Google出了LiteRT.js，浏览器里直接跑.tflite模型，GPU加速比CPU快5-60倍，不过记得自己删tensor。
Google于2026年7月9日发布LiteRT.js，这是LiteRT的JavaScript绑定，可在浏览器中通过WebAssembly运行.tflite模型。运行时支持XNNPACK on CPU、ML Drift over WebGPU以及实验性WebNN for NPUs。官方称相比其他web运行时性能提升3倍，GPU/NPU路径相比自身CPU路径快5-60倍。注意：tensor需手动管理并必须显式删除。
Google Releases LiteRT.js: A JavaScript Binding of LiteRT That Runs .tflite Models in Browsers via WebGPU
Google released LiteRT.js on July 9, 2026. It is a JavaScript binding of LiteRT, Google's on-device inference library. The runtime executes .tflite models directly in the browser through WebAssembly, with XNNPACK on CPU, ML Drift over WebGPU, and experimental WebNN for NPUs. Google reports up to 3x gains over other web runtimes, and 5–60x for GPU or NPU over its own CPU path. One detail the announcement omits: tensors are manually managed and must be deleted. The post Google Releases LiteRT.js: A JavaScript Binding of LiteRT That Runs .tflite Models in Browsers via WebGPU appeared first on MarkTechPost .