Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.
| Date | Stars |
|---|---|
| 2026-07-31 | 1240 |
| 2026-08-01 | 1240 |
| 2026-08-06 | 1240 |
| 2026-08-11 | 1245 |
| 2026-08-18 | 1250 |
| 2026-08-20 | 1251 |
| 2026-08-21 | 1252 |
| 2026-08-22 | 1253 |
| 2026-08-23 | 1255 |
| 2026-08-24 | 1257 |
| 2026-08-26 | 1259 |
| 2026-08-27 | 1260 |
| 2026-08-28 | 1260 |
| 2026-08-29 | 1262 |
| 2026-09-01 | 1264 |
| 2026-09-02 | 1267 |
| 2026-09-03 | 1269 |
| 2026-09-04 | 1270 |
| 2026-09-05 | 1273 |
| 2026-09-06 | 1273 |
| 2026-09-07 | 1273 |
| 2026-09-08 | 1274 |
| 2026-09-09 | 1276 |
| 2026-09-10 | 1275 |
| 2026-09-11 | 1275 |
| 2026-09-14 | 1275 |
| 2026-09-15 | 1277 |
| 2026-09-16 | 1279 |
| 2026-09-17 | 1281 |
| 2026-09-18 | 1282 |
| 2026-09-20 | 1282 |
Today
— stars today
This week
+7 stars this week
This month
+30 stars this month
Momentum
42.0
growth rate 0.55%/day
<div align="center">
<p align="center">
<h2 align="center">
<img src=https://github.com/vipshop/cache-dit/raw/main/assets/cache-dit-logo-v2.png width=185px align="left">
⚡️🎉A PyTorch-native Inference Engine with Cache, <br>Parallelism, Quantization and CPU Offload for DiTs<br>
<a href="https://pepy.tech/projects/cache-dit"><img src=https://static.pepy.tech/personalized-badge/cache-dit?period=total&units=ABBREVIATION&left_color=GRAY&right_color=BLUE&left_text=downloads/pypi ></a>
<a href="https://pypi.org/project/cache-dit/"><img src=https://img.shields.io/github/release/vipshop/cache-dit.svg?color=GREEN ></a>
<img src="https://img.shields.io/github/license/vipshop/cache-dit.svg?color=blue">
<a href="https://cache-dit.readthedocs.io/en/latest/COMMUNITY/"><img src=https://img.shields.io/badge/🤗-Community-orange.svg ></a>
<a href="https://hellogithub.com/repository/vipshop/cache-dit" target="_blank"><img src="https://api.hellogithub.com/v1/widgets/recommend.svg?rid=b8b03b3b32a449ea84cfc2b96cd384f3&claim_uid=ofSCbzTmdeQk3FD&theme=small" alt="Featured｜HelloGitHub" /></a>
</h2>
</p>
</div>
**🤗Why Cache-DiT❓❓**Cache-DiT is built on top of the 🤗[Diffusers](https://github.com/huggingface/diffusers) library and now supports nearly [ALL](https://cache-dit.readthedocs.io/en/latest/supported_matrix/NVIDIA_GPU/) DiTs from Diffusers. It provides [hybrid cache acceleration](https://cache-dit.readthedocs.io/en/latest/user_guide/CACHE_API/) (DBCache, TaylorSeer, SCM, etc.) and comprehensive [parallelism](https://cache-dit.readthedocs.io/en/latest/user_guide/CONTEXT_PARALLEL/) optimizations, including Context Parallelism, Tensor Parallelism, hybrid 2D or 3D parallelism, and dedicated extra parallelism support for Text Encoder, VAE, and ControlNet.
<div align="center">
<img src=https://github.com/vipshop/cache-dit/raw/main/assets/arch_v2.png width=815px>
</div>
Cache-DiT is compatible with compilation, CPU Offloading, and quantization, fully integrates with [SGLang Diffusion](https://docs.sglang.io/diffusion/performance/cache/cache_dit.html), [vLLM-Omni](https://docs.vllm.ai/projects/vllm-omni/en/latest/user_guide/diffusion/cache_acceleration/cache_dit/), [TensorRT-LLM](https://github.com/NVIDIA/TensorRT-LLM/pull/12548), ComfyUI, and runs natively on NVIDIA GPUs, Ascend NPUs and AMD GPUs. Cache-DiT is **fast**, **easy to use**, and **flexible** for various DiTs (online docs at 📘[cache-dit.io](https://cache-dit.readthedocs.io/en/latest/), tech report at 📘[paper](docs/papers/cache-dit-tech-report.pdf)).
<div align="center">
<p align="center">
<i>⚡️9x speedup by Cache-DiT with Cache, Context Parallelism and Compilation</i>
</p>
<img src=https://github.com/vipshop/cache-dit/raw/main/assets/speedup_v5.png width=800px>
</div>
## 📋Supported DiT Models
Cache-DiT supports **40+ DiT pipeline families (120+ Variants)** from 🤗Diffusers, covering the vast majority of DiT-based pipelines. For full support matrix and detailed usage, please refer to our documentation at 📘[cache-dit.io](https://cache-dit.readthedocs.io/en/latest/).
<div align="center">
| Modality | Pipeline Series | Transformer | Variants | C/P/Q/OF |
|:----------|:----------------|:-------------|:----------|:-------|
| **Image** | FLUX | [`FluxTransformer2DModel`](src/cache_dit/caching/block_adapters/adapters.py) | 10+ | ✔️/✔️/✔️/✔️ |
| Image | FLUX.2 | [`Flux2Transformer2DModel`](src/cache_dit/caching/block_adapters/adapters.py) | 1 | ✔️/✔️/✔️/✔️ |
| Image | FLUX.2 Klein | [`Flux2Transformer2DModel`](src/cache_dit/caching/block_adapters/adapters.py) | 3 | ✔️/✔️/✔️/✔️ |
| Image | ERNIE-Image | [`ErnieImageTransformer2DModel`](src/cache_dit/caching/block_adapters/adapters.py) | 1 | ✔️/✔️/✔️/✔️ |
| Image | Qwen-Image | [`QwenImageTransformer2DModel`](src/cache_dit/caching/block_adapters/adapters.py) | 9+ | ✔️/✔️/✔️/✔️ |
| Image | Z-Image | [`ZImageTransformer2DModel`](src/cache_dit/caching/block_adapters/adaptersExcerpt of 13,227 characters
Read on GitHub
DefTruth · @xlite-dev, @vipshop · China
1.1k
Xiaoyu Zhang · RadixArk
43
G.O.D · China
23
8
triple-mu · China
7
4
1
1
1
Johnny · NVIDIA · Spain
1
1
Samit · HKUST · Hong Kong
1
1
Krishi Attri
1
1
cheng peng
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:0d69e64f658d13ae, desc:inference engine