Preparing for system design interviews?  Try bugzed.com →

Cache-DiT

JSON →
library 1.3.5 ·python
verified Jun 28, 2026

Cache-DiT is a PyTorch-native inference engine designed for Diffusion Transformers (DiTs). It provides hybrid cache acceleration (DBCache, TaylorSeer, SCM), comprehensive parallelism optimizations (Context, Tensor, 2D/3D), and low-bit quantization (FP8, INT8, INT4). The library integrates seamlessly with Hugging Face Diffusers, SGLang Diffusion, vLLM-Omni, and ComfyUI to deliver significant speedups for image and video generation. Currently at version 1.3.5, it maintains an active release cadence with frequent updates and hotfixes.

total hits 159
actors 7 distinct systems
last hit 16d ago human
ByteDance
10
NewsAI
1
Script
1
ChatGPT-User
1
PerplexityBot
1
Search engines
1
Humans
140

top countries 🇺🇸 United States · 🇸🇬 Singapore · VN · BD · 🇨🇦 Canada