How Google Uses WebAssembly

We're excited to introduce LiteRT.js, the newest member of the LiteRT family! LiteRT.js is our powerful solution for running machine learning models directly in the browser, extending Google's cross-platform edge AI runtime to the web. Built for JavaScript developers, LiteRT.js delivers state-of-the-art ML model inference performance on WebGPU and upcoming WebNN, with a fallback to WebAssembly for CPU. This post provides a quick tour of LiteRT.js and gives web developers everything they need to get started.

The Web AI Summit 2024, hosted by Google on October 18, 2024, focused on client-side AI for developers, showcasing how machine learning models can operate offline in web browsers.

The article discusses the development of 'Purrfect Code', a programming puzzle game designed for developers, using Flutter, Dart, and the Flame game engine.

The article discusses the development of the I/O Crossword, a collaborative game that integrates various Google technologies, including the Gemini API, Flutter, and Firebase.

The article recaps the Google I/O 2024 event, highlighting advancements in AI technologies aimed at making AI accessible for developers.

The article discusses how Google is simplifying cross-platform development for developers by recommending specific technologies and frameworks.

This article provides essential dos and don'ts for web developers looking to integrate machine learning (ML) using MediaPipe Solutions.

The article discusses the implementation of MediaPipe on the web, highlighting how it enables cross-platform multimodal applied ML pipelines through WebAssembly and XNNPack.