Hugging Face open-sources 207 WebGPU kernels for in-browser AI inference

nicodotdev · x · 2026-09-01

Hugging Face ships @huggingface/kernels: 207 open-source WebGPU kernels loadable straight from the Hub. The author notes fast browser inference is a multi-layer effort — browser-friendly model formats, runtimes with efficient execution plans, and GPU kernels tuned for the browser — and this release provides the bottom layer.

Related event: Hugging Face open-sources 207 WebGPU kernels for faster browser inference(2 posts)→

Original post →

More from Infra

Infra channel →