Merge branch 'master' into torchfx_dynamic_shapes_split_slice_support

cavusmustafa · Jul 8, 2024 · 01b5bf3 · 01b5bf3
2 parents 99d1fcd + a71137d
commit 01b5bf3
Show file tree

Hide file tree

Showing 63 changed files with 1,761 additions and 881 deletions.
diff --git a/docs/articles_en/about-openvino/compatibility-and-support/supported-devices.rst b/docs/articles_en/about-openvino/compatibility-and-support/supported-devices.rst
@@ -1,8 +1,5 @@
-.. {#openvino_supported_devices}
-
-
-Inference Device Support
-========================
+Supported Inference Devices
+============================
 
 .. meta::
    :description: Check the list of devices used by OpenVINO to run inference

diff --git a/docs/articles_en/about-openvino/compatibility-and-support/supported-models.rst b/docs/articles_en/about-openvino/compatibility-and-support/supported-models.rst
@@ -10,22 +10,6 @@ HuggingFace). This list is not comprehensive and only includes models tested by
 .. raw:: html
 
    <link rel="stylesheet" type="text/css" href="../../_static/css/openVinoDataTables.css">
-   <label>hide/reveal additional columns:</label><br/>
-   <label class="column-container">
-      CPU
-      <input type="checkbox" id="AI PC CPU" name="AI PC CPU" value="AI PC CPU" data-column="3" class="toggle-vis"/>
-      <label for="AI PC CPU" class="checkmark"></label>
-   </label>
-   <label class="column-container">
-      GPU
-      <input type="checkbox" id="AI PC GPU" name="AI PC GPU" value="AI PC GPU" data-column="4" class="toggle-vis"/>
-      <label for="AI PC GPU" class="checkmark"></label>
-   </label>
-   <label class="column-container">
-      NPU
-      <input type="checkbox" id="AI PC NPU" name="AI PC NPU" value="AI PC NPU" data-column="5" class="toggle-vis"/>
-      <label for="AI PC NPU" class="checkmark"></label>
-   </label>
 
 
 .. csv-table::

diff --git a/docs/articles_en/about-openvino/performance-benchmarks.rst b/docs/articles_en/about-openvino/performance-benchmarks.rst
@@ -18,7 +18,7 @@ Performance Benchmarks
 
 This page presents benchmark results for
 `Intel® Distribution of OpenVINO™ toolkit <https://software.intel.com/content/www/us/en/develop/tools/openvino-toolkit.html>`__
-and :doc:`OpenVINO Model Server <../ovms_what_is_openvino_model_server>`, for a representative "./../"
+and :doc:`OpenVINO Model Server <../ovms_what_is_openvino_model_server>`, for a representative
 selection of public neural networks and Intel® devices. The results may help you decide which
 hardware to use in your applications or plan AI workload for the hardware you have already
 implemented in your solutions. Click the buttons below to see the chosen benchmark data.

diff --git a/...articles_en/about-openvino/performance-benchmarks/generative-ai-performance.rst b/...articles_en/about-openvino/performance-benchmarks/generative-ai-performance.rst
@@ -7,54 +7,11 @@ Intel® Core™ Ultra processor family and AI PCs.
 The table below lists the key performance indicators for a selection of Large Language Models,
 running on an Intel® Core™ Ultra 7-165H based system, on built-in GPUs.
 
-For complete information on the system config, see:
-`Hardware Platforms [PDF] <https://docs.openvino.ai/2024/_static/benchmarks_files/OV-2024.2-platform_list.pdf>`__
 
