Skip to main content

OpenVINO™ Execution Provider for ONNX Runtime is a product designed for ONNX Runtime developers who want to get started with OpenVINO™ in their inferencing applications. This product delivers OpenVINO™ inline optimizations which enhance inferencing performance with minimal code modifications.

OpenVINO™ Execution Provider for ONNX Runtime accelerates inference across many AI models on a variety of Intel® hardware such as:
  • Intel® CPUs

  • Intel® integrated GPUs

  • Intel® discrete GPUs

  • Intel® integrated NPUs

Installation

Requirements

  • Ubuntu 18.04 or above, or Windows 10 or above - 64 bit

  • Python 3.11, 3.12, 3.13 and 3.14 for Windows and Linux

This package supports:
  • Intel® CPUs

  • Intel® integrated GPUs

  • Intel® discrete GPUs

  • Intel® integrated NPUs

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.

OpenVINO™ Execution Provider for ONNX Runtime Linux Wheels comes with pre-built libraries of OpenVINO™ version 2025.4.1 eliminating the need to install OpenVINO™ separately.

For more details on build and installation please refer to Build.

Usage

By default, Intel® CPU is used to run inference. However, you can change the default option to either Intel® integrated GPU, discrete GPU, integrated NPU. Invoke the provider config device type argument to change the hardware on which inferencing is done.

For more API calls and environment variables, see Usage.

Samples

To see what you can do with OpenVINO™ Execution Provider for ONNX Runtime, explore the demos located in the Examples.

License

OpenVINO™ Execution Provider for ONNX Runtime is licensed under MIT. 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.

How to Contribute

We welcome community contributions to OpenVINO™ Execution Provider for ONNX Runtime. If you have an idea for improvement:

Release files for onnxruntime-openvino 1.24.1

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Built distributions (wheels)

Table of built distributions (wheels) for onnxruntime-openvino 1.24.1
File
onnxruntime_openvino-1.24.1-cp313-cp313-win_amd64.whl CPython 3.13 CPython 3.13 Windows x86-64 Details
onnxruntime_openvino-1.24.1-cp313-cp313-manylinux_2_28_x86_64.whl CPython 3.13 CPython 3.13 Linux glibc 2.28+ x86-64 Details
onnxruntime_openvino-1.24.1-cp312-cp312-win_amd64.whl CPython 3.12 CPython 3.12 Windows x86-64 Details
onnxruntime_openvino-1.24.1-cp312-cp312-manylinux_2_28_x86_64.whl CPython 3.12 CPython 3.12 Linux glibc 2.28+ x86-64 Details
onnxruntime_openvino-1.24.1-cp311-cp311-win_amd64.whl CPython 3.11 CPython 3.11 Windows x86-64 Details
onnxruntime_openvino-1.24.1-cp311-cp311-manylinux_2_28_x86_64.whl CPython 3.11 CPython 3.11 Linux glibc 2.28+ x86-64 Details

Total release size: 294.3 MB

Release files / onnxruntime_openvino-1.24.1-cp313-cp313-win_amd64.whl

Download URL onnxruntime_openvino-1.24.1-cp313-cp313-win_amd64.whl
Size 13.7 MB
Tags CPython 3.13 Windows x86-64
SHA-256 checksum
How to use checksums
434bf49aa71393c577a456c9d76c98e6d6958a833fa0876793e3d5437b5a511a
BLAKE2b-256 checksum
How to use checksums
3e9246ae2cd565961a89189900f385bb2f13a9fa731ea4674001d23720fbb1e0
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.8.13

Release files / onnxruntime_openvino-1.24.1-cp313-cp313-manylinux_2_28_x86_64.whl

Download URL onnxruntime_openvino-1.24.1-cp313-cp313-manylinux_2_28_x86_64.whl
Size 84.4 MB
Tags CPython 3.13 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
2c3bb73e68ac27f4891af8a595c1faf574ec68b772e6583c90a0b997a1822782
BLAKE2b-256 checksum
How to use checksums
0807f225999919f56506b603aaa3ff837ad563ab26f86906ed7fa7e5abcd849e
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.8.13

Release files / onnxruntime_openvino-1.24.1-cp312-cp312-win_amd64.whl

Download URL onnxruntime_openvino-1.24.1-cp312-cp312-win_amd64.whl
Size 13.7 MB
Tags CPython 3.12 Windows x86-64
SHA-256 checksum
How to use checksums
f186335a9c9b255633275290da7521d3d4d14c7773fee3127bfa040234d3fa5a
BLAKE2b-256 checksum
How to use checksums
5937d301f2c68b19a9485ed5db3047e0fb52478f3e73eb08c7d2a7c61be7cc1c
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.8.13

Release files / onnxruntime_openvino-1.24.1-cp312-cp312-manylinux_2_28_x86_64.whl

Download URL onnxruntime_openvino-1.24.1-cp312-cp312-manylinux_2_28_x86_64.whl
Size 84.4 MB
Tags CPython 3.12 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
d617fac2f59a6ab5ea59a788c3e1592240a129642519aaeaa774761dfe35150e
BLAKE2b-256 checksum
How to use checksums
50cf17ba72de2df0fcba349937d2788f154397bbc2d1a2d67772a97e26f6bc5f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.8.13

Release files / onnxruntime_openvino-1.24.1-cp311-cp311-win_amd64.whl

Download URL onnxruntime_openvino-1.24.1-cp311-cp311-win_amd64.whl
Size 13.7 MB
Tags CPython 3.11 Windows x86-64
SHA-256 checksum
How to use checksums
8042698232bf67f1f6b219c2b07728d7ae7ddff17d8524588de3675480609aef
BLAKE2b-256 checksum
How to use checksums
aa73619bb416bbfc40aebdd493fd6800d2637359294fe683d8a6bae3ff8d869a
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.8.13

Release files / onnxruntime_openvino-1.24.1-cp311-cp311-manylinux_2_28_x86_64.whl

Download URL onnxruntime_openvino-1.24.1-cp311-cp311-manylinux_2_28_x86_64.whl
Size 84.4 MB
Tags CPython 3.11 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
3007c803634cc69c6d52af1dea7ce729d9bb62b9a11070fd2f959119199007a8
BLAKE2b-256 checksum
How to use checksums
991669ca742f0b65c40d4de3ff44bb6abc23c47b23e932bc901116176ae69922
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/4.0.1 CPython/3.8.13

Release history Release notifications | RSS feed

This release

1.24.1 This release

6 release files

1.23.0

8 release files

1.22.0

8 release files

1.20.0

5 release files

1.19.0

5 release files

1.18.0

5 release files

1.16.0

4 release files

1.15.0

4 release files

1.14.0

4 release files

1.12.0

4 release files

1.11.0

4 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page