https://github.com/mit-han-lab/nunchaku/pull/113


Add dynamic Caching when batch_size = 1 for flux model by ita9naiwa · Pull Request #113 · mit-han-lab/nunchaku#105 Hi, this pr introduces ParaAttention's dynamic caching during diffusion process. I implement only for flux model, but it is not that difficult to extend to other models, so I want to ask m...github.com



Diffusion inference에 Dynamic Caching 추가해달라고 https://carpedm20.github.io/ 이 아저씨한테 퀘스트를 받아서 



했음


ㅇㅅㅇ