software-mansion /
runntime
High-performance neural networks engine for web, built on top of TypeGPU
Updated 57 min ago
Why now
Version v0.2.0 came out on October 29.
+15 stars gained this week
Stars gained each day, last 30 days
Usual pace · 1 / day
Oct 4Oct 19Today
This week Before Usual pace
In short
ruNNtime runs AI models such as speech, vision and language models directly on the user's GPU in the browser, React Native or Electron, using TypeGPU kernels compiled to WGSL. It is aimed at developers who want ready-to-use model APIs without shipping WASM binaries.
Summary written by AI from the repository’s description and README.
software-mansion / runntime
View on GitHub(opens in new tab)