Skip to main content

OpenVINO(TM) Runtime

Project description

Open-source software toolkit for optimizing and deploying deep learning models.

DocumentationBlogKey FeaturesTutorialsIntegrationsBenchmarksGenerative AI

PyPI Status Anaconda Status brew Status

PyPI Downloads Anaconda Downloads brew Downloads

  • Inference Optimization: Boost deep learning performance in computer vision, automatic speech recognition, generative AI, natural language processing with large and small language models, and many other common tasks.
  • Flexible Model Support: Use models trained with popular frameworks such as PyTorch, TensorFlow, ONNX, Keras, PaddlePaddle, and JAX/Flax. Directly integrate models built with transformers and diffusers from the Hugging Face Hub using Optimum Intel. Convert and deploy models without original frameworks.
  • Broad Platform Compatibility: Reduce resource demands and efficiently deploy on a range of platforms from edge to cloud. OpenVINO™ supports inference on CPU (x86, ARM), GPU (Intel integrated & discrete GPU) and AI accelerators (Intel NPU).
  • Community and Ecosystem: Join an active community contributing to the enhancement of deep learning performance across various domains.

Check out the OpenVINO Cheat Sheet and Key Features for a quick reference.

Installation

Get your preferred distribution of OpenVINO or use this command for quick installation:

pip install -U openvino

Check system requirements and supported devices for detailed information.

Tutorials and Examples

OpenVINO Quickstart example will walk you through the basics of deploying your first model.

Learn how to optimize and deploy popular models with the OpenVINO Notebooks📚:

Discover more examples in the OpenVINO Samples (Python & C++) and Notebooks (Python).

Here are easy-to-follow code examples demonstrating how to run PyTorch and TensorFlow model inference using OpenVINO:

PyTorch Model

import openvino as ov
import torch
import torchvision

# load PyTorch model into memory
model = torch.hub.load("pytorch/vision", "shufflenet_v2_x1_0", weights="DEFAULT")

# convert the model into OpenVINO model
example = torch.randn(1, 3, 224, 224)
ov_model = ov.convert_model(model, example_input=(example,))

# compile the model for CPU device
core = ov.Core()
compiled_model = core.compile_model(ov_model, 'CPU')

# infer the model on random data
output = compiled_model({0: example.numpy()})

TensorFlow Model

import numpy as np
import openvino as ov
import tensorflow as tf

# load TensorFlow model into memory
model = tf.keras.applications.MobileNetV2(weights='imagenet')

# convert the model into OpenVINO model
ov_model = ov.convert_model(model)

# compile the model for CPU device
core = ov.Core()
compiled_model = core.compile_model(ov_model, 'CPU')

# infer the model on random data
data = np.random.rand(1, 224, 224, 3)
output = compiled_model({0: data})

OpenVINO supports the CPU, GPU, and NPU devices and works with models from PyTorch, TensorFlow, ONNX, TensorFlow Lite, PaddlePaddle, and JAX/Flax frameworks. It includes APIs in C++, Python, C, NodeJS, and offers the GenAI API for optimized model pipelines and performance.

Generative AI with OpenVINO

Get started with the OpenVINO GenAI installation and refer to the detailed guide to explore the capabilities of Generative AI using OpenVINO.

Learn how to run LLMs and GenAI with Samples in the OpenVINO™ GenAI repo. See GenAI in action with Jupyter notebooks: LLM-powered Chatbot and LLM Instruction-following pipeline.

Documentation

User documentation contains detailed information about OpenVINO and guides you from installation through optimizing and deploying models for your AI applications.

Developer documentation focuses on the OpenVINO architecture and describes building and contributing processes.

