https://github.com/pytorch/executorch

On-device AI across mobile, embedded and edge for PyTorch
https://github.com/pytorch/executorch

deep-learning embedded gpu machine-learning mobile neural-network tensor

Last synced: 3 days ago
JSON representation

On-device AI across mobile, embedded and edge for PyTorch

• Host: GitHub
• URL: https://github.com/pytorch/executorch
• Owner: pytorch
• License: other
• Created: 2022-02-25T17:58:31.000Z (almost 3 years ago)
• Default Branch: main
• Last Pushed: 2024-12-03T21:25:47.000Z (9 days ago)
• Last Synced: 2024-12-03T21:32:56.647Z (9 days ago)
• Topics: deep-learning, embedded, gpu, machine-learning, mobile, neural-network, tensor
• Language: C++
• Homepage: https://pytorch.org/executorch/
• Size: 139 MB
• Stars: 2,245
• Watchers: 60
• Forks: 379
• Open Issues: 853
• Metadata Files:
  • Readme: README-wheel.md
  • Contributing: CONTRIBUTING.md
  • License: LICENSE
  • Code of conduct: CODE_OF_CONDUCT.md

Awesome Lists containing this project

• AiTreasureBox - pytorch/executorch - 12-07_2252_0](https://img.shields.io/github/stars/pytorch/executorch.svg)|On-device AI across mobile, embedded and edge for PyTorch| (Repos)
• awesome-repositories - pytorch/executorch - On-device AI across mobile, embedded and edge for PyTorch (C++)
• Awesome-LLMs-on-device - [Github

README

        
**ExecuTorch** is a [PyTorch](https://pytorch.org/) platform that provides

infrastructure to run PyTorch programs everywhere from AR/VR wearables to

standard on-device iOS and Android mobile deployments. One of the main goals for

ExecuTorch is to enable wider customization and deployment capabilities of the

PyTorch programs.

The `executorch` pip package is in alpha.

* Supported python versions: 3.10, 3.11

* Compatible systems: Linux x86_64, macOS aarch64

The prebuilt `executorch.extension.pybindings.portable_lib` module included in

this package provides a way to run ExecuTorch `.pte` files, with some

restrictions:

* Only [core ATen

  operators](https://pytorch.org/executorch/stable/ir-ops-set-definition.html)

  are linked into the prebuilt module

* Only the [XNNPACK backend

  delegate](https://pytorch.org/executorch/main/native-delegates-executorch-xnnpack-delegate.html)

  is linked into the prebuilt module

* [macOS only] [Core ML](https://pytorch.org/executorch/main/build-run-coreml.html) and [MPS](https://pytorch.org/executorch/main/build-run-mps.html) backend delegates are linked into the prebuilt module.

Please visit the [ExecuTorch website](https://pytorch.org/executorch/) for

tutorials and documentation. Here are some starting points:

* [Getting

  Started](https://pytorch.org/executorch/stable/getting-started-setup.html)

  * Set up the ExecuTorch environment and run PyTorch models locally.

* [Working with

  local LLMs](https://pytorch.org/executorch/stable/llm/getting-started.html)

  * Learn how to use ExecuTorch to export and accelerate a large-language model

    from scratch.

* [Exporting to

  ExecuTorch](https://pytorch.org/executorch/main/tutorials/export-to-executorch-tutorial.html)

  * Learn the fundamentals of exporting a PyTorch `nn.Module` to ExecuTorch, and

    optimizing its performance using quantization and hardware delegation.

* Running LLaMA on

  [iOS](https://pytorch.org/executorch/stable/llm/llama-demo-ios.html) and

  [Android](https://pytorch.org/executorch/stable/llm/llama-demo-android.html)

  devices.

  * Build and run LLaMA in a demo mobile app, and learn how to integrate models

    with your own apps.