ExecuTorch让PyTorch模型一键部署到各类边缘设备
ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device
- 基于PyTorch原生框架，统一支持从微控制器到SoC的部署
- 支持量化等优化，可在不同硬件上实现低延迟运行
- 研究者可全程在PyTorch内验证部署效果，加速研发到落地
边缘设备上的本地AI执行对低延迟和离线运行至关重要。然而，将模型部署到多样硬件仍呈碎片化状态，常需在PyTorch生态外进行模型转换或重写。我们提出ExecuTorch，一个原生支持PyTorch的边缘AI统一部署框架。该框架可无缝跨异构计算环境部署机器学习模型，覆盖从嵌入式微控制器到配备专用加速器的复杂系统级芯片（SoCs），支持从可穿戴设备、智能手机到大型计算集群的各类设备。ExecuTorch保持PyTorch语义一致，同时支持量化等优化，并提供可插拔的执行后端。这些特性共同实现快速实验，使研究人员能在PyTorch内完整验证部署行为，弥合研究与生产之间的鸿沟。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。