Home Projects stable-fast
stable-fast
Python

stable-fast

https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

by chengzeyi · GitHub
Stars
Forks
License
Created
Last commit
Category
Language
cudadeeplearnngdiffusersMITPython
View on GitHub
In plain words

Optimize the performance of AI models running on NVIDIA GPUs with stable-fast.

You maintain this project?

Claim its page: indexed whatever its rank, translated into six languages, and enriched with what you write yourself.

Claim this page →
stable-fast — GitHub preview card
📈 Star history
1.31k1.30k
2026-07-202026-08-31
📈 Track stable-fast

Get an email alert on its next release or when it starts trending — never miss the moment.

Free · no card · unsubscribe anytime
Get email alerts →
📄 About

https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

stable-fast has 1.3k stars on GitHub. It has been forked 92 times. stable-fast is written mainly in Python. It has been in active development since 2023. stable-fast is available under the MIT license. Its main topics are cuda, deeplearnng, diffusers, inference-engines.

Frequently asked questions

What is stable-fast?

https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Is stable-fast open source?

stable-fast is an open-source project. It is released under the MIT license.

Is stable-fast free?

Yes. stable-fast is free and open source — you can use, modify and self-host it.

What license does stable-fast use?

stable-fast is available under the MIT license.

What language is stable-fast written in?

stable-fast is written mainly in Python.

🏅 Maintainer of this project?
olud.ai badge — stable-fast

Add this live badge to your README — your GitHub stars and directory rank, refreshed daily.

[![olud.ai](https://olud.ai/badge.php?tool=chengzeyi-stable-fast)](https://olud.ai/project/chengzeyi-stable-fast.html)
More badge options →
🧬 Shares DNA with🧬 View the DNA map →

Measured from GitHub topics shared by both projects, weighted by how rare each topic is.