OpenVINO Ecosystem

OpenVINO Tools

Integrations

  • 🤗Optimum Intel - grab and use models leveraging OpenVINO within the Hugging Face API.
  • Torch.compile - use OpenVINO for Python-native applications by JIT-compiling code into optimized kernels.
  • OpenVINO LLMs inference and serving with vLLM​ - enhance vLLM's fast and easy model serving with the OpenVINO backend.
  • OpenVINO Execution Provider for ONNX Runtime - use OpenVINO as a backend with your existing ONNX Runtime code.
  • LlamaIndex - build context-augmented GenAI applications with the LlamaIndex framework and enhance runtime performance with OpenVINO.
  • LangChain - integrate OpenVINO with the LangChain framework to enhance runtime performance for GenAI applications.
  • Keras 3 - Keras 3 is a multi-backend deep learning framework. Users can switch model inference to the OpenVINO backend using the Keras API.

Check out the Awesome OpenVINO repository to discover a collection of community-made AI projects based on OpenVINO!

Performance

Explore OpenVINO Performance Benchmarks to discover the optimal hardware configurations and plan your AI deployment based on verified data.

Contribution and Support

Check out Contribution Guidelines for more details. Read the Good First Issues section, if you're looking for a place to start contributing. We welcome contributions of all kinds!

You can ask questions and get support on:

Resources

Telemetry

OpenVINO™ collects software performance and usage data for the purpose of improving OpenVINO™ tools. This data is collected directly by OpenVINO™ or through the use of Google Analytics 4. You can opt-out at any time by running the command:

opt_in_out --opt_out

More Information is available at OpenVINO™ Telemetry.

License

OpenVINO™ Toolkit is licensed under Apache License Version 2.0. By contributing to the project, you agree to the license and copyright terms therein and release your contribution under these terms.


* Other names and brands may be claimed as the property of others.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

openvino-2025.2.0-19140-cp313-cp313-win_amd64.whl (39.5 MB view details)

Uploaded CPython 3.13Windows x86-64

openvino-2025.2.0-19140-cp313-cp313-manylinux_2_31_aarch64.whl (26.9 MB view details)

Uploaded CPython 3.13manylinux: glibc 2.31+ ARM64

openvino-2025.2.0-19140-cp313-cp313-manylinux2014_x86_64.whl (47.6 MB view details)

Uploaded CPython 3.13

openvino-2025.2.0-19140-cp313-cp313-macosx_11_0_arm64.whl (31.1 MB view details)

Uploaded CPython 3.13macOS 11.0+ ARM64

openvino-2025.2.0-19140-cp313-cp313-macosx_10_15_x86_64.whl (38.5 MB view details)

Uploaded CPython 3.13macOS 10.15+ x86-64

openvino-2025.2.0-19140-cp312-cp312-win_amd64.whl (39.5 MB view details)

Uploaded CPython 3.12Windows x86-64

openvino-2025.2.0-19140-cp312-cp312-manylinux_2_31_aarch64.whl (26.9 MB view details)

Uploaded CPython 3.12manylinux: glibc 2.31+ ARM64

openvino-2025.2.0-19140-cp312-cp312-manylinux2014_x86_64.whl (47.6 MB view details)

Uploaded CPython 3.12

openvino-2025.2.0-19140-cp312-cp312-macosx_11_0_arm64.whl (31.1 MB view details)

Uploaded CPython 3.12macOS 11.0+ ARM64

openvino-2025.2.0-19140-cp312-cp312-macosx_10_15_x86_64.whl (38.5 MB view details)

Uploaded CPython 3.12macOS 10.15+ x86-64

openvino-2025.2.0-19140-cp311-cp311-win_amd64.whl (39.5 MB view details)

Uploaded CPython 3.11Windows x86-64

openvino-2025.2.0-19140-cp311-cp311-manylinux_2_31_aarch64.whl (26.9 MB view details)

Uploaded CPython 3.11manylinux: glibc 2.31+ ARM64

openvino-2025.2.0-19140-cp311-cp311-manylinux2014_x86_64.whl (47.6 MB view details)

Uploaded CPython 3.11

openvino-2025.2.0-19140-cp311-cp311-macosx_11_0_arm64.whl (31.0 MB view details)

Uploaded CPython 3.11macOS 11.0+ ARM64

openvino-2025.2.0-19140-cp311-cp311-macosx_10_15_x86_64.whl (38.4 MB view details)

