# Google releases LiteRT Tensor API for native edge model authoring

> The new API lets developers hand‑craft C++ model graphs that run on CPU, GPU or NPU without rewriting code for each hardware.

Oossa · 2026-10-19 · https://oossa.com/en/google-releases-litert-tensor-api-for-native-edge-model-authoring

Event date: 2026-10-19

Google announced the LiteRT Tensor API, a lightweight C++ layer for building on‑device AI models. It gives full control over the computation graph while staying portable across CPUs, GPUs (via ML Drift) and NPUs. The API was demonstrated with Meta’s Segment Anything Model 2 running entirely in a browser on WebGPU, achieving over 30 fps at 512×512 resolution. Developers can also load weights directly from checkpoints and keep data on accelerators with zero‑copy buffers.

## The facts

- Announced on Oct. 19, 2026
- SAM 2 runs at >30 fps on WebGPU using the LiteRT Tensor API

## Why it matters

App developers can ship faster, lower‑latency AI features to phones and browsers without maintaining separate code for each chip.

## Sources & references

1. [Native Model Authoring for Edge with LiteRT Tensor API](https://developers.googleblog.com/en/native-model-authoring-for-edge-with-litert-tensor-api/) – Google for Developers

Last updated: 2026-10-19