ParaAttention

chengzeyi

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

flux

View on GitHub

426 Stars

45 Forks

426 Watchers

Python Language

other License

100 SrcLog Score

Cost to Build

$547.9K

Market Value

$1.78M

How is this calculated?

Growth over time

3 data points · 2026-04-08 → 2026-04-22

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about ParaAttention

Question copied to clipboard

What is the chengzeyi/ParaAttention GitHub project? Description: "https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching". Written in Python. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone ParaAttention

Clone via HTTPS

git clone https://github.com/chengzeyi/ParaAttention.git

Clone via SSH

[email protected]:chengzeyi/ParaAttention.git

Download ZIP

Download master.zip

Found an issue?

Report bugs or request features on the ParaAttention issue tracker:

Open GitHub Issues

Similar to ParaAttention

nylas-mail react-starter-kit normalizr react-native-nw-react-calculator reactjs101 fluxible reactor-core redux-zero stockroom freezer react-waterfall undux delorean redux-api react-quick-tutorial nylas-mail microcosm dutier iOSDesignPatternSamples Flux.jl Gank reactor-netty almin fluorine typescript-fsa Store denormalizr smitty grox VueFlux