diff --git a/docs/articles_en/about_openvino.rst b/docs/articles_en/about_openvino.rst index 2cc7e8e1aab..ab81a9c358b 100644 --- a/docs/articles_en/about_openvino.rst +++ b/docs/articles_en/about_openvino.rst @@ -12,6 +12,7 @@ About OpenVINO compatibility_and_support system_requirements Release Notes + release_policy Additional Resources OpenVINO is a toolkit for simple and efficient deployment of various deep learning models. @@ -24,7 +25,7 @@ OpenVINO (Open Visual Inference and Neural network Optimization) is an open-sour Features ############################################################## -One of the main purposes of OpenVINO is to streamline the deployment of deep learning models in user applications. It optimizes and accelerates model inference, which is crucial for such domains as Generative AI, Large Language models, and use cases like object detection, classification, segmentation, and many others. +One of the main purposes of OpenVINO is to streamline the deployment of deep learning models in user applications. It optimizes and accelerates model inference, which is crucial for such domains as Generative AI, Large Language models, and use cases like object detection, classification, segmentation, and many others. * :doc:`Model Optimization ` @@ -32,7 +33,7 @@ OpenVINO provides multiple optimization methods for both the training and post-t * :doc:`Model Conversion and Framework Compatibility ` -Supported models can be loaded directly or converted to the OpenVINO format to achieve better performance. Supported frameworks include ONNX, PyTorch, TensorFlow, TensorFlow Lite, Keras, and PaddlePaddle. +Supported models can be loaded directly or converted to the OpenVINO format to achieve better performance. Supported frameworks include ONNX, PyTorch, TensorFlow, TensorFlow Lite, Keras, and PaddlePaddle. * :doc:`Model Inference ` @@ -40,14 +41,14 @@ OpenVINO accelerates deep learning models on various hardware platforms, ensurin * `Deployment on a server `__ -A model can be deployed either locally using OpenVINO Runtime or on a model server. Runtime is a set of C++ libraries with C and Python bindings providing a common API to deliver inference solutions. The model server enables quick model inference using external resources. +A model can be deployed either locally using OpenVINO Runtime or on a model server. Runtime is a set of C++ libraries with C and Python bindings providing a common API to deliver inference solutions. The model server enables quick model inference using external resources. Architecture ############################################################## To learn more about how OpenVINO works, read the Developer documentation on its `architecture `__ and `core components `__. -OpenVINO Ecosystem +OpenVINO Ecosystem ############################################################## Along with the primary components of model optimization and runtime, the toolkit also includes: diff --git a/docs/articles_en/about_openvino/release_policy.rst b/docs/articles_en/about_openvino/release_policy.rst new file mode 100644 index 00000000000..b402f23e956 --- /dev/null +++ b/docs/articles_en/about_openvino/release_policy.rst @@ -0,0 +1,175 @@ +.. {#release_policy} + +Release Policy +============================================================================= + +OpenVINO offers releases of three different types, each targeting a different use case: + +* `Regular releases <#regular-releases>`__ +* `Long-Term Support <#long-term-support-releases>`__ +* `Nightly <#nightly-releases>`__ + + +Regular releases +#################### + +OpenVINO™ is published multiple times a year, when significant new features and bug fixes have +been completed and validated. For each regular release, a dedicated development branch in GitHub +is created, targeting changes such as: + +* New features of gold quality, as well as Beta features, labeled as “preview.” +* Key bug fixes. +* Newest hardware support. + +Each regular release is supported until the next version arrives, making it suitable for: + +* Most typical use cases (the recommended release type). +* Products requiring frequent changes in supported hardware, libraries, operating systems, and models. + + +Long-Term Support releases +########################### + +Each year's final release becomes a Long-Term Support (LTS) version, which continues to receive +bug fixes and security updates, even after newer versions are published. Therefore, LTS may be +used for production environments where: + +* There is no need for frequent changes in hardware or model support. +* New optimizations are not prioritized. +* Upgrading is challenging, e.g., due to high software complexity. +* A legacy feature, discontinued in newer OpenVINO versions, is still required. + +**LTS Lifecycle** + +* LTS is typically published at the end of every year cycle. +* LTS uses the branch of the last yearly regular release. +* LTS aim to receive an update once a year. +* Security updates are offered for the duration of the entire LTS period, which is two years + (or until superseded by two consecutive LTS versions). +* Updates targeting newly discovered bugs are offered for the period of one year. + +.. note:: + LTS releases may offer limited distribution options. + +**Components covered by LTS** + +Not all components associated with the OpenVINO™ toolkit are covered by the LTS policy. +The following elements are not guaranteed to receive updates: + +* Components in the deprecation period. +* Preview features (highlighted in the release notes). +* Components not directly connected to the OpenVINO™ workflow, such as: Samples, demos, and Jupyter notebooks. +* OpenVINO tools, such as NNCF and OVMS. +* Code samples used in component testing. + + +Nightly releases +########################### + +OpenVINO nightly releases are the first source of newly added features and priority bug fixes +reported for the previous versions, as a preview of the most recent changes. They are: + +* Released every workday. +* Based on the master branch of the OpenVINO GitHub repository. +* Not fit for production environments. +* Offered with limited distribution options: + +Since their validation scope is limited, **they should never be used for production purposes**. +Instead, they may serve: + +* Early integration testing. +* Community contribution development and integration. +* Tracking development progress. + +.. tab-set:: + + .. tab-item:: Downloadable Archives + :sync: archives-s3 + + 1. Go to `OpenVINO Nightly Packages `__. + 2. Select a package you want to install. + 3. Download the archive for your platform. + 4. Unpack the archive in a convenient location. + 5. Once unpacked, proceed as with a regular OpenVINO archive (see :doc:`installation guides `). + + .. tab-item:: OV Wheels on S3 + :sync: wheels-s3 + + A PyPI repository deployed on AWS S3 (`see more details `__) + enables the use of regular PyPI without the need to rename wheels. Installation commands vary depending + on the branch: + + .. tab-set:: + + .. tab-item:: Master + :sync: master + + .. code-block:: py + + pip install --pre openvino --extra-index-url + https://storage.openvinotoolkit.org/simple/wheels/nightly + + .. tab-item:: Release + :sync: release + + * This command includes **Release Candidates**. + * To use ``extra-index-url``, you need to pass a link containing ``simple``. + * The ``--pre`` allows the installation of dev-builds. + + .. code-block:: py + + pip install --pre openvino --extra-index-url + https://storage.openvinotoolkit.org/simple/wheels/pre-release + + .. tab-item:: OV Wheels on PyPi (not recommended) + :sync: wheels-pypi + + + Install OV Wheels from PyPI: + + .. code-block:: py + + pip install openvino-nightly + + +Additional Information +######################### + +| **Determining the OpenVINO Version** +| If you need to operate on a specific OpenVINO release, and you are not sure which version + is included in the installed package, you can verify it in one of two ways: + +.. tab-set:: + + .. tab-item:: Python + :sync: python + + Execute the following command within the installed package: + + .. code-block:: python + + python3 -c "import openvino; print(openvino.__version__)" + + .. tab-item:: Archives + :sync: archives + + You can find the file version in: + + .. code-block:: text + + /runtime/version.txt + +| **Issue Reporting** +| To report issues, use the `Intel® Premier Support `__ + clearly stating the issue, impact, and the expected timeline. + +| **Distribution:** + +* `Selector tool `__ of all distribution options. +* Source code distribution: `GitHub `__ and + `Gitee `__ . +* Binary distribution: + + * Download from `OpenVINO storage `__ + * `pypi.org `__ + * `DockerHub* `__