---
title: "WebGPU"
description: "3 posts about WebGPU, summarised, each linking to the original."
---

# WebGPU
> 3 posts about WebGPU, summarised, each linking to the original.

## Articles

### [Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI](https://yomu.fyi/post/introducing-huggingface-kernels-200-webgpu-kernels-for-local-ai.md)
- Company: [Hugging Face](https://yomu.fyi/company/hugging-face.md)
- Author: Nico Martin, Joshua
- Published: Sep 1, 2026
- Type: Announcement

Hugging Face’s WebAI team is releasing @huggingface/kernels, a JavaScript loader for optimized WebGPU kernels hosted on the Hub, alongside an initial collection of 207 Apache-2.0 kernels. Each kernel repository packages a versioned contract, metadata, correctness cases, benchmark cases, and parameterized WGSL shader templates, while the loader derives outputs and selects variants for a request and device. Fleet adds browser-based correctness and performance testing, with consent-based private evidence used to identify failures, compare variants, and guide optimization. In comparisons against ORT WebGPU on an Apple M4, matching cases showed a 2.57x geometric-mean speedup and a 1.90x median speedup, though the measurements cover individual GPU operations and exclude setup costs. The project is also intended as a shared foundation for browser inference and future integration with higher-level tooling.


### [LiteRT.js, Google's high performance Web AI Inference](https://yomu.fyi/post/litert-js-google-s-high-performance-web-ai-inference.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Ping Yu, Marko Ristić, Matthew Soulanille, Chintan Parikh
- Published: Jul 9, 2026
- Type: Announcement

Google announces LiteRT.js, a JavaScript binding of LiteRT that runs .tflite AI and ML models directly in web browsers. It targets local inference for JavaScript and TypeScript applications, with privacy benefits, zero server costs, and low latency, while providing smoother deployment for existing .tflite models. Through WebAssembly, it exposes LiteRT’s optimized runtime across XNNPACK CPU, ML Drift with WebGPU, and experimental WebNN for NPUs; LiteRT Torch supports one-step PyTorch conversion, and AI Edge Quantizer enables layer-specific quantization. The initial release includes the @litertjs/core npm package, demos, and examples covering YOLO26, depth estimation, and Real-ESRGAN upscaling. In controlled benchmarks on a 2024 Apple MacBook Pro with M4, it outperformed other web runtimes by up to 3x, while WebGPU or WebNN delivered 5–60x speedups over CPU execution; results may vary with hardware, thermal conditions, and browser drivers.


### [Blazing fast on-device GenAI with LiteRT-LM](https://yomu.fyi/post/blazing-fast-on-device-genai-with-litert-lm.md)
- Company: [Google](https://yomu.fyi/company/google.md)
- Author: Tenghui Zhu, Yu-hui Chen, Ram Iyengar
- Published: May 19, 2026
- Type: Announcement

LiteRT-LM is presented as an on-device runtime for deploying Gemma 4 across Android, iOS, and the web despite constrained memory, limited compute, and varied hardware. It combines LiteRT inference, quantization, XNNPACK and MLDrift kernels, CPU/GPU/NPU backends, transfer-avoiding pipelines, Multi-Token Prediction (MTP), and session management. Reported decode rates reach 52 tokens/sec on Android GPU, 56 on iOS Metal, and up to 76 on WebGPU; MTP provides up to a 2.2x speedup, while a ~2.58GB E2B model uses 607MB of physical memory on Apple mobile CPUs. The runtime also supports save/restore of KV caches, native vision and audio loading, Thinking Mode, constrained decoding, and function calling. New Swift and JavaScript APIs extend the integration surface, including WASM/WebGPU browser inference designed for serverless, secure, privacy-preserving applications.