Uploaded CPython 3.11macOS 10.15+ x86-64

openvino-2025.2.0-19140-cp310-cp310-win_amd64.whl (39.5 MB view details)

Uploaded CPython 3.10Windows x86-64

openvino-2025.2.0-19140-cp310-cp310-manylinux_2_31_aarch64.whl (26.9 MB view details)

Uploaded CPython 3.10manylinux: glibc 2.31+ ARM64

openvino-2025.2.0-19140-cp310-cp310-manylinux2014_x86_64.whl (47.6 MB view details)

Uploaded CPython 3.10

openvino-2025.2.0-19140-cp310-cp310-macosx_11_0_arm64.whl (31.0 MB view details)

Uploaded CPython 3.10macOS 11.0+ ARM64

openvino-2025.2.0-19140-cp310-cp310-macosx_10_15_x86_64.whl (38.4 MB view details)

Uploaded CPython 3.10macOS 10.15+ x86-64

openvino-2025.2.0-19140-cp39-cp39-win_amd64.whl (39.5 MB view details)

Uploaded CPython 3.9Windows x86-64

openvino-2025.2.0-19140-cp39-cp39-manylinux_2_31_aarch64.whl (26.9 MB view details)

Uploaded CPython 3.9manylinux: glibc 2.31+ ARM64

openvino-2025.2.0-19140-cp39-cp39-manylinux2014_x86_64.whl (47.6 MB view details)

Uploaded CPython 3.9

openvino-2025.2.0-19140-cp39-cp39-macosx_11_0_arm64.whl (31.0 MB view details)

Uploaded CPython 3.9macOS 11.0+ ARM64

openvino-2025.2.0-19140-cp39-cp39-macosx_10_15_x86_64.whl (38.4 MB view details)

Uploaded CPython 3.9macOS 10.15+ x86-64

File details

Details for the file openvino-2025.2.0-19140-cp313-cp313-win_amd64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp313-cp313-win_amd64.whl
Algorithm Hash digest
SHA256 0eaf04b585527b8c7b8b5eea338398cf003c556c4a7a5a7e41d7095528b7bd47
MD5 634fed3eac08b196d9b702633130e59f
BLAKE2b-256 5955ba80b0379438f4d9d07b0735053fc1fd25d745492aa787539fc7e3024dd1

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp313-cp313-manylinux_2_31_aarch64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp313-cp313-manylinux_2_31_aarch64.whl
Algorithm Hash digest
SHA256 c1b71f969a98be4557c8ea3626e6f6e14410b9a399fafc6e37b42be999bfe866
MD5 ecbe17fca00b5fdf15f38c2d2011ca60
BLAKE2b-256 82a373f89ca704246dc846a58fdd97831a6a47e66abc545c4f8a937894eca09a

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp313-cp313-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp313-cp313-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 69a9fc29e2c34d89bc6d04fa0698d766f13e00f4596649100a3f7b6cfe29b0d1
MD5 e1ad3d735e4be2f38179aac127daf3f1
BLAKE2b-256 ab0438b51322b5f276281e11ee568e51b163888095e314b86c07da7a9718b9eb

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp313-cp313-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp313-cp313-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 08ae91950340924d4658106da96142197db4b0a481ba5e70eb817ef16cca33b9
MD5 8c202cea412b1205e6499a81e10275ed
BLAKE2b-256 faad76ada3d87c8495b674ffb2ef239392243bac45d88e5504e449a9991dc451

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp313-cp313-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp313-cp313-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 fe9ec680e7af68fd7f523020ede139b3938faef4fb438a1452d44be4ef661efb
MD5 020896480a1cf537e6155f6e29c34ebc
BLAKE2b-256 229339bdf98039bb6464c1cef3f4eb1e8044fcc01b7c14a6d7bc1d0c509cc455

