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 here

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 Builds (Linux)

This project provides reproducible builds for Linux.

A reproducible build means that the same source code will always produce identical binary outputs, no matter who builds it or where it is built.

To achieve this, we use the SOURCE_DATE_EPOCH standard. This ensures that build timestamps and other time-dependent information are fixed, making the output bit-for-bit identical across different environments.

Why this matters

Transparency: Anyone can verify that the distributed binaries were created from the published source code.
Security: Prevents tampering or hidden changes in the build process.
Trust: Users can be confident that the binaries they download are exactly what the maintainers intended.

If you prefer, you can use the prebuilt reproducible binaries instead of building from source yourself.

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.dev20260713.tar.gz (12.2 MB view details)

Uploaded Jul 13, 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.dev20260713-cp314-cp314t-win_arm64.whl (18.6 MB view details)

Uploaded Jul 13, 2026 CPython 3.14tWindows ARM64

onnx_weekly-1.23.0.dev20260713-cp314-cp314t-win_amd64.whl (18.5 MB view details)

Uploaded Jul 13, 2026 CPython 3.14tWindows x86-64

onnx_weekly-1.23.0.dev20260713-cp314-cp314t-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (19.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.14tmanylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

onnx_weekly-1.23.0.dev20260713-cp314-cp314t-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (19.1 MB view details)

Uploaded Jul 13, 2026 CPython 3.14tmanylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

onnx_weekly-1.23.0.dev20260713-cp314-cp314t-macosx_12_0_universal2.whl (20.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.14tmacOS 12.0+ universal2 (ARM64, x86-64)

onnx_weekly-1.23.0.dev20260713-cp312-abi3-win_arm64.whl (18.6 MB view details)

Uploaded Jul 13, 2026 CPython 3.12+Windows ARM64

onnx_weekly-1.23.0.dev20260713-cp312-abi3-win_amd64.whl (18.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.12+Windows x86-64

onnx_weekly-1.23.0.dev20260713-cp312-abi3-win32.whl (18.3 MB view details)

Uploaded Jul 13, 2026 CPython 3.12+Windows x86

onnx_weekly-1.23.0.dev20260713-cp312-abi3-pyemscripten_2025_0_wasm32.whl (17.2 MB view details)

Uploaded Jul 13, 2026 CPython 3.12+PyEmscripten 2025.0 wasm32

onnx_weekly-1.23.0.dev20260713-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (19.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.12+manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

onnx_weekly-1.23.0.dev20260713-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (19.1 MB view details)

Uploaded Jul 13, 2026 CPython 3.12+manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

onnx_weekly-1.23.0.dev20260713-cp312-abi3-macosx_12_0_universal2.whl (20.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.12+macOS 12.0+ universal2 (ARM64, x86-64)

onnx_weekly-1.23.0.dev20260713-cp311-cp311-win_arm64.whl (18.6 MB view details)

Uploaded Jul 13, 2026 CPython 3.11Windows ARM64

onnx_weekly-1.23.0.dev20260713-cp311-cp311-win_amd64.whl (18.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.11Windows x86-64

onnx_weekly-1.23.0.dev20260713-cp311-cp311-win32.whl (18.3 MB view details)

Uploaded Jul 13, 2026 CPython 3.11Windows x86

onnx_weekly-1.23.0.dev20260713-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (19.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.11manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

onnx_weekly-1.23.0.dev20260713-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (19.1 MB view details)

Uploaded Jul 13, 2026 CPython 3.11manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

onnx_weekly-1.23.0.dev20260713-cp311-cp311-macosx_12_0_universal2.whl (20.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.11macOS 12.0+ universal2 (ARM64, x86-64)

onnx_weekly-1.23.0.dev20260713-cp310-cp310-win_amd64.whl (18.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.10Windows x86-64

onnx_weekly-1.23.0.dev20260713-cp310-cp310-win32.whl (18.3 MB view details)

Uploaded Jul 13, 2026 CPython 3.10Windows x86

onnx_weekly-1.23.0.dev20260713-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (19.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.10manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

onnx_weekly-1.23.0.dev20260713-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl (19.1 MB view details)

Uploaded Jul 13, 2026 CPython 3.10manylinux: glibc 2.26+ ARM64manylinux: glibc 2.28+ ARM64

onnx_weekly-1.23.0.dev20260713-cp310-cp310-macosx_12_0_universal2.whl (20.4 MB view details)

Uploaded Jul 13, 2026 CPython 3.10macOS 12.0+ universal2 (ARM64, x86-64)

File details

Details for the file onnx_weekly-1.23.0.dev20260713.tar.gz.

