Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI
Back to Articles a]:hidden"> Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI Published September 1, 2026 Update on GitHub Upvote 11 +5…
Summary
Back to Articles a]:hidden"> Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI Published September 1, 2026 Update on GitHub Upvote 11 +5 Nico Martin nico-martin Follow Joshua Xenova Follow:last-child]:mb-0"> One of our biggest goals on the WebAI team at Hugging Face is to make browser inference as fast and as user-friendly as possible. Getting there is a multi-layer effort: models need browser-friendly representations, runtimes need to build efficient execution plans, and the individual GPU operations at the bottom of the stack need to make the most of many different devices and browser implementations. Today, we are releasing the first layer of that effort: @huggingface/kernels, a minimal library for loading and running optimized WebGPU kernels from the Hugging Face Hub, together with an initial collection of 207 kernels at huggingface. The collection covers operations used across a wide variety of machine learning architectures and workloads.
Positives
- We are also launching Fleet, an in-browser GPU benchmarking and testing suite that runs and scores the kernels on your hardware.
Risks & concerns
- Getting there is a multi-layer effort: models need browser-friendly representations, runtimes need to build efficient execution plans, and the individual GPU operations at the bottom of the stack need to make the most of many different devices and browser implementations.