Skip to main content

ExecuTorch is a PyTorch 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 beta.

  • Supported python versions: 3.10, 3.11, 3.12, 3.13, 3.14
  • Compatible systems: Linux x86_64, Linux aarch64, macOS aarch64

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 are linked into the prebuilt module
  • Only the XNNPACK backend delegate is linked into the prebuilt module.
  • [macOS only] Core ML and MLX backends are also linked into the prebuilt module.
  • [Linux x86_64] QNN backend is linked into the prebuilt module.
  • [Linux] OpenVINO backend is also linked into the prebuilt module. OpenVINO requires the runtime to be installed separately: pip install executorch[openvino]

Please visit the ExecuTorch website for tutorials and documentation. Here are some starting points:

  • Getting Started
    • Set up the ExecuTorch environment and run PyTorch models locally.
  • Working with local LLMs
    • Learn how to use ExecuTorch to export and accelerate a large-language model from scratch.
  • Exporting to ExecuTorch
    • Learn the fundamentals of exporting a PyTorch nn.Module to ExecuTorch, and optimizing its performance using quantization and hardware delegation.
  • Running etLLM on iOS and Android devices.
    • Build and run LLaMA in a demo mobile app, and learn how to integrate models with your own apps.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

executorch-1.5.0-cp314-cp314-win_amd64.whl (14.3 MB view details)

Uploaded CPython 3.14Windows x86-64

executorch-1.5.0-cp314-cp314-manylinux_2_28_x86_64.whl (18.9 MB view details)

Uploaded CPython 3.14manylinux: glibc 2.28+ x86-64

executorch-1.5.0-cp314-cp314-manylinux_2_28_aarch64.whl (17.8 MB view details)

Uploaded CPython 3.14manylinux: glibc 2.28+ ARM64

executorch-1.5.0-cp314-cp314-macosx_14_0_arm64.whl (18.7 MB view details)

Uploaded CPython 3.14macOS 14.0+ ARM64

executorch-1.5.0-cp313-cp313-win_amd64.whl (14.3 MB view details)

Uploaded CPython 3.13Windows x86-64

executorch-1.5.0-cp313-cp313-manylinux_2_28_x86_64.whl (18.9 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.28+ x86-64

executorch-1.5.0-cp313-cp313-manylinux_2_28_aarch64.whl (17.8 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.28+ ARM64

executorch-1.5.0-cp313-cp313-macosx_14_0_arm64.whl (18.7 MB view details)

Uploaded CPython 3.13macOS 14.0+ ARM64

executorch-1.5.0-cp312-cp312-win_amd64.whl (14.3 MB view details)

Uploaded CPython 3.12Windows x86-64

executorch-1.5.0-cp312-cp312-manylinux_2_28_x86_64.whl (19.0 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.28+ x86-64

executorch-1.5.0-cp312-cp312-manylinux_2_28_aarch64.whl (17.9 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.28+ ARM64

executorch-1.5.0-cp312-cp312-macosx_14_0_arm64.whl (18.8 MB view details)

Uploaded CPython 3.12macOS 14.0+ ARM64

executorch-1.5.0-cp311-cp311-win_amd64.whl (14.3 MB view details)

Uploaded CPython 3.11Windows x86-64

executorch-1.5.0-cp311-cp311-manylinux_2_28_x86_64.whl (18.9 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.28+ x86-64

executorch-1.5.0-cp311-cp311-manylinux_2_28_aarch64.whl (17.8 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.28+ ARM64

executorch-1.5.0-cp311-cp311-macosx_14_0_arm64.whl (18.7 MB view details)

Uploaded CPython 3.11macOS 14.0+ ARM64

executorch-1.5.0-cp310-cp310-win_amd64.whl (14.3 MB view details)

Uploaded CPython 3.10Windows x86-64

executorch-1.5.0-cp310-cp310-manylinux_2_28_x86_64.whl (18.9 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.28+ x86-64

executorch-1.5.0-cp310-cp310-manylinux_2_28_aarch64.whl (17.8 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.28+ ARM64

executorch-1.5.0-cp310-cp310-macosx_14_0_arm64.whl (18.7 MB view details)

Uploaded CPython 3.10macOS 14.0+ ARM64

File details

Details for the file executorch-1.5.0-cp314-cp314-win_amd64.whl.

File metadata

  • Download URL: executorch-1.5.0-cp314-cp314-win_amd64.whl
  • Upload date:
  • Size: 14.3 MB
  • Tags: CPython 3.14, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for executorch-1.5.0-cp314-cp314-win_amd64.whl
Algorithm Hash digest
SHA256 232186f46a2f00bec6eb31742bff9a65108e4b8e29f9648a3a4dac95b4859331
MD5 ff109603b345a10be231f30bf47ffaf7
BLAKE2b-256 ea7276b094c3a3883e5a1eed73c0d48a6bf9a613e5fb4ece622d0af1c7e28045

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp314-cp314-win_amd64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp314-cp314-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp314-cp314-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 e91920496b54bf3b1f111fa22b0f63e5ad09b7502f41dceec3ad4a1322c4cbe8
MD5 1da71b6ffaa3c41a6d67c13e707af188
BLAKE2b-256 579743c2f7ea60acbdf1001ce86b796dd283201a1f3417346aec4f8eddda45fa

