Pre-release

This release is a pre-release and may not be stable for production use.

Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developers to choose the right tools as their project evolves. ONNX provides an open source format for AI models, both deep learning and traditional ML. It defines an extensible computation graph model, as well as definitions of built-in operators and standard data types. Currently we focus on the capabilities needed for inferencing (scoring).

ONNX is widely supported and can be found in many frameworks, tools, and hardware. Enabling interoperability between different frameworks and streamlining the path from research to production helps increase the speed of innovation in the AI community. We invite the community to join us and further evolve ONNX.

Use ONNX

Learn about the ONNX spec

Overview
ONNX intermediate representation spec
Versioning principles of the spec
Operators documentation
Operators documentation (latest release)
Python API Overview

Programming utilities for working with ONNX Graphs

Contribute

ONNX is a community project and the open governance model is described here. We encourage you to join the effort and contribute feedback, ideas, and code. You can participate in the Special Interest Groups and Working Groups to shape the future of ONNX.

Check out our contribution guide to get started.

If you think some operator should be added to ONNX specification, please read this document.

Community meetings

The schedules of the regular meetings of the Steering Committee, the working groups and the SIGs can be found here

Community Meetups are held at least once a year. Content from previous community meetups are at:

Discuss

We encourage you to open Issues, or use Slack (If you have not joined yet, please use this link to join the group) for more real-time discussion.

Stay up to date with the latest ONNX news. [Facebook] [Twitter/X]

Roadmap

A roadmap process takes place every year. More details can be found in ROADMAP.md.

Installation

ONNX released packages are published in PyPi.

pip install onnx # or pip install onnx[reference] for optional reference implementation dependencies

ONNX weekly packages are published in PyPI to enable experimentation and early testing.

Detailed install instructions, including Common Build Options and Common Errors can be found here

Python ABI3 Compatibility

This package provides abi3-compatible wheels, allowing a single binary wheel to work across multiple Python versions (from 3.12 onwards).

Testing

ONNX uses pytest as test driver. In order to run tests, you will first need to install pytest:

pip install pytest

After installing pytest, use the following command to run tests.

pytest

Development

Check out the contributor guide for instructions.

Reproducible Build Support

ONNX build and release workflows set SOURCE_DATE_EPOCH to the source commit timestamp. This removes timestamp-dependent variation from supported build steps and makes independent build comparison easier.

SOURCE_DATE_EPOCH alone does not guarantee byte-for-byte identical artifacts across different environments. A reproducibility check must also use the same source revision, dependency versions, toolchain, target platform, and build configuration, and then compare the resulting artifacts.

Why this matters

A fixed build timestamp removes one known source of nondeterminism. When independent builds use the same controlled inputs, their artifacts can be compared byte for byte, with cryptographic digests providing a practical shortcut. A byte-for-byte match demonstrates identical outputs, while a mismatch identifies a difference that needs investigation. This comparison complements release provenance attestations; it does not replace them.

Release artifacts are available from PyPI.

License

Apache License v2.0

Trademark

Checkout https://trademarks.justia.com for the trademark.

General rules of the Linux Foundation on Trademark usage

Code of Conduct

ONNX Open Source Code of Conduct

Download files

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

Source Distribution

onnx_weekly-1.23.0.dev20260817.tar.gz (6.0 MB view details)

Uploaded Aug 17, 2026 Source

Built Distributions

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

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

onnx_weekly-1.23.0.dev20260817-cp314-cp314t-win_arm64.whl (8.0 MB view details)

Uploaded Aug 17, 2026 CPython 3.14tWindows ARM64

onnx_weekly-1.23.0.dev20260817-cp314-cp314t-win_amd64.whl (7.8 MB view details)

Uploaded Aug 17, 2026 CPython 3.14tWindows x86-64

onnx_weekly-1.23.0.dev20260817-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (8.8 MB view details)

Uploaded Aug 17, 2026 CPython 3.14tmanylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

onnx_weekly-1.23.0.dev20260817-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (8.6 MB view details)

Uploaded Aug 17, 2026 CPython 3.14tmanylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

onnx_weekly-1.23.0.dev20260817-cp314-cp314t-macosx_13_0_universal2.whl (9.6 MB view details)

Uploaded Aug 17, 2026 CPython 3.14tmacOS 13.0+ universal2 (ARM64, x86-64)

onnx_weekly-1.23.0.dev20260817-cp312-abi3-win_arm64.whl (8.0 MB view details)

