Folders and files

Name		Name	Last commit message	Last commit date
Latest commit History 3,465 Commits
.github		.github
LICENSES		LICENSES
cmake		cmake
community		community
docs		docs
examples		examples
onnx		onnx
tools		tools
workflow_scripts		workflow_scripts
.clang-format		.clang-format
.clang-tidy		.clang-tidy
.editorconfig		.editorconfig
.git-blame-ignore-revs		.git-blame-ignore-revs
.gitattributes		.gitattributes
.gitignore		.gitignore
.gitmodules		.gitmodules
.lintrunner.toml		.lintrunner.toml
CMakeLists.txt		CMakeLists.txt
CODEOWNERS		CODEOWNERS
CODE_OF_CONDUCT.md		CODE_OF_CONDUCT.md
CONTRIBUTING.md		CONTRIBUTING.md
CPPLINT.cfg		CPPLINT.cfg
INSTALL.md		INSTALL.md
LICENSE		LICENSE
MANIFEST.in		MANIFEST.in
README.md		README.md
RELEASE-MANAGEMENT.md		RELEASE-MANAGEMENT.md
REUSE.toml		REUSE.toml
SECURITY.md		SECURITY.md
VERSION_NUMBER		VERSION_NUMBER
backend.py		backend.py
codecov.yml		codecov.yml
pixi.lock		pixi.lock
pixi.toml		pixi.toml
pyproject.toml		pyproject.toml
requirements-dev.txt		requirements-dev.txt
requirements-lintrunner.txt		requirements-lintrunner.txt
requirements-min.txt		requirements-min.txt
requirements-reference.txt		requirements-reference.txt
requirements-release_build.txt		requirements-release_build.txt
requirements-release_test.txt		requirements-release_test.txt
requirements.txt		requirements.txt
setup.py		setup.py

Repository files navigation

Open Neural Network Exchange (ONNX) is an open ecosystem that empowers AI developersto 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 standarddata types. Currently we focus on the capabilities needed for inferencing (scoring).

ONNX iswidely 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

Programming utilities for working with ONNX Graphs

Contribute

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

Check out ourcontribution guide to get started.

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

Community meetings

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

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

Discuss

We encourage you to openIssues, or useSlack (If you have not joined yet, please use thislink 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 foundhere

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 foundhere

Python ABI3 Compatibility

This package providesabi3-compatible wheels, allowing a single binary wheel to work across multiple Python versions (from 3.12 onwards).

Testing

ONNX usespytest as test driver. In order to run tests, you will first need to installpytest:

pip install pytest

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

pytest

Development

Check out thecontributor guide for instructions.

Reproducible Builds (Linux)

This project provides reproducible builds for Linux.

Areproducible 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 theSOURCE_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.