SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers

Liu et al. "SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.

[Liu et al. "SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2025.](https://mlanthology.org/cvprw/2025/liu2025cvprw-smoothcache/)

@inproceedings{liu2025cvprw-smoothcache,
  title     = {{SmoothCache: A Universal Inference Acceleration Technique for Diffusion Transformers}},
  author    = {Liu, Joseph and Geddes, Joshua and Guo, Ziyu and Jiang, Haomiao and Nandwana, Mahesh Kumar},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2025},
  pages     = {3229-3238},
  url       = {https://mlanthology.org/cvprw/2025/liu2025cvprw-smoothcache/}
}