Uploaded Aug 17, 2026 CPython 3.12+Windows ARM64

onnx_weekly-1.23.0.dev20260817-cp312-abi3-win_amd64.whl (7.8 MB view details)

Uploaded Aug 17, 2026 CPython 3.12+Windows x86-64

onnx_weekly-1.23.0.dev20260817-cp312-abi3-win32.whl (7.7 MB view details)

Uploaded Aug 17, 2026 CPython 3.12+Windows x86

onnx_weekly-1.23.0.dev20260817-cp312-abi3-pyemscripten_2026_0_wasm32.whl (7.3 MB view details)

Uploaded Aug 17, 2026 CPython 3.12+PyEmscripten 2026.0 wasm32

onnx_weekly-1.23.0.dev20260817-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (8.8 MB view details)

Uploaded Aug 17, 2026 CPython 3.12+manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

onnx_weekly-1.23.0.dev20260817-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (8.6 MB view details)

Uploaded Aug 17, 2026 CPython 3.12+manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

onnx_weekly-1.23.0.dev20260817-cp312-abi3-macosx_13_0_universal2.whl (9.6 MB view details)

Uploaded Aug 17, 2026 CPython 3.12+macOS 13.0+ universal2 (ARM64, x86-64)

onnx_weekly-1.23.0.dev20260817-cp311-cp311-win_arm64.whl (8.0 MB view details)

Uploaded Aug 17, 2026 CPython 3.11Windows ARM64

onnx_weekly-1.23.0.dev20260817-cp311-cp311-win_amd64.whl (7.8 MB view details)

Uploaded Aug 17, 2026 CPython 3.11Windows x86-64

onnx_weekly-1.23.0.dev20260817-cp311-cp311-win32.whl (7.7 MB view details)

Uploaded Aug 17, 2026 CPython 3.11Windows x86

onnx_weekly-1.23.0.dev20260817-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (8.8 MB view details)

Uploaded Aug 17, 2026 CPython 3.11manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

onnx_weekly-1.23.0.dev20260817-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (8.6 MB view details)

Uploaded Aug 17, 2026 CPython 3.11manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

onnx_weekly-1.23.0.dev20260817-cp311-cp311-macosx_13_0_universal2.whl (9.6 MB view details)

Uploaded Aug 17, 2026 CPython 3.11macOS 13.0+ universal2 (ARM64, x86-64)

onnx_weekly-1.23.0.dev20260817-cp310-cp310-win_amd64.whl (7.8 MB view details)

Uploaded Aug 17, 2026 CPython 3.10Windows x86-64

onnx_weekly-1.23.0.dev20260817-cp310-cp310-win32.whl (7.7 MB view details)

Uploaded Aug 17, 2026 CPython 3.10Windows x86

onnx_weekly-1.23.0.dev20260817-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (8.8 MB view details)

Uploaded Aug 17, 2026 CPython 3.10manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

onnx_weekly-1.23.0.dev20260817-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (8.6 MB view details)

Uploaded Aug 17, 2026 CPython 3.10manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

onnx_weekly-1.23.0.dev20260817-cp310-cp310-macosx_13_0_universal2.whl (9.6 MB view details)

Uploaded Aug 17, 2026 CPython 3.10macOS 13.0+ universal2 (ARM64, x86-64)

File details

Details for the file onnx_weekly-1.23.0.dev20260817.tar.gz.

File metadata

Download URL: onnx_weekly-1.23.0.dev20260817.tar.gz
Upload date: Aug 17, 2026
Size: 6.0 MB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.14

File hashes

Hashes for onnx_weekly-1.23.0.dev20260817.tar.gz
Algorithm	Hash digest
SHA256	`860d42175f474562fe05236f168ba2340c66b566119750792caa8cada18c74da`
MD5	`d2968d793a99375018cfd9b530312bbe`
BLAKE2b-256	`9e44f24ce74b129bbcbeac50e07e30ee807f3abaa711f81873fe2afe110e484d`

Algorithm	Hash digest
SHA256	`7356e0ecb2fd4d0735a18aaa660fc28f0de337de4bb7034b40ad95ea82a9f367`
MD5	`f87beacf4151ff45f656555cd5c72c09`
BLAKE2b-256	`51838a298d46f464da93c9e13737f5b3e9d1a23cb2d9feef8b6d3d273c2db2e0`

