Metadata-Version: 2.4
Name: executorch
Version: 1.6.0
Summary: On-device AI across mobile, embedded and edge for PyTorch
Author-email: PyTorch Team <packages@pytorch.org>
License: BSD-3-Clause
Project-URL: Homepage, https://pytorch.org/executorch/
Project-URL: Repository, https://github.com/pytorch/executorch
Project-URL: Issues, https://github.com/pytorch/executorch/issues
Project-URL: Changelog, https://github.com/pytorch/executorch/releases
Keywords: pytorch,machine learning
Classifier: Development Status :: 5 - Production/Stable
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Education
Classifier: Intended Audience :: Science/Research
Classifier: Topic :: Scientific/Engineering
Classifier: Topic :: Scientific/Engineering :: Mathematics
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
Classifier: Topic :: Software Development
Classifier: Topic :: Software Development :: Libraries
Classifier: Topic :: Software Development :: Libraries :: Python Modules
Classifier: Programming Language :: C++
Classifier: Programming Language :: Python :: 3
Classifier: Programming Language :: Python :: 3.11
Classifier: Programming Language :: Python :: 3.12
Classifier: Programming Language :: Python :: 3.13
Classifier: Programming Language :: Python :: 3.14
Classifier: Programming Language :: Python :: 3.15
Requires-Python: <3.16,>=3.11
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: flatbuffers
Requires-Dist: mpmath==1.3.0
Requires-Dist: numpy>=2.0.0; python_version >= "3.10"
Requires-Dist: packaging
Requires-Dist: pandas>=2.2.2; python_version >= "3.10"
Requires-Dist: py-cpuinfo
Requires-Dist: requests
Requires-Dist: pytorch-tokenizers
Requires-Dist: torch==2.15.0
Requires-Dist: torchao>=0.18.0
Requires-Dist: pyyaml
Requires-Dist: ruamel.yaml
Requires-Dist: sympy
Requires-Dist: tabulate
Requires-Dist: typing-extensions>=4.10.0
Requires-Dist: coremltools==9.0; (platform_system == "Darwin" or (platform_system == "Linux" and platform_machine == "x86_64")) and python_version < "3.14"
Requires-Dist: scikit-learn>=1.7.1; (platform_system == "Darwin" or (platform_system == "Linux" and platform_machine == "x86_64")) and python_version < "3.14"
Requires-Dist: hydra-core>=1.3.0
Requires-Dist: omegaconf>=2.3.0
Provides-Extra: vgf
Requires-Dist: ai_ml_emulation_layer_for_vulkan==0.11.0; extra == "vgf"
Requires-Dist: ai_ml_sdk_model_converter==0.11.0; extra == "vgf"
Requires-Dist: ml_dtypes==0.5.1; extra == "vgf"
Requires-Dist: tosa-tools==2026.5.0; extra == "vgf"
Provides-Extra: ethos-u
Requires-Dist: ethos-u-vela==5.2.0; extra == "ethos-u"
Requires-Dist: ml_dtypes==0.5.1; extra == "ethos-u"
Requires-Dist: tosa-tools==2026.5.0; extra == "ethos-u"
Provides-Extra: openvino
Requires-Dist: openvino<2027.0.0,>=2025.1.0; ((platform_system == "Linux" or (platform_system == "Windows" and platform_machine == "AMD64")) and python_version < "3.15" and (platform_machine != "aarch64" or python_version < "3.14")) and extra == "openvino"
Dynamic: license-file
Dynamic: requires-dist

**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.

* Supported Python versions: 3.11, 3.12, 3.13, 3.14, 3.15
* Compatible systems: Linux x86_64, Linux aarch64, macOS aarch64, Windows x86_64

Backend export tools can require optional Python dependencies. For example,
install the dependencies needed for Ethos-U ahead-of-time (AOT) export with:

```bash
pip install 'executorch[ethos_u]'
```

The `ethos_u` extra does not install components needed to build or run a target
runtime.

To build a minimal wheel from source, set
`EXECUTORCH_BUILD_MINIMAL=1` when running `pip wheel` or `pip install`.
That wheel contains the Python EXIR export path and `flatc` for `.pte`
serialization, but omits runtime pybindings, kernels, backend packages, headers,
examples, and devtools. It also declares only the Python dependencies the export
path needs (no `coremltools`, `pandas`, `scikit-learn`, `hydra-core`, or
`omegaconf`), so a normal install stays small. Like the full wheel, it does not
bundle PyTorch, so install a compatible `torch` separately. The wheel is still
platform specific because it ships `flatc`.

The prebuilt `executorch.runtime` module included in this package provides a way
to run ExecuTorch `.pte` files, with some restrictions:
* Only [core ATen operators](docs/source/ir-ops-set-definition.md) are linked into the prebuilt module
* Only the [XNNPACK backend delegate](docs/source/backends/xnnpack/xnnpack-overview.md) is linked into the prebuilt module.
* \[macOS only] [Core ML](docs/source/backends/coreml/coreml-overview.md) and MLX backends are
  also linked into the prebuilt module.
* \[Linux x86_64] [QNN](docs/source/backends-qualcomm.md) backend is linked into the prebuilt module.
* \[Linux and Windows] [OpenVINO](docs/source/build-run-openvino.md) backend is also linked into the
  prebuilt module. OpenVINO requires the runtime to be installed separately:
  `pip install executorch[openvino]`. For now the extra installs no runtime on Python 3.15,
  or on Linux aarch64 with Python 3.14. OpenVINO publishes no build for Python 3.15, and its
  aarch64 builds for Python 3.14 need glibc 2.35 or newer.

On Linux, macOS and Windows the runtime, kernels and backends also ship as shared libraries
with headers and a CMake package, so a C++ application can link them without building
ExecuTorch; see [Using ExecuTorch with C++](docs/source/using-executorch-cpp.md).

Please visit the [ExecuTorch website](https://pytorch.org/executorch) for
tutorials and documentation. Here are some starting points:
* [Getting Started](https://pytorch.org/executorch/main/getting-started-setup)
  * Set up the ExecuTorch environment and run PyTorch models locally.
* [Working with local LLMs](docs/source/llm/getting-started.md)
  * 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)
  * Learn the fundamentals of exporting a PyTorch `nn.Module` to ExecuTorch, and
    optimizing its performance using quantization and hardware delegation.
* Running etLLM on [iOS](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/apple) and [Android](https://github.com/meta-pytorch/executorch-examples/tree/main/llm/android) devices.
  * Build and run LLaMA in a demo mobile app, and learn how to integrate models
    with your own apps.
