A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for 100+ DiTs.
- flux2-klein
- svdquant
- flux3
- flux3-klein
89,572 visible repositories in the index
1–1 of 1 · Most stars
A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for 100+ DiTs.