xref: /aosp_15_r20/external/executorch/docs/source/intro-overview.md (revision 523fa7a60841cd1ecfb9cc4201f1ca8b03ed023a)
1# ExecuTorch Overview
2
3**ExecuTorch** is an end-to-end solution for enabling on-device inference
4capabilities across mobile and edge devices including wearables, embedded
5devices and microcontrollers. It is part of the PyTorch Edge ecosystem and
6enables efficient deployment of PyTorch models to edge devices.
7
8Key value propositions of ExecuTorch are:
9
10- **Portability:** Compatibility with a wide variety of computing platforms,
11  from high-end mobile phones to highly constrained embedded systems and
12  microcontrollers.
13- **Productivity:** Enabling developers to use the same toolchains and Developer
14  Tools from PyTorch model authoring and conversion, to debugging and deployment
15  to a wide variety of platforms.
16- **Performance:** Providing end users with a seamless and high-performance
17  experience due to a lightweight runtime and utilizing full hardware
18  capabilities such as CPUs, NPUs, and DSPs.
19
20## Why ExecuTorch?
21
22Supporting on-device AI presents unique challenges with diverse hardware,
23critical power requirements, low/no internet connectivity, and realtime
24processing needs. These constraints have historically prevented or slowed down
25the creation of scalable and performant on-device AI solutions. We designed
26ExecuTorch, backed by our industry partners like Meta, Arm, Apple, and Qualcomm,
27to be highly portable and provide superior developer productivity without losing
28on performance.
29
30## How is ExecuTorch Different from PyTorch Mobile (Lite Interpreter)?
31
32PyTorch Mobile uses [TorchScript](https://pytorch.org/docs/stable/jit.html) to
33allow PyTorch models to run on devices with limited resources. ExecuTorch has a
34significantly smaller memory size and a dynamic memory footprint resulting in
35superior performance and portability compared to PyTorch Mobile. Also, ExecuTorch
36does not rely on TorchScript, and instead leverages PyTorch 2 compiler and export
37functionality for on-device execution of PyTorch models.
38
39Read more in-depth technical overview topics about ExecuTorch:
40
41- [How ExecuTorch Works](intro-how-it-works.md)
42- [High-level Architecture and Components of ExecuTorch](getting-started-architecture.md)
43- [ExecuTorch Runtime Overview](runtime-overview.md)
44