GitHub · Python
vipshop/cache-dit
A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.
- Stars
- 1,308
- Forks
- 95
- Stars gained in 24 hours
- 0
- Forks gained in 24 hours
- 0
Topics: flux2-klein, svdquant, flux3, flux3-klein, qwen-image-2-1, minimax-h3, minimax-h3-image
Latest data point: Nov 22, 2026 · 1,308 stars · 95 forks