Description:
OpenVINO™ Execution Provider For ONNXRuntime v5.7 Release based on the latest OpenVINO™ 2025.1.0 Release and OnnxRuntime 1.22.0 Release
For all the latest information, Refer to our official documentation:
https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html
This release supports ONNXRuntime 1.22.0 with the latest OpenVINO™ 2025.1.0 release.
Please refer to the OpenVINO™ Execution Provider For ONNXRuntime build instructions for information on system pre-requisites as well as instructions to build from source.
https://onnxruntime.ai/docs/build/eps.html#openvino
Modifications:
Supports OpenVINO 2025.1.0.
Enable device-string to LUID mapping in OV EP (C++ API).
Enable NPU compiler-side ONNX QDQ stripping flag in OV EP.
Support for parsing AUTO, HETERO and MULTI from json config
Bug Fixes
Samples:
https://github.com/microsoft/onnxruntime-inference-examples
Python Package:
https://pypi.org/project/onnxruntime-openvino/
Installation and usage Instructions on Windows:
pip install onnxruntime-openvino
/* Steps If using python openvino package to set openvino runtime environment */
pip install openvino==2025.1.0
<Add these 2 lines in the application code>
import onnxruntime.tools.add_openvino_win_libs as utils
utils.add_openvino_libs_to_path()
C# Package:
Download the Microsoft.ML.OnnxRuntime.Managed nuget from the link below
https://www.nuget.org/packages/Microsoft.ML.OnnxRuntime.Managed
and use it with the Intel.ML.OnnxRuntime.OpenVino nuget from the link below
https://www.nuget.org/packages/Intel.ML.OnnxRuntime.OpenVino
ONNXRuntime APIs usage:
Please refer to the link below for Python/C++ APIs:
https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html#configuration-options