Repository files navigation

We are excited to announce that thefirst API-stable version (v1.0.0) of cache-dit has finally been released!cache-dit is aUnified andFlexible Inference Engine for 🤗Diffusers, enabling acceleration with just♥️one line♥️ of code. Key features:Unified Cache APIs,Forward Pattern Matching,Automatic Block Adapter,DBCache,DBPrune,Hybrid TaylorSeer Calibrator,Hybrid Cache CFG,Context Parallelism,Tensor Parallelism,Torch Compile Compatible and🎉SOTA performance.

pip3 install -U cache-dit# pip3 install git+https://github.com/vipshop/cache-dit.git

You can install the stable release of cache-dit from PyPI, or the latest development version from GitHub. Then try♥️ Cache Acceleration with justone line of code ~♥️

>>>importcache_dit>>>fromdiffusersimportDiffusionPipeline>>>pipe=DiffusionPipeline.from_pretrained("Qwen/Qwen-Image")# Can be any diffusion pipeline>>>cache_dit.enable_cache(pipe)# One-line code with default cache options.>>>output=pipe(...)# Just call the pipe as normal.>>>stats=cache_dit.summary(pipe)# Then, get the summary of cache acceleration stats.>>>cache_dit.disable_cache(pipe)# Disable cache and run original pipe.

• 🎉Full 🤗Diffusers Support: Notably,cache-dit now supports nearlyall of Diffusers'DiT-based pipelines, include30+ series, nearly100+ pipelines, such as FLUX.1, Qwen-Image, Qwen-Image-Lightning, Wan 2.1/2.2, HunyuanImage-2.1, HunyuanVideo, HiDream, AuraFlow, CogView3Plus, CogView4, CogVideoX, LTXVideo, ConsisID, SkyReelsV2, VisualCloze, PixArt, Chroma, Mochi, SD 3.5, DiT-XL, etc.
• 🎉Extremely Easy to Use: In most cases, you only needone line of code:cache_dit.enable_cache(...). After calling this API, just use the pipeline as normal.
• 🎉Easy New Model Integration: Features likeUnified Cache APIs,Forward Pattern Matching,Automatic Block Adapter,Hybrid Forward Pattern, andPatch Functor make it highly functional and flexible. For example, we achieved 🎉 Day 1 support forHunyuanImage-2.1 with 1.7x speedup w/o precision loss—even before it was available in the Diffusers library.
• 🎉State-of-the-Art Performance: Compared with algorithms including Δ-DiT, Chipmunk, FORA, DuCa, TaylorSeer and FoCa, cache-dit achieved theSOTA performance w/7.4x↑🎉 speedup on ClipScore!
• 🎉Support for 4/8-Steps Distilled Models: Surprisingly, cache-dit'sDBCache works for extremely few-step distilled models—something many other methods fail to do.
• 🎉Compatibility with Other Optimizations: Designed to work seamlessly with torch.compile, Quantization (torchao,🔥nunchaku), CPU or Sequential Offloading,🔥Context Parallelism,🔥Tensor Parallelism, etc.
• 🎉Hybrid Cache Acceleration: Now supports hybridBlock-wise Cache + Calibrator schemes (e.g., DBCache or DBPrune + TaylorSeerCalibrator). DBCache or DBPrune acts as theIndicator to decidewhen to cache, while the Calibrator decideshow to cache. More mainstream cache acceleration algorithms (e.g., FoCa) will be supported in the future, along with additional benchmarks—stay tuned for updates!
• 🤗Diffusers Ecosystem Integration: 🔥cache-dit has joined the Diffusers community ecosystem as thefirst DiT-specific cache acceleration framework! Check out the documentation here:

🔥Click here to show manyImage/Video cases🔥

🎉Now, cache-dit covers almost All Diffusers' DiT Pipelines🎉
🔥Qwen-Image |Qwen-Image-Edit |Qwen-Image-Edit-Plus 🔥
🔥FLUX.1 |Qwen-Image-Lightning 4/8 Steps | Wan 2.1 | Wan 2.2🔥
🔥HunyuanImage-2.1 |HunyuanVideo |HunyuanDiT |HiDream |AuraFlow🔥
🔥CogView3Plus |CogView4 |LTXVideo |CogVideoX |CogVideoX 1.5 |ConsisID🔥
🔥Cosmos |SkyReelsV2 |VisualCloze |OmniGen 1/2 |Lumina 1/2 |PixArt🔥
🔥Chroma |Sana |Allegro |Mochi |SD 3/3.5 |Amused | ... |DiT-XL🔥

