Skip to main content

⚡️🎉A PyTorch-native Inference Engine with Cache,
Parallelism, Quantization and CPU Offload for DiTs
Featured|HelloGitHub

Cache-DiT is a PyTorch-native inference engine with cache acceleration (DBCache, TaylorSeers, FoCa, SCM, SVD-Cache, DMD-Cache, HiCache, etc), quantization (SVDQ/FP8/FP4/INT4), cpu offload and parallelism (CP/TP/USP/TE-P/VAE-P/2D-P/3D-P) for various DiTs and runs natively on NVIDIA GPUs, Huawei Ascend NPUs and AMD GPUs.

Cache-DiT is fast, easy to use, and flexible for various DiTs.

Cache-DiT is also compatible with torch.compile and fully integrates with SGLang Diffusion, vLLM-Omni, TensorRT-LLM, xDiT. Cache-DiT now supports 60+🎉 DiT pipeline families (150+🎉 Variants), covering the vast majority of DiTs. For full support matrix and detailed usage, please refer to our docs at 📘cache-dit.io.

🌐Community Integration

©️Acknowledgements

Special thanks to vipshop's Computer Vision AI Team for supporting testing and deployment of this project. We learned and reused codes from: Diffusers, SGLang, vLLM-Omni, Nunchaku, xDiT and TaylorSeer.

©️Citations

@misc{cache-dit@2025,
  title={Cache-DiT: A PyTorch-native Inference Engine with Cache, Parallelism, Quantization and CPU Offload for DiTs.},
  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, etc.},
  year={2025}
}

Metadata

Release files for cache-dit 1.5.6

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distribution (wheel)

Table of built distributions (wheels) for cache-dit 1.5.6
File Interpreter ABI Platform Actions
cache_dit-1.5.6-py3-none-any.whl Python 3 none any Details for cache_dit-1.5.6-py3-none-any.whl

Release files / cache_dit-1.5.6-py3-none-any.whl

Download URL cache_dit-1.5.6-py3-none-any.whl
Size 1.5 MB
Tags Python 3
SHA-256 checksum
How to use checksums
01c0edc22aac6e910cd33c5210d94d8cb9a67902f5806f83e0a63f67ece50e4e
BLAKE2b-256 checksum
How to use checksums
c559114d2238d0271bde5bb249f6ec28ad48ae34ac834789f064a0b3e3f2c500
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.13

Security for cache-dit 1.5.6

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Release history Release notifications | RSS feed

This release

1.5.6 This release

1 release file No provenance

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page