xDiT supports parallel inference of HunyuanDiT

[feifeibear]

We are excited to announce that our xDiT project, a DiT parallel inference engine, has recently added support for HunyuanDiT's parallel inference. By leveraging CFG Parallel and PipeFusion Parallel, HunyuanDiT achieves significant acceleration ratios even on PCIe-interconnected NPUs without NVLink.

https://github.com/xdit-project/xDiT https://github.com/xdit-project/xDiT/blob/main/examples/hunyuandit_example.py

We kindly request the authors to consider including a link to xDiT in the Accelerate section of the readme.

Thank you for your attention and consideration.