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp312-cp312-win_amd64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp312-cp312-win_amd64.whl
Algorithm Hash digest
SHA256 95d5c606c512b6694439ce0e1d5159d977ba806385634ad2dcaaaacd368e93ff
MD5 19cd6ed52ae6c0a023d22881a4903512
BLAKE2b-256 56808f4ecd1cd80b5225de091bf01307b35374b88195ced04f28ff83e807832f

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp312-cp312-manylinux_2_31_aarch64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp312-cp312-manylinux_2_31_aarch64.whl
Algorithm Hash digest
SHA256 c35b439ddf7b6bc1f10e0ed713889c9b4fb5c7e769183704e07665e486a1b39e
MD5 2dd38635f515ae68ccc05e70184fb428
BLAKE2b-256 2d2ffca398e08a389db72727650789bd6b57845a5e7a58318ce1d10b2cebb441

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp312-cp312-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp312-cp312-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 0b8eb7e51636bcd90a8d7a0f00df7f314998f887dad458ad5154b447eab2f60c
MD5 83c00b6010e32a572eba195572f902fd
BLAKE2b-256 535141c8513a5ccc1d3cdf06bf2feb29413dd3c7b105855b13a5e790c06b0fef

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp312-cp312-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp312-cp312-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 ded78ab9679588fa71c5cfc6b6bb1cd073fae1da4b8a234ecae308c597d88ff5
MD5 77bee466283ee5bf5b8b567490602f51
BLAKE2b-256 20d9a23dacbb59ecbd6f1df6a2ded9b9fb58873a2c55147aea6d25c8d3da5bb1

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp312-cp312-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp312-cp312-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 db68c03ca674ee88ea9213909b7504ba88ddf3dfd01bec266f62b84a72c1ae9b
MD5 6919c85b790d34d1f9bc480cd5df3c4c
BLAKE2b-256 072c28c824c82138765bcb5efcc901187e511b92bcb34c20401a106fbbe5ec01

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp311-cp311-win_amd64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp311-cp311-win_amd64.whl
Algorithm Hash digest
SHA256 9df9b6a79cf606a30bb6ba886c826ed8969c3873da5a609d0ac468b4ac75bae4
MD5 1a34a27276c9f19a79d971efcf688f51
BLAKE2b-256 64b452875b325e47cd0800fdf7ca3705b8720d78a913538bd6bbad61a49612c6

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp311-cp311-manylinux_2_31_aarch64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp311-cp311-manylinux_2_31_aarch64.whl
Algorithm Hash digest
SHA256 0be6d18622023b03d41199c90b809d3521c292871010878a385625b3359e449f
MD5 0647ec157972c2db6f9efc0884bd62e7
BLAKE2b-256 70dc09ea1044951582bb0e1b45d6a7c517fbab865b59730c0493c26c38d2dcbf

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp311-cp311-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp311-cp311-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 8e0bf80965191d524a05aaf5d3f663aecd726e061045d9568c66dc6ad75e4f24
MD5 8acaa5c98412247b9fb9d4a58dbb74b9
BLAKE2b-256 b9d16bf309663a92a7bfa97a9ed3f4a75d75b637a90bbc910595e4f782a294a3

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp311-cp311-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp311-cp311-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 673be01202002f2ff64321938c3a0b7750e7c4fe347d19b6e6140f966f28dde6
MD5 eae2c725370d44abe6897a53df5714f6
BLAKE2b-256 c272b6d919ff26dc348b7ea609fc55eb09cbf0bdf883b7912e509bb668f7e010

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp311-cp311-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp311-cp311-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 d971bd5a41b2d35a1c36ce70ecd41e5fc68f65bfbc12afe148f2255754c3ffce
MD5 bd671471f19c397266c8ecc040d3ddb4
BLAKE2b-256 35419d983d3faa6b879a19a8133d36994b3d766ea950a23fbe28a56ce872442b

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp310-cp310-win_amd64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp310-cp310-win_amd64.whl
Algorithm Hash digest
SHA256 c73d1d5e8de26c75fccdd1eb85ebcc96ba1744516c83e046c09701b80dd19e26
MD5 e8cf2695641bea53cf97f23c65c2b526
BLAKE2b-256 d7ffee19a8a247b41fa70fa4b0428cdb2327334891e6e1d48b51bfc6daa5cb05

