LiteRT.js, Google's high performance Web AI Inference- Google Developers Blog

We are excited to announce LiteRT.js, a JavaScript binding of LiteRT for running AI directly inside the web browser. By bringing the trusted on-device inference library LiteRT to the web, web developers can now run ML and AI models with maximum performance entirely locally. This means enhanced user privacy, zero server costs, and ultra-low latency for real-time experiences. For developers with exi

[nguyen-oi]

WebAssemblyとWebGPUでブラウザAIがどこまで実用的になるか見ものだな

[misshiki]

Googleがブラウザ内AI推論基盤「LiteRT.js」を発表。CPU・GPUで既存Webランタイム比最大3倍、GPU・NPUはCPU比5〜60倍高速化。.tfliteを端末上で実行できる。