OpenVINO™ Execution Provider for ONNX Runtime
===============================================
`OpenVINO™ Execution Provider for ONNX Runtime <https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html>`_ is a product designed for ONNX Runtime developers who want to get started with OpenVINO™ in their inferencing applications. This product delivers `OpenVINO™ <https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html>`_ inline optimizations which enhance inferencing performance with minimal code modifications.
OpenVINO™ Execution Provider for ONNX Runtime accelerates inference across many `AI models <https://github.com/onnx/models>`_ on a variety of Intel® hardware such as:
- Intel® CPUs
- Intel® integrated GPUs
- Intel® discrete GPUs
Installation
------------
Requirements
^^^^^^^^^^^^
- Ubuntu 20.06, or Windows 10 - 64 bit
- Python 3.9,3.10,3,11 for Linux and Python3.10 and Python 3.11 for Windows
- OpenVINO 2023.3.0 Version only
This package supports:
- Intel® CPUs
- Intel® integrated GPUs
- Intel® discrete GPUs
``pip3 install onnxruntime-openvino``
Please install OpenVINO™ PyPi Package separately for Windows.
For installation instructions on Windows please refer to `OpenVINO™ Execution Provider for ONNX Runtime for Windows <https://github.com/intel/onnxruntime/releases/>`_.
**OpenVINO™ Execution Provider for ONNX Runtime** Linux Wheels comes with pre-built libraries of OpenVINO™ version 2023.3.0 eliminating the need to install OpenVINO™ separately. The OpenVINO™ libraries are prebuilt with CXX11_ABI flag set to 0.
For more details on build and installation please refer to `Build <https://onnxruntime.ai/docs/build/eps.html#openvino>`_.
Usage
^^^^^
By default, Intel® CPU is used to run inference. However, you can change the default option to either Intel® integrated or discrete GPU.
Invoke `the provider config device type argument <https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html#summary-of-options>`_ to change the hardware on which inferencing is done.
For more API calls and environment variables, see `Usage <https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html#configuration-options>`_.
Samples
^^^^^^^^
To see what you can do with **OpenVINO™ Execution Provider for ONNX Runtime**, explore the demos located in the `Examples <https://github.com/microsoft/onnxruntime-inference-examples/tree/main/python/OpenVINO_EP>`_.
License
^^^^^^^^
**OpenVINO™ Execution Provider for ONNX Runtime** is licensed under `MIT <https://github.com/microsoft/onnxruntime/blob/main/LICENSE>`_.
By contributing to the project, you agree to the license and copyright terms therein
and release your contribution under these terms.
Support
^^^^^^^^
Please submit your questions, feature requests and bug reports via `GitHub Issues <https://github.com/microsoft/onnxruntime/issues>`_.
How to Contribute
^^^^^^^^^^^^^^^^^^
We welcome community contributions to **OpenVINO™ Execution Provider for ONNX Runtime**. If you have an idea for improvement:
* Share your proposal via `GitHub Issues <https://github.com/microsoft/onnxruntime/issues>`_.
* Submit a `Pull Request <https://github.com/microsoft/onnxruntime/pulls>`_.
Raw data
{
"_id": null,
"home_page": "https://onnxruntime.ai",
"name": "onnxruntime-openvino",
"maintainer": "",
"docs_url": null,
"requires_python": "",
"maintainer_email": "",
"keywords": "onnx machine learning",
"author": "Microsoft Corporation",
"author_email": "onnxruntime@microsoft.com",
"download_url": "https://github.com/microsoft/onnxruntime/tags",
"platform": null,
"description": "OpenVINO\u2122 Execution Provider for ONNX Runtime\r\n===============================================\r\n\r\n`OpenVINO\u2122 Execution Provider for ONNX Runtime <https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html>`_ is a product designed for ONNX Runtime developers who want to get started with OpenVINO\u2122 in their inferencing applications. This product delivers `OpenVINO\u2122 <https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html>`_ inline optimizations which enhance inferencing performance with minimal code modifications.\r\n\r\nOpenVINO\u2122 Execution Provider for ONNX Runtime accelerates inference across many `AI models <https://github.com/onnx/models>`_ on a variety of Intel\u00ae hardware such as:\r\n - Intel\u00ae CPUs\r\n - Intel\u00ae integrated GPUs\r\n - Intel\u00ae discrete GPUs\r\n\r\nInstallation\r\n------------\r\n\r\nRequirements\r\n^^^^^^^^^^^^\r\n\r\n- Ubuntu 20.06, or Windows 10 - 64 bit\r\n- Python 3.9,3.10,3,11 for Linux and Python3.10 and Python 3.11 for Windows\r\n- OpenVINO 2023.3.0 Version only\r\n\r\nThis package supports:\r\n - Intel\u00ae CPUs\r\n - Intel\u00ae integrated GPUs\r\n - Intel\u00ae discrete GPUs\r\n\r\n``pip3 install onnxruntime-openvino``\r\n\r\nPlease install OpenVINO\u2122 PyPi Package separately for Windows.