WWWAI: Constructing a Truly Open GenAI App with WebAssembly, WebGPU, and WebAI
summary
Shows how to run open, high-performance generative AI models entirely in the browser using WebAssembly, WebGPU, and the WebAI APIs to build local, customizable, and secure web applications without relying on third-party cloud services. Covers system design, optimization strategies, and practical integration of open-source models to achieve real-world performance for robust, scalable GenAI web apps.
AI-written summary · about
chapters (11)
- 0:00Introduction and welcome
- 1:03What is Web AI and why it matters
- 3:59Open-source models for in-browser AI
- 6:26Understanding WebAssembly for AI
- 13:48Why GPUs are critical for AI models
- 15:33Introduction to WebGPU
- 23:45Exploring WebNN API
- 27:15Combining technologies for Web AI apps
- 32:15Decision framework for tech selection
- 40:40Future of Web AI and AIPC
- 42:24Q&A session
related talks
33mLocal Models: How to Run AI in the Browser
39mUnraveling the Magic of Two Hot Trends: WebAssembly and Generative AI
24mWeb Apps of the Future With Web AI
37mGetting Started with AI and WebAssembly
01h 04mDevelop, Build & Deploy Lightweight AI Services with WebAssembly
33mMachine Learning in the Browser: Fast Iteration with ONNX & WebAssembly
37mAI/ML at the Extreme Edge with WebAssembly: A Path Forward
41mCreating Versatile AI Agents Through Wasm+Rust