 
 .. raw:: html
 
    <label><link rel="stylesheet" type="text/css" href="../../_static/css/openVinoDataTables.css"></label>
-   <br/><label>hide/reveal additional columns:</label><br/>
-   <label class="column-container">
-       Token latency
-       <input type="checkbox" checked id="1st" name="1st" value="1st" data-column="2" class="toggle-vis"/>
-       <label for="1st" class="checkmark"></label>
-    </label>
-    <label class="column-container">
-       Memory used
-       <input type="checkbox" checked id="maxrss" name="maxrss" value="maxrss" data-column="3" class="toggle-vis"/>
-       <label for="maxrss" class="checkmark"></label>
-    </label>
-    <label class="column-container">
-       Input tokens
-       <input type="checkbox" checked id="input" name="input" value="input" data-column="4" class="toggle-vis"/>
-       <label for="input" class="checkmark"></label>
-    </label>
-    <label class="column-container">
-       Output tokens
-       <input type="checkbox" checked id="output" name="output" value="output" data-column="5" class="toggle-vis"/>
-       <label for="output" class="checkmark"></label>
-    </label>
-    <label class="column-container">
-       Model precision
-       <input type="checkbox" checked id="precision" name="precision" value="precision" data-column="6" class="toggle-vis"/>
-       <label for="precision" class="checkmark"></label>
-    </label>
-    <label class="column-container">
-       Beam
-       <input type="checkbox" checked id="beam" name="beam" value="beam" data-column="7" class="toggle-vis"/>
-       <label for="beam" class="checkmark"></label>
-    </label>
-    <label class="column-container">
-       Batch size
-       <input type="checkbox" checked id="batch" name="batch" value="batch" data-column="8" class="toggle-vis"/>
-       <label for="batch" class="checkmark"></label>
-    </label>
-    <label class="column-container">
-       Framework
-       <input type="checkbox" checked id="framework" name="framework" value="framework" data-column="9" class="toggle-vis"/>
-       <label for="framework" class="checkmark"></label>
-    </label>
 
 
 .. csv-table::
@@ -64,8 +21,4 @@ For complete information on the system config, see:
    :file:  ../../_static/download/llm_models.csv
 
 
-This page is regularly updated to help you identify the best-performing LLMs on the
-Intel® Core™ Ultra processor family and AI PCs.
-
-For complete information on the system config, see:
-`Hardware Platforms [PDF] <https://docs.openvino.ai/2024/_static/benchmarks_files/OV-2024.2-platform_list.pdf>`__
+For complete information on the system config, see: `Hardware Platforms [PDF] <https://docs.openvino.ai/2024/_static/benchmarks_files/OV-2024.2-platform_list.pdf>`__
diff --git a/docs/articles_en/about-openvino/release-notes-openvino/system-requirements.rst b/docs/articles_en/about-openvino/release-notes-openvino/system-requirements.rst
@@ -30,6 +30,7 @@ CPU
 
    .. tab-item:: Supported Operating Systems
 
+      * Ubuntu 24.04 long-term support (LTS), 64-bit (Kernel 6.8+)
       * Ubuntu 22.04 long-term support (LTS), 64-bit (Kernel 5.15+)
       * Ubuntu 20.04 long-term support (LTS), 64-bit (Kernel 5.15+)
       * Ubuntu 18.04 long-term support (LTS) with limitations, 64-bit (Kernel 5.4+)
@@ -59,6 +60,7 @@ GPU
 
    .. tab-item::  Supported Operating Systems
 
+      * Ubuntu 24.04 long-term support (LTS), 64-bit
       * Ubuntu 22.04 long-term support (LTS), 64-bit
       * Ubuntu 20.04 long-term support (LTS), 64-bit
       * Windows 10, 64-bit
@@ -88,6 +90,7 @@ Intel® Neural Processing Unit
 
    .. tab-item:: Operating Systems for NPU
 
+      * Ubuntu 24.04 long-term support (LTS), 64-bit
       * Ubuntu 22.04 long-term support (LTS), 64-bit
       * Windows 11, 64-bit (22H2, 23H2)
 
@@ -106,6 +109,7 @@ Operating systems and developer environment
 
    .. tab-item:: Linux OS
 
+      * Ubuntu 24.04 with Linux kernel 6.8+
       * Ubuntu 22.04 with Linux kernel 5.15+
       * Ubuntu 20.04 with Linux kernel 5.15+
       * Red Hat Enterprise Linux 8 with Linux kernel 5.4

diff --git a/docs/articles_en/assets/images/quantized_convolution.png b/docs/articles_en/assets/images/quantized_convolution.png
diff --git a/docs/articles_en/assets/images/quantized_model_example.png b/docs/articles_en/assets/images/quantized_model_example.png
diff --git a/...vino-extensibility/openvino-plugin-library/advanced-guides/quantized-models.rst b/...vino-extensibility/openvino-plugin-library/advanced-guides/quantized-models.rst
@@ -7,7 +7,6 @@ Quantized models compute and restrictions
    :maxdepth: 1
    :hidden:
 
-   quantized-models/low-precision-model-representation
 
 .. meta::
    :description: Learn about the support for quantized models with different
@@ -16,8 +15,7 @@ Quantized models compute and restrictions
 