Algorithm	Hash digest
SHA256	`06825d130ad0bd6d710101dbc3b5dc058a2fa3690935c131d3bb3f3a418319ff`
MD5	`3d5178a268f2906fcbfa87bd5bb98f6b`
BLAKE2b-256	`7a3647ce73cbb7087074ec8d407f73ef822f4e6ce1fceff29d2d481d648b1918`

Algorithm	Hash digest
SHA256	`5a110f8a1235051a93dc3ce2e5c2fb08ed106a765fa2048a84c307f34f4798cb`
MD5	`5e82d534c4b39dd233154e50ab96e73a`
BLAKE2b-256	`4a788f52bc4ccf4c932e9cd846998ce718d60a0b050475fe4f8e5025cfee5476`

Algorithm	Hash digest
SHA256	`f773df309e601347faf22317afecaaf0887085b8dd273da9e5becc5c88a7ca6a`
MD5	`86a5c39affde82612c40a70b358a5e86`
BLAKE2b-256	`9316ab9cea1ef665a7fa4ba2bac4979722aec14f3da7d377ee89914eb04cd36b`

Algorithm	Hash digest
SHA256	`26343783ebdab0b4b4f0ff2c4ae7268bf1f636369dab2902e365c0606d743ceb`
MD5	`bb86c339e62ad6841083e15cd14d5ad5`
BLAKE2b-256	`bb4e872021cd8600851bacdc5f98955ae4e2a70c357467a3f87ec59ade1ff941`

Algorithm	Hash digest
SHA256	`e25dfe10f476e815412dfc311edec90a155fb69be58122ba12e982903b49ba58`
MD5	`eb485923041932c54b1a70aaf0867772`
BLAKE2b-256	`efb2d79a1695cd4af96595c2ececdad4faf35cd0c4fd4d85c749c1d98221e1a8`

Algorithm	Hash digest
SHA256	`26c20262d3ffeca223f46a92476315c0065f3092a2f8cabfb48d4b3b591f363d`
MD5	`6c6ed3469bd494282a1f31c296c53c51`
BLAKE2b-256	`57c7348267f6b47e534ffa359f21653fb69f361acfb9f28fd2033d0bb921baaf`

Algorithm	Hash digest
SHA256	`70eec883dac2022448b609c2870510d0d7b945d365c402fa4b72db8d4efbb05e`
MD5	`4cc74dbbd66ee3a292a3fe5a9226ce92`
BLAKE2b-256	`a39cb195f33771887717fd4573dc12d364a3821215ef21b9e2218a42c9eb9403`

Algorithm	Hash digest
SHA256	`eee895265f0cae798d94e034aec55a2919a6a889e5e22137e267f1f6b974f3de`
MD5	`95ac99d55fcebb308087396f41be98be`
BLAKE2b-256	`e911dcb732ca671023278f15c9f939daa10b5321370f17d39f525ee7832c60b5`

Algorithm	Hash digest
SHA256	`d745b1467293256a8ab5862c325e553d8e164a7c89f20b3ef3cf9fa3a52ec741`
MD5	`1106382fc0fe6066d7c30fb98f8569bd`
BLAKE2b-256	`e9ec17ca27c34a47e8c167e509d844da585cbe8ea8245a48e580dab9b3d520a3`

Algorithm	Hash digest
SHA256	`30ab14fd43b30c4f1ae36258bac0f552bd7949990fca168a55b5bd051980cacb`
MD5	`d1c722e4d7e52df8a870e5c67b6a81b6`
BLAKE2b-256	`5eb91bcc73642d295824d5df57489ca87ba0de3a0a6cc7e0ff6b2422bce10c74`

Algorithm	Hash digest
SHA256	`9390ed019355a233a0ae81b392579cf3c9a0cdd5edcbeef30ca52a535443e0a1`
MD5	`a768471c3827b9f45f20aa1ee057d965`
BLAKE2b-256	`1324f457d73ad21d0bf875ecccf4ef75ca707ba2fbd28c3fe19dc3bce50426b5`

Algorithm	Hash digest
SHA256	`bd18a2d52a09e99d2b591591062a4a5472e3932a05ea9e7b09868e22cb87c9f9`
MD5	`585fd79c722009e0a738165ee8bf2da8`
BLAKE2b-256	`86bc3702374ef5fd13c5dc6c61126a9c8f182bebd67cb94f2e6328648839ec8b`