File metadata

Download URL: onnx_weekly-1.23.0.dev20260713.tar.gz
Upload date: Jul 13, 2026
Size: 12.2 MB
Tags: Source
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.1.0 CPython/3.13.13

File hashes

Hashes for onnx_weekly-1.23.0.dev20260713.tar.gz
Algorithm	Hash digest
SHA256	`800badd6b71b832def957e430e4080832d9c7ebb0677a438a23917263ca005a3`
MD5	`8644f17e2992c97108b5e49e0a4e5f0f`
BLAKE2b-256	`bfdaf19a533330b460acaa409f545e34f328c380819d78b74e2215596be9b2a9`

Algorithm	Hash digest
SHA256	`00b656fab3f132acd394563c856075708a318d30e67fdca04c68755ba6ddfbed`
MD5	`47e48c28b41d48d95950524a89d9aabf`
BLAKE2b-256	`85fc219716133b7800f2e44d67574031a77fc3755e02950a7bf63ce8aa429ac9`

Algorithm	Hash digest
SHA256	`bccbc32577949b414d5ef992636f00410d52920fba09f992fdcda4b4193c8c58`
MD5	`17587d168b7b9b22a859b05c7a306923`
BLAKE2b-256	`db98bb9319a2d2af2f35340f5158836ec64231fa6dab44e5792e965c344acd37`

Algorithm	Hash digest
SHA256	`c6a5026f3a351d49c46f1f94979e243f225dc005cf6daf277a01f0b4688cf3f8`
MD5	`3a4d59e723e6b1787d5e15a8c547544e`
BLAKE2b-256	`7b804434b3e48e29d8d88cffb3097037258cc6a4c2f0c48c2371e03ccac3d1c1`

Algorithm	Hash digest
SHA256	`80c9f818b004813825d3079fe80b98c1f9b460a493e39a4136dd9648f1ea09e2`
MD5	`a823ba406b32928e7c562b60a05086a9`
BLAKE2b-256	`8223f18669aca15b2c31062b02702555b333dae10e6589204433c41b1023324a`

Algorithm	Hash digest
SHA256	`75d71e15499b22d5c167b4912559751c5aa5f5df1958b16edd13c9af8be963b3`
MD5	`04f5ef3a89c87c9e02750c7daebf0603`
BLAKE2b-256	`e26baa219697ffb4a3a062fd1ed60c9d06553ce08e7b8ef285eb402c51f3ec4e`

Algorithm	Hash digest
SHA256	`893cf653fec6fc6a14ab210517a58842f427a12c04bbf2c63466e948aa926ffd`
MD5	`84822d81927064856e1a77d39e4606d3`
BLAKE2b-256	`0f7fe4fb68d85529c5eaeb76841b53b5ee57cad8352323aee9ff70e4e6fb8f17`

Algorithm	Hash digest
SHA256	`d167dd4a81eef9a0904c4904bf24d7b00d303085a88961b4edf6b500ae52431b`
MD5	`45c7f2522c55449a434e35e8d130005e`
BLAKE2b-256	`0f010a30bc89c39cb13dac1353abbb436c831a405f6f0133fda4e49a7cfe86c0`

Algorithm	Hash digest
SHA256	`4061649ac184f9b372b9e3e447034eabd3070b89b777186210ca5c2fc7679ab9`
MD5	`fe5ddd1bfd1282e0dcee4bc7dd8eb0b0`
BLAKE2b-256	`1df693d38974d70baf44257b22bf7ad4c8c840339c9f0d8e1a96d71ebe79ca40`

Algorithm	Hash digest
SHA256	`c3360ac756cd6f1ffa568aea43564f2d7eb541f95c7857b582253f836133c281`
MD5	`5890c9f5dfdca1fb15f611084b0702b6`
BLAKE2b-256	`fe7473fc2556dc0939c1fb5feec98edafe5590092c489b17d687b7fbda934345`

Algorithm	Hash digest
SHA256	`33c4df29f53dc1e4cfb0b6090f808a4f79d48e49d91fab1da1e2e8b5f2a6c17f`
MD5	`b489a18f0014e9907d9a68b940735054`
BLAKE2b-256	`c944f09d1fa26d284ef7364c82e2407118d21b0702689334533a9fa77100376c`

Algorithm	Hash digest
SHA256	`b43606afd430de6fef2b4e0d46fc8b6cc6064c6c04e42b332e5a594d6c19ac87`
MD5	`6b10c8d68e0183dbd48ac0faafa8cc9c`
BLAKE2b-256	`2d0c9957ac596f7be7bb0b0cf414a400cc9353c7f8e55462654a0b064fdd6d87`

