Poster 4

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

Mergen Nachin ⋅ Digant Desai ⋅ Sicheng Jia ⋅ Chen Lai ⋅ Mengwei Liu ⋅ Jacob Szwejbka ⋅ Raziel Alvarez ⋅ Robert Ascani ⋅ Dave Bort ⋅ Manuel Candales ⋅ Andrew Caples ⋅ Yanan Cao ⋅ Zhengxu Chen ⋅ Soumith Chintala ⋅ Gregory Comer ⋅ Tanvir Islam ⋅ Songhao Jia ⋅ Tarun Karuturi ⋅ Jack Khuu ⋅ Abhinay Kukkadapu ⋅ Tugsbayasgalan Manlaibaatar ⋅ Andrew Or ⋅ Kimish Patel ⋅ Siddartha Pothapragada ⋅ Lucy Qiu ⋅ Supriya Rao ⋅ Orion Reblitz-Richardson ⋅ Max Ren ⋅ Scott Roy ⋅ Anthony Shoumikhin ⋅ Scott Wolchok ⋅ Guang Yang ⋅ Angela Yi ⋅ Martin Yuan ⋅ Hansong Zhang ⋅ Jack Zhang ⋅ Zhenrui Zhang ⋅ Shunting Zhang ⋅ Cemal Bilgin

Project Page [ OpenReview]

Abstract

Local execution of AI on edge devices is critical for privacy, low latency, and offline operation. However, deploying models on diverse hardware remains fragmented, often requiring model conversion or complete implementation 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 completely 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.

Chat is not available.