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp314-cp314-manylinux_2_28_x86_64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp314-cp314-manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp314-cp314-manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 a67ea2b6e97ccaee0956efe133b4c61786afb4e78ed6734c046758e17e24340f
MD5 5e738cfcda742a53d31802f577c59e8f
BLAKE2b-256 bc53a6d0f4308b7a4c0a4c5d450e6a4c447325636fb96cf11e836ec5ae79487f

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp314-cp314-manylinux_2_28_aarch64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp314-cp314-macosx_14_0_arm64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp314-cp314-macosx_14_0_arm64.whl
Algorithm Hash digest
SHA256 5e26b9bf839490ad6617792f8cfa48c3f6aa008eb4ba19a7613ed0dbecc0ee62
MD5 0ce9bffd3ec623a903344aac3c925873
BLAKE2b-256 82ceef7837fba56a66d464d96476c3acef7c917ffa4b6b9dd2455eab63a74b76

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp314-cp314-macosx_14_0_arm64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp313-cp313-win_amd64.whl.

File metadata

  • Download URL: executorch-1.5.0-cp313-cp313-win_amd64.whl
  • Upload date:
  • Size: 14.3 MB
  • Tags: CPython 3.13, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for executorch-1.5.0-cp313-cp313-win_amd64.whl
Algorithm Hash digest
SHA256 099d7af52c41527bfa739c8df9e9b7434e91df646d08065c7fabf6d6e8e77a0a
MD5 4362daa6670518365db1b3e7f628f71f
BLAKE2b-256 168dfb0239c65be1270bebe0b9cfb59de534cf0f2fb346b73694b5ab2afdb945

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp313-cp313-win_amd64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp313-cp313-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp313-cp313-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 02987db1b0e2c6351fd23050e085ba61977cd47318b82570639a17a7a39b70e5
MD5 f768375086b0f33a7eb401d982919450
BLAKE2b-256 b1abc15e25b8f240bce97bd8139a78650ffb2eb4c491706fe34eb5505dca7960

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp313-cp313-manylinux_2_28_x86_64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp313-cp313-manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp313-cp313-manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 eba13b31a7119bd4bb38bc2ab16e44935ca8ccb02a2fb481004d168396ad08eb
MD5 f8eaf85b40a678b95fcaba248a074f88
BLAKE2b-256 d069c887f8f9b2df5f25308a0f03eaa8eda3ec6b39323905bf260b30d0006b03

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp313-cp313-manylinux_2_28_aarch64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp313-cp313-macosx_14_0_arm64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp313-cp313-macosx_14_0_arm64.whl
Algorithm Hash digest
SHA256 3878336ccef09d26fb8485837ce379e69e75e317f72555b498f748b66c776130
MD5 6b1706e16be215c939c60eff3653d43f
BLAKE2b-256 096ef412c367b66c886089f540252fc1d7e32fcf51af341d3bf0f7e78d0e4e81

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp313-cp313-macosx_14_0_arm64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp312-cp312-win_amd64.whl.

File metadata

  • Download URL: executorch-1.5.0-cp312-cp312-win_amd64.whl
  • Upload date:
  • Size: 14.3 MB
  • Tags: CPython 3.12, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for executorch-1.5.0-cp312-cp312-win_amd64.whl
Algorithm Hash digest
SHA256 9b96b71f7b1b1411f45e0bf62e0df0d61138adb83fdab599e99412ca16a3b98d
MD5 f34f77a2efd9ac352e04f40bee444c64
BLAKE2b-256 9483abaf002ee2c1b4c44d8ccbfeeae5a4780e6a94635e6c8e41c572898141a4

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp312-cp312-win_amd64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp312-cp312-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp312-cp312-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 29b7a7c512b3078c844e9b3e7554afde4987de89d40bc8de0ae41146a62d6329
MD5 fe8eed76fb696a716802de361cab142c
BLAKE2b-256 a05e0dea92d518ef698808763ec11183cd39403fdf126ff1b69561f05387f02a

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp312-cp312-manylinux_2_28_x86_64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp312-cp312-manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp312-cp312-manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 7ad0763b84fa26658b2e4d880905f3c0dd54cc92be06264fd473ddf97cc9402c
MD5 02a1860dcbd40b6c9b18a44142f8a5ab
BLAKE2b-256 ea919fb1fee7d3a240b635a16748947d35eb2d6ce9268749eb8cd341fe51b861

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp312-cp312-manylinux_2_28_aarch64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp312-cp312-macosx_14_0_arm64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp312-cp312-macosx_14_0_arm64.whl
Algorithm Hash digest
SHA256 56274ca6fa7f511d4c7bca92ff385911599262251012c3cc376adc40bb7d72c3
MD5 f9c13b8609997aad372c222d0f1ab96b
BLAKE2b-256 dab404c20f85a349571b5225b2f5c5da0400c6b3c6417ba060b19e966d0d267f

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp312-cp312-macosx_14_0_arm64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp311-cp311-win_amd64.whl.

