Hear from Moh Haghighat, Fellow at Intel, where he showcases WebNN, an emerging unified W3C web standard API for on-device web ML acceleration across client AI execution engines: CPU, GPU, and NPU. Currently in Developer Preview on Chrome and Edge browsers and integrated in popular ML frameworks (e.g., ONNX Runtime Web), WebNN delivers “near-native” performance and power characteristics. We will show exciting WebNN demos and adoption previews that bring a new class of experiences to the web.
Resources:
WebNN Demos → https://goo.gle/40KTHGz
Samples → https://goo.gle/3ClRaIZ
Spec → https://goo.gle/4fDNhNG
Explainer → https://goo.gle/3CjFC8O
Implementation Status → https://goo.gle/3UO7rfT
Awesome WebNN → https://goo.gle/4hFNMJ1
Tutorial → https://goo.gle/40CNMn1
AI PC Development → https://goo.gle/3UNiSVg
See more Web AI talks → https://goo.gle/web-ai
Subscribe to Chrome for Developers → https://goo.gle/ChromeDevs
Speaker: Moh Haghighat
Products mentioned: AI for the web, Google Chrome Browser, Chrome Browser Automation, Chrome Extensions, Chrome, Chrome Web Platform, Web AI, Web apps, Web Assembly (Wasm), Web Platform in Chrome, WebAssembly for Chrome, WebGPU, CodeGemma, Gemma 2, Gemma, RecurrentGemma, Generative AI, AI, Google AI, Google AI Edge, Responsible AI, Kaggle Models, LiteRT, TensorFlow, Hugging Face Models