3 repos
Shenyi-Z/ToCa
[ICLR2025] Accelerating Diffusion Transformers with Token-wise Feature Caching
224
68 commits
macovaseas/ProCache
[AAAI 2026] Official implementation for "ProCache: Constraint-Aware Feature Caching with Selective…
6
22 commits
vipshop/cache-dit
A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.
1,282
1,183 commits
