ONNX Runtime
Project record
ONNX Runtime is Microsoft's open-source, cross-platform engine for running and accelerating machine-learning models in the ONNX format. It runs models exported from frameworks such as PyTorch and TensorFlow/Keras and from classical libraries such as scikit-learn, LightGBM, and XGBoost, applying graph optimizations and hardware-specific execution providers; it also offers accelerated training for transformer models on NVIDIA GPUs.15
- Repository: Repository (external site: github.com)
- Documentation: Documentation (external site: onnxruntime.ai)
- License: LICENSE (MIT) (external site: github.com)
- Release notes: Releases (external site: github.com)
Availability and license
Overall availability
Documented as available to the general public. Access conditions and license terms may still apply.13
Availability is separate from permission: read the license before using or redistributing.
The README states that the project may collect usage data and send it to Microsoft, and refers to the repository's privacy statement for details.1
Public materials checklist
| Item | Status | Notes and evidence |
|---|---|---|
| Source codeIs the source code publicly readable? | Public | 1 |
| DocumentationIs user documentation published? | Public | Usage documentation and tutorials are published at onnxruntime.ai/docs.13 |
| InstallationAre installation instructions or packages publicly available? | Public | Packages are published for pip, NuGet, npm, Maven Central, and CocoaPods, with separate GPU builds (CUDA, DirectML) where applicable.3 |
| Supported platformsAre supported operating systems or hardware documented? | Public | Windows, Linux, macOS, Android, iOS, and web browsers; execution providers cover NVIDIA CUDA and TensorRT, Intel OpenVINO and oneDNN, DirectML, Qualcomm QNN, Apple Core ML, and WebGPU.34 |
| Release statusAre versioned releases published? | Public | Versioned releases are published on GitHub and PyPI; version 1.30.0 was released on PyPI on September 10, 2026.15 |
What it is useful for
Deploying trained models for inference on servers, desktops, mobile devices, and in web browsers, with bindings for Python, C#, C/C++, Java, JavaScript, Objective-C, and Kotlin.3
Organization context
U.S. eligibility
Eligible · basis: U.S. headquarters
Microsoft Corporation holds the copyright, publishes the project in its microsoft GitHub organization, and is listed as the package author on PyPI. Microsoft Corporation lists Redmond, Washington as its address on the cover page of its Form 10-K for fiscal year 2026.2156
Sources
This listing is not an endorsement, a safety assessment, or a federal approval.