Algorithm	Hash digest
SHA256	`6e5c79c3563281183bf0ed84dce9935bd3e5511cae3b8fbb47b9331db166a107`
MD5	`c8d6dfbb56d1261f642d048286c9a3da`
BLAKE2b-256	`f7136f211f304d55aa5f6d7a0382cb3971b99069c3fac2500fde629731407209`

Algorithm	Hash digest
SHA256	`f258eb4481ecfddb9662cc9fa6b8ff70df8497caff5a9db5f884023cfd44615a`
MD5	`25c20502e25b68f25676be01b38608c6`
BLAKE2b-256	`fbf451f2d2c122e86d154c646ec8f044b99619662d4e53e4dcd1a2c01f7d039e`

Algorithm	Hash digest
SHA256	`a72173e48603bd7e690943d60d18aa20aee85e6bf1b9e1c815c91abe2b65572c`
MD5	`ba0f793d185432df064fbdff44c95996`
BLAKE2b-256	`6aab0a465d9615da8dcc5054e473036197f2ca9d8691e8b8736b8cd1263ca18d`

Algorithm	Hash digest
SHA256	`31c0da4121c55aa78ab8fc0fd0d0edb4da36411ae37160557e8f0887f89b663d`
MD5	`f54de8bb04a4999b4660f07aa99dbdc8`
BLAKE2b-256	`fcadc2d4ebe5cdbbcfb29ad4b5a7be573d3843f78e835f1eb79cd7da5ebee708`

Algorithm	Hash digest
SHA256	`54089c791b121e5585113b057709df26762d24ddb4d5623d790e82f8a11d8186`
MD5	`0053f1728a9aa2f8387fa2bf70088ed2`
BLAKE2b-256	`f3c7b3852445b9168729ada00acfda0db19965a245065613030b67d45ac53f40`

Algorithm	Hash digest
SHA256	`b36b1172e3d8230468983e080102f0505c981253f1b76eb5ad31383c557fdf6b`
MD5	`9c9c32b47fc316c2d3fe45bdebb9c9a1`
BLAKE2b-256	`fd10aedc729684ae025d2e74cf9691ad3f2c5540d2e977e3dd853ff84026d26d`

Algorithm	Hash digest
SHA256	`28dd8caba5c62071acb15cce95c3c21cf8bd6c31272f9ac6d7f43281f0994ac7`
MD5	`2310daad3a02882bb32ed9188eb2f9e3`
BLAKE2b-256	`47cb6401b1d1116582ddfc20dd681db17f4c4481adb72ee1231d857f2e9c7afe`

Algorithm	Hash digest
SHA256	`59585ccde28b1107e81ab972c5f7a09a8f6ab30563ef376118d3e0f349b1903c`
MD5	`075494b4634b3e9ea5bc69658eaf56a5`
BLAKE2b-256	`4f2872da51d6e8fd8e75f13e6fc27e2e001bbb019f18256cc809312c100da9f5`

Algorithm	Hash digest
SHA256	`c958b5484f8c63c21574ee27b54158c9b34047b4244271a09b76bb1655063a9a`
MD5	`1b9196fed3ba35f9abdb697af0f1ad0d`
BLAKE2b-256	`04a8974df023712a3958062e52c0884f6550cf6f18ff10917794d7ad73bf2ebc`

onnx-weekly 1.23.0.dev20260713

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 Builds (Linux)

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	`2fbc4fe4107263bb914411e5ff5b6bab129bf343cc44a8c3b348629c72d85218`
MD5	`cf3196f20e8b8c92072ec446c704fd83`
BLAKE2b-256	`664e34141591be30cd15237f434bc1d90c4df5a3a357063e0306ed7b4c5742ef`

Algorithm	Hash digest
SHA256	`9a9169dffb7d2d2277e5a04b746c6a08c14b0f7ed8cd4c7c64f4e218b46c796c`
MD5	`f1c37a31596f75fe3ad1efdeaef90f68`
BLAKE2b-256	`0fe2b0391f0a62098444e690eea5d3f08bdd025e0b2240f79d62aa18759fd14b`

Algorithm	Hash digest
SHA256	`99a540795f16dd834a6fef851b1700d0585508baff78ac921085d0fb8ec5cade`
MD5	`a66b46d610a680ba839c96ff17f5753f`
BLAKE2b-256	`b433d8fa5c0a191c25f5c277a783a484d6cb73ee8a0b0fbd0598c5e63634ceb0`