ONNX is an open format for machine learning (ML) models that is supported by various ML and DNN frameworks and tools. This format makes it easier to interoperate between frameworks and to maximize the reach of your hardware optimization investments. Learn more about ONNX on [https://onnx.ai](https://onnx.ai) or view the [Github Repo](https://github.com/onnx/onnx).
ONNX Runtime is an open architecture that is continually evolving to adapt to and address the newest developments and challenges in AI and Deep Learning. We will keep ONNX Runtime up to date with the ONNX standard, supporting all ONNX releases with future compatibliity while maintaining backwards compatibility with prior releases.
ONNX Runtime continuously strives to provide top performance for a broad and growing number of usage scenarios in Machine Learning. Our investments focus on these 3 core areas:
ONNX Runtime provides comprehensive support of the ONNX spec and can be used to run all models based on ONNX v1.2.1 and higher. See ONNX version release details [here](https://github.com/onnx/onnx/releases).
ONNX Runtime fully supports the ONNX-ML profile of the ONNX spec for traditional ML scenarios.
## High Performance
You can use ONNX Runtime with both CPU and GPU hardware. You can also plug in additional execution providers to ONNX Runtime. With many graph optimizations and various accelerators, ONNX Runtime can often provide lower latency and higher efficiency compared to other runtimes. This provides smoother end-to-end customer experiences and lower costs from improved machine utilization.
Currently ONNX Runtime supports CUDA and MKL-DNN (with option to build with MKL) for computation acceleration. To add an execution provider, please refer to [this page](docs/AddingExecutionProvider.md).
We are continuously working to integrate new execution providers to provide improvements in latency and efficiency. We have ongoing collaborations to integrate the following with ONNX Runtime:
Looking ahead: To broaden the reach of the runtime, we will continue investments to make ONNX Runtime available and compatible with more platforms. These include but are not limited to:
If you already have an ONNX model, just [install the runtime](#Installation) for your machine to try it out. One easy way to deploy the model on the cloud is by using [Azure Machine Learning](https://azure.microsoft.com/en-us/services/machine-learning-service). See detailed instructions [here](https://docs.microsoft.com/en-us/azure/machine-learning/service/how-to-build-deploy-onnx).
* The OnnxRuntime binaries in CPU packages use OpenMP and depends on the library being available at runtime in the system. For Windows, OpenMP support comes as part of VC runtime. For Linux, the system must have the libgomp.so.1 installed.
* The GPU builds require the CUDA9.1 and cuDNN 7.3 runtime libraries being installed in the system.
For an overview of the high level architecture and key decisions in the technical design of ONNX Runtime, see [Engineering Design](docs/HighLevelDesign.md).
ONNX Runtime is built with an extensible design that makes it versatile to support a wide array of models with high performance.
