" Run WebGPU compute kernels drawn from real AI workloads directly on your hardware and earn a personalized card built for your device.

On top of that, we're open-sourcing hundreds of these WebGPU kernels, our first step toward making browser inference as fast as physically possible. Contributed results show how they perform across real hardware and help make them faster.

Benchmark your GPU: https://webgpu-kernels-fleet.hf.space/
Blog post: https://huggingface.co/blog/webgpu-kernels
Kernels: https://huggingface.co/webgpu-kernels/kernels "