File metadata

  • Download URL: executorch-1.5.0-cp311-cp311-win_amd64.whl
  • Upload date:
  • Size: 14.3 MB
  • Tags: CPython 3.11, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for executorch-1.5.0-cp311-cp311-win_amd64.whl
Algorithm Hash digest
SHA256 572052c30c3037b19cd25ac3ffaa42e9d34cda0701b4846c4e8eed2edf9f11f5
MD5 b36293ce75359057899112f7268903f8
BLAKE2b-256 ecd9a68b1b4cae698a0593b23703e279fc649257b1c279e2fc9259002f5029fc

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp311-cp311-win_amd64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp311-cp311-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp311-cp311-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 970d9ec9fc7fb7e30ece5b942b16ddc84372353af94ebf69d94687153ac8ab67
MD5 9990dc11d0d3ca110ac76d01ccf74288
BLAKE2b-256 33cb632db0efd7d2e76955b739b031e19e237a905f90bffd2ae92924036d2914

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp311-cp311-manylinux_2_28_x86_64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp311-cp311-manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp311-cp311-manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 b378f610c76ba5869fa44e4c4d1b4b17b186f2715ab3a01787dc1a1056e84db0
MD5 6ddec1159063d20f8ca84fa39c8fe4e6
BLAKE2b-256 94fdd3e9f19372b84f92a30ea8e97d43ade17fa925e31604e8537564c2e58a8f

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp311-cp311-manylinux_2_28_aarch64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp311-cp311-macosx_14_0_arm64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp311-cp311-macosx_14_0_arm64.whl
Algorithm Hash digest
SHA256 4ea28ab1c261934d3c15c7d044b27c5f1febbd885c59bb55feb4423d11e20719
MD5 20aa144c21bc19261e884f329eb04cc8
BLAKE2b-256 ed39b50fe47819b4791f0c188beeec9ccdf38f11fef74c04cd97e50147e48220

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp311-cp311-macosx_14_0_arm64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp310-cp310-win_amd64.whl.

File metadata

  • Download URL: executorch-1.5.0-cp310-cp310-win_amd64.whl
  • Upload date:
  • Size: 14.3 MB
  • Tags: CPython 3.10, Windows x86-64
  • Uploaded using Trusted Publishing? Yes
  • Uploaded via: twine/7.0.0 CPython/3.13.14

File hashes

Hashes for executorch-1.5.0-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 9ea11e763d257ca55ce39a7033b2e0266b3cc17e8bb24d4daed507079349f337
MD5 9ae41b459c1e7ae9c7b8b01264885fd6
BLAKE2b-256 f8d54b1495c60201463ed3590b669369cbfa9f819a98bbffd3e6b14a91c8d3cd

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp310-cp310-win_amd64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp310-cp310-manylinux_2_28_x86_64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp310-cp310-manylinux_2_28_x86_64.whl
Algorithm Hash digest
SHA256 a87e69ff617eabb129b65e17b70d7efa05e247037cca541dd61c2119c1c8ddbf
MD5 002b39cc5764a17b6fd22dda597d6460
BLAKE2b-256 f32aad06158261229e045b30a661a97eb023dbd54df67cd104a9c38a59265c3d

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp310-cp310-manylinux_2_28_x86_64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp310-cp310-manylinux_2_28_aarch64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp310-cp310-manylinux_2_28_aarch64.whl
Algorithm Hash digest
SHA256 04266c02cc91a512d27115277d884e1f0560e7e162bde5ba5e8e51c3541290d3
MD5 e50b9b0de39bad16851193c0cd267f87
BLAKE2b-256 0277617a4338060f4267f9a7357e6379740dd3309d0d7d209ff34dee403c1103

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp310-cp310-manylinux_2_28_aarch64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

File details

Details for the file executorch-1.5.0-cp310-cp310-macosx_14_0_arm64.whl.

File metadata

File hashes

Hashes for executorch-1.5.0-cp310-cp310-macosx_14_0_arm64.whl
Algorithm Hash digest
SHA256 04219ed58d9fe6a16fa35b4e1299080116f1adc8479428b533f8f71bd1ca2c4a
MD5 705b40d2a6c687dd43d2d6fc45085f9c
BLAKE2b-256 f9d5b709b0b04caa788c6856c67364100d5048854c78d11fe6d8b622679a27e6

See more details on using hashes here.

Provenance

The following attestation bundles were made for executorch-1.5.0-cp310-cp310-macosx_14_0_arm64.whl:

Publisher: release-pypi.yml on pytorch/test-infra

Attestations: Values shown here reflect the state when the release was signed and may no longer be current.

Release history Release notifications | RSS feed

This release

1.5.0 This release

20 files

1.4.1

20 files

1.4.0

20 files

1.3.1

16 files

1.2.0

16 files

1.1.0

16 files

1.0.1

12 files

1.0.0

12 files

0.7.0

6 files

0.6.0

6 files

0.5.0

6 files

0.4.0

6 files

0.3.0

8 files

0.2.1

6 files

0.2.0

4 files

0.1.2

2 files

0.1.0

2 files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page