🔥Wan2.2 MoE |+cache-dit:2.0x↑🎉 |HunyuanVideo |+cache-dit:2.1x↑🎉

🔥Qwen-Image |+cache-dit:1.8x↑🎉 |FLUX.1-dev |+cache-dit:2.1x↑🎉

🔥Qwen...Lightning |+cache-dit:1.14x↑🎉 |HunyuanImage |+cache-dit:1.7x↑🎉

🔥Qwen-Image-Edit | Input w/o Edit | Baseline |+cache-dit:1.6x↑🎉 | 1.9x↑🎉

🔥FLUX-Kontext-dev | Baseline |+cache-dit:1.3x↑🎉 | 1.7x↑🎉 | 2.0x↑ 🎉

🔥HiDream-I1 |+cache-dit:1.9x↑🎉 |CogView4 |+cache-dit:1.4x↑🎉 | 1.7x↑🎉

🔥CogView3 |+cache-dit:1.5x↑🎉 | 2.0x↑🎉|Chroma1-HD |+cache-dit:1.9x↑🎉

🔥Mochi-1-preview |+cache-dit:1.8x↑🎉 |SkyReelsV2 |+cache-dit:1.6x↑🎉

🔥VisualCloze-512 | Model | Cloth | Baseline |+cache-dit:1.4x↑🎉 | 1.7x↑🎉

🔥LTX-Video-0.9.7 |+cache-dit:1.7x↑🎉 |CogVideoX1.5 |+cache-dit:2.0x↑🎉

🔥OmniGen-v1 |+cache-dit:1.5x↑🎉 | 3.3x↑🎉 |Lumina2 |+cache-dit:1.9x↑🎉

🔥Allegro |+cache-dit:1.36x↑🎉 |AuraFlow-v0.3 |+cache-dit:2.27x↑🎉

🔥Sana |+cache-dit:1.3x↑🎉 | 1.6x↑🎉|PixArt-Sigma |+cache-dit:2.3x↑🎉

🔥PixArt-Alpha |+cache-dit:1.6x↑🎉 | 1.8x↑🎉|SD 3.5 |+cache-dit:2.5x↑🎉

🔥Asumed |+cache-dit:1.1x↑🎉 | 1.2x↑🎉 |DiT-XL-256 |+cache-dit:1.8x↑🎉
♥️ Please consider to leave a⭐️ Star to support us ~♥️

For more advanced features such asUnified Cache APIs,Forward Pattern Matching,Automatic Block Adapter,Hybrid Forward Pattern,Patch Functor,DBCache,DBPrune,TaylorSeer Calibrator,Hybrid Cache CFG,Context Parallelism andTensor Parallelism, please refer to the🎉User_Guide.md for details.

• ⚙️Installation
• 🔥Supported DiTs
• 🔥Benchmarks
• 🎉Unified Cache APIs
  • 📚Forward Pattern Matching
  • 📚Cache with One-line Code
  • 🔥Automatic Block Adapter
  • 📚Hybrid Forward Pattern
  • 📚Implement Patch Functor
  • 📚Transformer-Only Interface
  • 📚How to use ParamsModifier
  • 🤖Cache Acceleration Stats
• ⚡️DBCache: Dual Block Cache
• ⚡️DBPrune: Dynamic Block Prune
• ⚡️Hybrid Cache CFG
• 🔥Hybrid TaylorSeer Calibrator
• ⚡️Hybrid Context Parallelism
• ⚡️Hybrid Tensor Parallelism
• 🤖Low-bits Quantization
• 🛠Metrics Command Line
• ⚙️Torch Compile
• 📚API Documents

How to contribute? Star ⭐️ this repo to support us or checkCONTRIBUTE.md.

Here is a curated list of open-source projects integratingCacheDiT, including popular repositories likejetson-containers,flux-fast, andsdnext. 🎉CacheDiT has beenrecommended by:Wan 2.2,Qwen-Image-Lightning,Qwen-Image,LongCat-Video,Kandinsky-5,🤗diffusers andHelloGitHub, among others.

Special thanks to vipshop's Computer Vision AI Team for supporting document, testing and production-level deployment of this project.

@misc{cache-dit@2025,title={cache-dit: A Unified and Flexible Inference Engine with Hybrid Cache Acceleration and Parallelism for Diffusers.},url={https://github.com/vipshop/cache-dit.git},note={Open-source software available at https://github.com/vipshop/cache-dit.git},author={DefTruth, vipshop.com},year={2025}}