WebML at Hugging Face, Google Developer Expert, and a few years of conference stages behind me. The long version, plus what came before.
Who I amAI agents in the browser, K.I.T.T. in JavaScript, robots over Bluetooth, ... Every one with on-device live demos along the way.
See the talksSide projects, articles, videos, pictures and podcast appearances. Whatever I am currently building and exploring.
Have a lookOver the past few years, I’ve spoken at conferences and meetups across Europe, meeting brilliant people and happily nerding out about what browsers can do.
Nico Martin, open source ML engineer at Hugging Face, talks with Mike Grabowski on React Universe On Air about Transformers.js, WebGPU, browser agents and Hugging Face's upcoming WebGPU inference engine.
all open source on the Hugging Face Hub, plus @huggingface/kernels, a library that loads, validates, renders and runs them for you. This video walks through how it works: what an op is vs a kernel, why WGSL, and why we ship Jinja templates instead of fixed WGSL files. The browser picks the data types and workgroup sizes your device supports and builds the fastest kernel for that hardware. Then two demos built on top of it: an attention mechanism with the tinyBERT weights in ~20 lines of JavaScript, and a 1M+ cell wave animation driven by a single matmul kernel, capped only by requestAnimationFrame. Finally, Fleet: run the kernel benchmarks on your own GPU. The results help us optimize the kernels for the thousands of devices we can't test ourselves.
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.
