LiteRT Tensor API

Latest news

1. 19 Oct
   Google releases LiteRT Tensor API for native edge model authoring

   Google announced the LiteRT Tensor API, a lightweight authoring layer in the LiteRT stack to simplify writing and optimizing on-device AI for diverse hardware. The API aims to reduce manual C++/shader rewrites and buffer-management work when targeting CPU, GPU, and NPU backends on edge devices.

   Developers · 1 source

   

Articles

No articles about LiteRT Tensor API yet.