Loading video...
Video Failed to Load
We just open-sourced the world's fastest WebGPU kernels for 200+ machine learning operations. Specialized for your hardware. They run entirely locally in your browser. Now available on Hugging Face 🤗 Tell your agent to use @huggingface/kernels in your next project.
21,791 views • 1 month ago •via X (Twitter)
7 Comments

Xenova1 month ago
We're also working to upstream these optimizations to Transformers.js, ONNX Runtime Web, LiteRT.js, and more! Kernels: Blog:

Julien Blanchon 🇺🇦1 month ago
I guess this is forward only, no backward ?

Zack Fitch1 month ago
WebGPU is life

Jens Fursund1 month ago
Oooh super nice!

soulblocks1 month ago
Oh damn 🔥

banzaan1 month ago
browser is turning into an entire os running local models there changes everything wild drop

Harsha1 month ago
local kernels make the browser a more interesting compute boundary. i'd love a demo where the model runs on private input locally and the agent gets only the result it needs. how much of the workflow can stay inside that boundary?