\r\nFor installation instructions on Windows please refer to `OpenVINO\u2122 Execution Provider for ONNX Runtime for Windows <https://github.com/intel/onnxruntime/releases/>`_.\r\n\r\n**OpenVINO\u2122 Execution Provider for ONNX Runtime** Linux Wheels comes with pre-built libraries of OpenVINO\u2122 version 2023.3.0 eliminating the need to install OpenVINO\u2122 separately. The OpenVINO\u2122 libraries are prebuilt with CXX11_ABI flag set to 0.\r\n\r\nFor more details on build and installation please refer to `Build <https://onnxruntime.ai/docs/build/eps.html#openvino>`_.\r\n\r\nUsage\r\n^^^^^\r\n\r\nBy default, Intel\u00ae CPU is used to run inference. However, you can change the default option to either Intel\u00ae integrated or discrete GPU.\r\nInvoke `the provider config device type argument <https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html#summary-of-options>`_ to change the hardware on which inferencing is done.\r\n\r\nFor more API calls and environment variables, see `Usage <https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html#configuration-options>`_.\r\n\r\nSamples\r\n^^^^^^^^\r\n\r\nTo see what you can do with **OpenVINO\u2122 Execution Provider for ONNX Runtime**, explore the demos located in the `Examples <https://github.com/microsoft/onnxruntime-inference-examples/tree/main/python/OpenVINO_EP>`_.\r\n\r\nLicense\r\n^^^^^^^^\r\n\r\n**OpenVINO\u2122 Execution Provider for ONNX Runtime** is licensed under `MIT <https://github.com/microsoft/onnxruntime/blob/main/LICENSE>`_.\r\nBy contributing to the project, you agree to the license and copyright terms therein\r\nand release your contribution under these terms.\r\n\r\nSupport\r\n^^^^^^^^\r\n\r\nPlease submit your questions, feature requests and bug reports via `GitHub Issues <https://github.com/microsoft/onnxruntime/issues>`_.\r\n\r\nHow to Contribute\r\n^^^^^^^^^^^^^^^^^^\r\n\r\nWe welcome community contributions to **OpenVINO\u2122 Execution Provider for ONNX Runtime**. If you have an idea for improvement:\r\n\r\n* Share your proposal via `GitHub Issues <https://github.com/microsoft/onnxruntime/issues>`_.\r\n* Submit a `Pull Request <https://github.com/microsoft/onnxruntime/pulls>`_.\r\n",
"bugtrack_url": null,
"license": "MIT License",
"summary": "ONNX Runtime is a runtime accelerator for Machine Learning models",
"version": "1.17.1",
"project_urls": {
"Download": "https://github.com/microsoft/onnxruntime/tags",
"Homepage": "https://onnxruntime.ai"
},
"split_keywords": [
"onnx",
"machine",
"learning"
],
"urls": [
{
"comment_text": "",
"digests": {
"blake2b_256": "73e7f5b6fcc537088db5cd7c8c9f5e21269467116b3a9f8e621b1aaaf79bfa47",
"md5": "84726f2cc90f28db65f3518e147892a9",
"sha256": "5152b5e56e83e022ced2986700d68dd8ba7b1466761725ce774f679c5710ab87"
},
"downloads": -1,
"filename": "onnxruntime_openvino-1.17.1-cp310-cp310-win_amd64.whl",
"has_sig": false,
"md5_digest": "84726f2cc90f28db65f3518e147892a9",
"packagetype": "bdist_wheel",
"python_version": "cp310",
"requires_python": null,
"size": 6738768,
"upload_time": "2024-03-08T14:52:14",
"upload_time_iso_8601": "2024-03-08T14:52:14.475848Z",
"url": "https://files.pythonhosted.org/packages/73/e7/f5b6fcc537088db5cd7c8c9f5e21269467116b3a9f8e621b1aaaf79bfa47/onnxruntime_openvino-1.17.1-cp310-cp310-win_amd64.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": "",
"digests": {
"blake2b_256": "8d2c5b46e5929fe1dfc559954c70336bf1c7383df4cd808a89f7bcc269eaa224",
"md5": "ea1cc28c3528e35063b944f15194e943",
"sha256": "21133a701bb07ea19e01f48b8c23beee575f2e879f49173843f275d7c91a625a"
},
"downloads": -1,
"filename": "onnxruntime_openvino-1.17.1-cp311-cp311-win_amd64.whl",
"has_sig": false,
"md5_digest": "ea1cc28c3528e35063b944f15194e943",
"packagetype": "bdist_wheel",
"python_version": "cp311",
"requires_python": null,
"size": 6738827,
"upload_time": "2024-03-08T14:52:17",
"upload_time_iso_8601": "2024-03-08T14:52:17.689605Z",
"url": "https://files.pythonhosted.org/packages/8d/2c/5b46e5929fe1dfc559954c70336bf1c7383df4cd808a89f7bcc269eaa224/onnxruntime_openvino-1.17.1-cp311-cp311-win_amd64.whl",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2024-03-08 14:52:14",
"github": true,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"github_user": "microsoft",
"github_project": "onnxruntime",
"travis_ci": false,
"coveralls": false,
"github_actions": true,
"lcname": "onnxruntime-openvino"
}