LiteRT.js, Google’s high performance WebAI runtime
Harness the power of LiteRT on the web! This talk introduces LiteRT.js, Google's new WebAI runtime that runs your custom .tflite models with WebGPU. Matthew Soulanille, ODML Software Engineer, and Chintan Parikh, Product Manager, cover features of the library, its best-in-class performance, how it complements Google's existing Web AI ecosystem, and what's coming next. Resources: Docs → https://goo.gle/47tIuNH Github → https://goo.gle/4oo3201 NPM → https://goo.gle/47LLvb1 See more Web AI talks → https://goo.gle/web-ai Subscribe to Chrome for Developers → https://goo.gle/ChromeDevs Event: Web AI Summit 2025 Speaker: Matthew Soulanille, Chintan Parikh Products Mentioned: AI for the web, LiteRT.js, WebGPU #ChromeforDevelopers #WebAI
Transformers.js: Building Next-Generation WebAI Applications
The Web Neural Network (WebNN) API: Where we are and what's Next
TLMs: Tiny LLMs and Agents on Edge Devices with LiteRT-LM — Cormac Brick, Google
How to build AI-powered VS Code extensions with local models
The Hardest Problem AI Ever Solved, with Google DeepMind CEO
What's new in Web UI
Ex-Google Officer: You Only Have 3 Years Left Before It Hits! - Mo Gawdat
InferenceJS: Real-time computer vision in your browser
Andrej Karpathy: Software Is Changing (Again)
Web AI Summit 2025: State of client side AI
Transformers.js Explained by Its Creator: State-of-the-Art Machine Learning for the Web
Why WebGPU + Transformers.js is a Game Changer
Wasm, WebGPU, & WebNN: How compute abstraction are enabling client side AI
Google I/O 2026 keynote in 35 minutes
What is Transformers.js?
Client-side Agents with WebAI
Learn 97% of Claude in Under 16 Minutes
Running Google's Gemma LLMs in the browser with MediaPipe Web
Master Gemma 4 in 20 Minutes
