Welcome to the ExecuTorch Documentation#

ExecuTorch is PyTorch’s solution for efficient AI inference on edge devices — from mobile phones to embedded systems.

Key Value Propositions#

  • Portability: Run on diverse platforms, from high-end mobile to constrained microcontrollers

  • Performance: Lightweight runtime with full hardware acceleration (CPU, GPU, NPU, DSP)

  • Productivity: Use familiar PyTorch tools from authoring to deployment


🎯 Wins & Success Stories#


Quick Navigation#

Get Started

New to ExecuTorch? Start here for installation and your first model deployment.

Quick Start
Deploy on Edge Platforms

Deploy on Android, iOS, Laptops / Desktops and embedded platforms with optimized backends.

Edge
Work with LLMs

Export, optimize, and deploy Large Language Models on edge devices.

LLMs
🔧 Developer Tools

Profile, debug, and inspect your models with comprehensive tooling.

Tools

Explore Documentation#

Intro

Overview, architecture, and core concepts — Understand how ExecuTorch works and its benefits

Intro
Quick Start

Get started with ExecuTorch — Install, export your first model, and run inference

Quick Start
Edge

Android, iOS, Desktop, Embedded — Platform-specific deployment guides and examples

Edge
Backends

CPU, GPU, NPU/Accelerator backends — Hardware acceleration and backend selection

Backends
LLMs

LLM export, optimization, and deployment — Complete LLM workflow for edge devices

LLMs
Advanced

Quantization, memory planning, custom passes — Deep customization and optimization

Advanced
Tools

Developer tools, profiling, debugging — Comprehensive development and debugging suite

Tools
API

API Reference Usages & Examples — Detailed Python, C++, and Java API references

API
💬 Support

FAQ, troubleshooting, contributing — Get help and contribute to the project

Support

What’s Supported#

Model Types

  • Large Language Models (LLMs)

  • Computer Vision (CV)

  • Speech Recognition (ASR)

  • Text-to-Speech (TTS)

  • More …

Platforms

  • Android & iOS

  • Linux, macOS, Windows

  • Embedded & MCUs

  • Go Edge

Rich Acceleration