:43 -07:00