Google Releases LiteRT.js: A JavaScript Binding of LiteRT That Runs .tflite Models in Browsers via WebGPU

Google released LiteRT.js, a JavaScript binding of LiteRT, allowing .tflite models to run in browsers via WebGPU. LiteRT.js reportedly offers up to 3x faster performance than other web runtimes and 5-60x speedup with GPU or NPU acceleration. It supports three backends: CPU, GPU, and NPU, with manual tensor management required to avoid memory leaks.