Algorithm	Hash digest
SHA256	`b72ffc88692edda759412a34f1b993aabba522bc18eb02a718e9fcbca3a643fc`
MD5	`513fc2b1595cda1f9f4b999846d7d04d`
BLAKE2b-256	`3e805d2919289a6e1b6e7e769eb63c76f0de200bb27e09b4051b47ea266192f1`

Algorithm	Hash digest
SHA256	`5c961b8d2f5e5d11b807b1680c9657e1a0ac7193d5398db82a8994a207b03da6`
MD5	`eeec582fa4f2c83ae529d9b464331526`
BLAKE2b-256	`0792118a23beaf9df570f7de67a384f25e2991cc4b6a270f1a728e9d58c29044`

Algorithm	Hash digest
SHA256	`a16c08ddc4b746d1814843c153e97200a8191aa17ed95d64ac9f128e528c0a71`
MD5	`f118f29403aa8d0d0131b64ab892742e`
BLAKE2b-256	`9f1910224b7963c0a4efd47d67df29203f187701f0ff66340598276f1b31774b`

Algorithm	Hash digest
SHA256	`6f530a618cdca5b6e087f86a65d86b48211138c3cf5356527846015441b9b63b`
MD5	`115745a330fc4f2ca6cc6124f05652f0`
BLAKE2b-256	`39e97f4629aea125df1762c82d29bcc0838d8ba866c317359b105ca956adaf4c`

Algorithm	Hash digest
SHA256	`1c7f546936d848fad40527a11edbb162da8c68e0fde2e6a0712f5798f0279353`
MD5	`60da7bc1480f40b638f2f0a9803927a4`
BLAKE2b-256	`e37e5cd2e7463a9ab9c62f68162bacef939764befd9f8c5f0db9d21dded649ce`

Algorithm	Hash digest
SHA256	`dfb8ce2ddf125cef1415076ef52a81fd6b028f4dcc83cff7d2db49cd35217573`
MD5	`98e5c0185887f026da04376c74cd80ce`
BLAKE2b-256	`eb2c5b805377cf61d0b24a788315b7c2af3e26115eeccf68012d647abd6a1376`

Algorithm	Hash digest
SHA256	`bb443eeb9164d94859e0072d15f73c8718507c781de8ebd862135985ec0db2a9`
MD5	`0d0e6e9c7090ccf72acd7d475f6f4b95`
BLAKE2b-256	`ed08dd1e86e66cfe5153e606665971068bf8e9d9abfa8675abd076f8f67e5bde`

onnx-weekly 1.23.0.dev20260817

Use ONNX

Learn about the ONNX spec

Programming utilities for working with ONNX Graphs

Contribute

Community meetings

Discuss

Follow Us

Roadmap

Installation

Python ABI3 Compatibility

Testing

Development

Reproducible Build Support

Why this matters

License

Trademark

Code of Conduct

Project links

Key dates

Owner

3 maintainers

Credits

GitHub Statistics

License expression

Requires

Provides Extra

Classifiers

Download files

Source Distribution

Built Distributions

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

File metadata

File hashes

Provenance

File details

Algorithm	Hash digest
SHA256	`8b8d9d519841440fc52313de154fc8f38442e8d413ce151b86ba6aa19c8d07d7`
MD5	`562aa531e493e8e3829b477b175f8280`
BLAKE2b-256	`3f674399c02e92132725e532b05f14d49e6738e0f87e848ba6e50fbe544409be`

Algorithm	Hash digest
SHA256	`c58910d4a6a1b996beed3d0615f3657ab2b5c91e6e8a6a51d9525c604a213336`
MD5	`b225081fe15a9167683d382e22d3ae16`
BLAKE2b-256	`1961392b09f41964411bd2d63a4112ee6143e0bd04ab53044eac1f7625774542`

Algorithm	Hash digest
SHA256	`da975217cc014c3f6ce9c35137a2a75128e76fdc4bb51b5e33bfe50b11668e83`
MD5	`885065d3e909ba28b2772534d882617a`
BLAKE2b-256	`ba9a938c9f264ea90c049191dbba0002bcce27e36592446eb4176aaa0d7f5493`