Embedded Systems

Deploy ExecuTorch on constrained embedded systems and microcontrollers.

API Reference & Development

Start here for C++ development with ExecuTorch runtime APIs and essential tutorials.

• Runtime API Reference — Start here: Complete runtime API reference for embedded development

• Detailed C++ Runtime APIs Tutorial — Step-by-step C++ API tutorial with practical examples

• Running an ExecuTorch Model Using the Module Extension in C++ — Custom module extensions for specialized functionality

• Managing Tensor Memory in C++ — Tensor operations and memory management extensions

Build & Integration Guide

• Using ExecuTorch with C++ — Complete setup guide for C++ runtime integration

• Building from Source — Building from Source

Choose Backend for acceleration

• Backends — Available embedded backends and acceleration options

Tutorials

• Arm Ethos-U NPU Backend Tutorial — Export a simple PyTorch model for the ExecuTorch Ethos-U backend

• ExecuTorch on Raspberry Pi — Deploy a LLaMA model on a Raspberry Pi

• Pico2: A simple MNIST Tutorial — Deploy a demo MNIST model on the Raspberry Pi Pico 2