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp310-cp310-manylinux_2_31_aarch64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp310-cp310-manylinux_2_31_aarch64.whl
Algorithm Hash digest
SHA256 57141e5983a0be3ebf2e2e01e547058886fb579bd9abf347decb184c164a4232
MD5 685729d8cb41767d928b56bb9be5bd7b
BLAKE2b-256 0257ccafeb48645dfd536aa8912d02e92a8ef4f597227925662508ac85e02f02

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp310-cp310-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp310-cp310-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 34090c899b82e31fd6124b4d45eadd6c9e3d8b28fd204b95cbf4207b38731782
MD5 d8723adc113de61754c44248aa34ab88
BLAKE2b-256 86fae8bdde70b4f2482d48c0ff9658ff0fe4947237a065694854b4ba98789a0d

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp310-cp310-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp310-cp310-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 edf5944b793abdac730314c0be5c0c7a4d0dd5aab8cea8d991182f3de66d77df
MD5 aa4f11008afcc864cbe4cc8f633fa079
BLAKE2b-256 0063b00291c27b0edbb62137759a7ad5db616d60d482a95066e2fec55ca54ea0

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp310-cp310-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp310-cp310-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 b66851ceb001770d994199439aaeb7ad8dee28220a9d20b4216e8ffdb476f451
MD5 e9c47c44e66379a32b3c587b5eee774d
BLAKE2b-256 0a79ed97d848e951c574535768a099c00d283aa4ac2dac652ae29d03591a8ae5

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp39-cp39-win_amd64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp39-cp39-win_amd64.whl
Algorithm Hash digest
SHA256 a01e6a3356f42b42885f0840216beef517bef450381a0a01703fd5f8ad6bba77
MD5 493a79448fd8c4b1bdfcff53113f80be
BLAKE2b-256 b85c7e99295c6cd7563c00f2aa4f36501378b5418c502b498d48aea81ba2d939

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp39-cp39-manylinux_2_31_aarch64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp39-cp39-manylinux_2_31_aarch64.whl
Algorithm Hash digest
SHA256 fa839241a52f661f29362aea2bb3c6ae6f550dbafdac38d0b41cbca87d3f1f22
MD5 38b33439776e6a3b5fa68b34b07575da
BLAKE2b-256 22a7da8c680cca91a5e5de99926b2045b55770e7a62e3e2e0748cc15b277ddd0

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp39-cp39-manylinux2014_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp39-cp39-manylinux2014_x86_64.whl
Algorithm Hash digest
SHA256 e89c4e6b23188ea0f96e3e633b41efe5cf8a45c91d2eb516ad4375747ee26e67
MD5 8679192e8fcc0aeb1f64961dac19e827
BLAKE2b-256 cc1f33ea57ad3bfccabda9f2183119d55e995f5818e372ba645a2b66e16a4abc

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp39-cp39-macosx_11_0_arm64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp39-cp39-macosx_11_0_arm64.whl
Algorithm Hash digest
SHA256 85551e6786ad06856bd87e25f1b5b5c3d27db6f26d11f69ad6394d86a9de0f12
MD5 86aa310e719b6ab51ca962f29a11a896
BLAKE2b-256 e7dab1e8892a395eab6d262410490208119f4af170aa50b94a293632cc97cd1e

See more details on using hashes here.

File details

Details for the file openvino-2025.2.0-19140-cp39-cp39-macosx_10_15_x86_64.whl.

File metadata

File hashes

Hashes for openvino-2025.2.0-19140-cp39-cp39-macosx_10_15_x86_64.whl
Algorithm Hash digest
SHA256 919946fb8c36010c4e24b13d8aa030d7503b30400da507a414eb7f4f9fbf379b
MD5 7ce2f4c38c4893fb5a13163e9a46ddf2
BLAKE2b-256 f47b50d843254443f2fe897330b64274b2178df63e7689913670a3d3feb5b649

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page