Загрузка видео...
Не удалось загрузить видео
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 просмотров • 1 месяц назад •via X (Twitter)
Комментарии: 7

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

Julien Blanchon 🇺🇦1 месяц назад
I guess this is forward only, no backward ?

Zack Fitch1 месяц назад
WebGPU is life

Jens Fursund1 месяц назад
Oooh super nice!

soulblocks1 месяц назад
Oh damn 🔥

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

Harsha1 месяц назад
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?

