Rethinking What to Cache in Few-Step Diffusion Transformers: Solver-Aware Target Selection
Diffusion Transformers (DiTs) can generate high-quality images and videos, but generating each sample requires multiple costly DiT forward passes. Two common ways to accelerate DiT sampling are step distillation, which reduces the number of sampling steps, and caching, which skips some DiT evaluations by reusing a tensor computed at an earlier step. Most caching methods decide in advance which…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
