ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device

TL;DR

ExecuTorch is a unified, PyTorch-native framework that simplifies deploying AI models across diverse edge hardware, supporting customization, optimization, and seamless experimentation within PyTorch.

Contribution

It introduces a comprehensive deployment solution that maintains PyTorch semantics and supports heterogeneous hardware, bridging research and production workflows.

Findings

Supports deployment from microcontrollers to large SoCs.

Enables validation of deployment behavior within PyTorch.

Supports optimizations like quantization and customizable backends.

Abstract

Local execution of AI on edge devices is important for low latency and offline operation. However, deploying models on diverse hardware remains fragmented, often requiring model conversion or complete reimplementation outside the PyTorch ecosystem where the model was originally authored. We introduce ExecuTorch, a unified PyTorch-native deployment framework for edge AI. ExecuTorch enables seamless deployment of machine learning models across heterogeneous compute environments. It scales from embedded microcontrollers to complex system-on-chips (SoCs) with dedicated accelerators, powering devices ranging from wearables and smartphones to large compute clusters. ExecuTorch preserves PyTorch semantics while allowing customization, support for optimizations like quantization, and pluggable execution "backends". These features together enable fast experimentation, allowing researchers to validate deployment behavior entirely within PyTorch, bridging the gap between research and production.