search

xdit-project / xDiT

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism
Apache License 2.0
720 stars 55 forks source link

How about quantized models? #344

Closed wxsms closed 1 week ago

wxsms commented 1 week ago

for example: https://github.com/mit-han-lab/nunchaku

can quantized models intergrated with xDiT? Thanks!