 One of the feature of OpenVINO is the support of quantized models with different precisions: INT8, INT4, etc.
 However, it is up to the plugin to define what exact precisions are supported by the particular HW.
-All quantized models which can be expressed in IR have a unified representation by means of *FakeQuantize* operation.
-For more details about low-precision model representation please refer to this :doc:`document <quantized-models/low-precision-model-representation>`.
+
 
 Interpreting FakeQuantize at runtime
 ####################################

diff --git a/...library/advanced-guides/quantized-models/low-precision-model-representation.rst b/...library/advanced-guides/quantized-models/low-precision-model-representation.rst
diff --git a/docs/articles_en/get-started/install-openvino.rst b/docs/articles_en/get-started/install-openvino.rst
@@ -47,7 +47,7 @@ All currently supported versions are:
       NPU              V\*         V\*     V\ *             n/a       n/a          n/a        n/a        V\*
       ===============  ==========  ======  ===============  ========  ============ ========== ========== ==========
 
-      | \* **Of the Linux systems, version 22.04 includes drivers for NPU.**
+      | \* **Of the Linux systems, versions 22.04 and 24.04 include drivers for NPU.**
       |  **For Windows, CPU inference on ARM64 is not supported.**
 
 .. dropdown:: Effortless GenAI integration with OpenVINO GenAI Flavor

diff --git a/docs/articles_en/get-started/install-openvino/install-openvino-conda.rst b/docs/articles_en/get-started/install-openvino/install-openvino-conda.rst
@@ -71,6 +71,48 @@ need to install additional components. Check the description below, as well as t
 :doc:`list of additional configurations <../configurations>`
 to see if your case needs any of them.
 
+Installing specific components of OpenVINO from Conda Forge
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+
+You do not have to install the entire OpenVINO package. You can install selected
+components by using:
+
+.. code-block:: sh
+
+   conda install conda-forge::<component_name>
+
+``<component_name>`` may be one of the components of OpenVINO listed below:
+
+- ``libopenvino-auto-batch-plugin``
+- ``libopenvino-auto-plugin``
+- ``libopenvino-hetero-plugin``
+- ``libopenvino-intel-cpu-plugin``
+- ``libopenvino-intel-gpu-plugin``
+- ``libopenvino-intel-npu-plugin``
+- ``libopenvino-ir-frontend``
+- ``libopenvino-onnx-frontend``
+- ``libopenvino-paddle-frontend``
+- ``libopenvino-pytorch-frontend``
+- ``libopenvino-tensorflow-frontend``
+- ``libopenvino-tensorflow-lite-frontend``
+- ``libopenvino-dev``
+- ``libopenvino-python``
+- ``libopenvino-arm-cpu-plugin``
+
+
+For example, to install a single component, use:
+
+.. code-block:: sh
+
+   conda install conda-forge::libopenvino-intel-cpu-plugin
+
+For multiple components, use:
+
+.. code-block:: sh
+
+   conda install conda-forge::libopenvino-intel-cpu-plugin conda-forge::libopenvino-arm-cpu-plugin conda-forge::libopenvino-intel-npu-plugin conda-forge::libopenvino-intel-gpu-plugin
+
+
 Compiling with OpenVINO Runtime from Conda-Forge on Linux
 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 
@@ -110,13 +152,19 @@ OpenCL™ Driver is included with the Intel® Graphics Driver package.
 Uninstalling OpenVINO™ Runtime
 ###########################################################
 
-Once OpenVINO Runtime is installed via Conda, you can remove it using the following command,
+Once OpenVINO Runtime is installed via Conda, you can remove it, using the following command,
 with the proper OpenVINO version number:
 
 .. code-block:: sh
 
    conda remove openvino=2024.2.0
 
+If you have installed specific components of OpenVINO, you can remove them, using:
+
+.. code-block:: sh
+
+   conda remove conda-forge::<component_name>
+
 What's Next?
 ############################################################
 

diff --git a/docs/articles_en/openvino-workflow/model-preparation.rst b/docs/articles_en/openvino-workflow/model-preparation.rst
@@ -1,5 +1,3 @@
-.. {#openvino_docs_model_processing_introduction}
-
 Model Preparation
 =================
 
@@ -66,15 +64,15 @@ The easiest way to obtain a model is to download it from an online database, suc
    For PyTorch models, `Python API <#convert-a-model-with-python-convert-model>`__ is the only
    conversion option.
 
-Model States
+Different model representations
 ##############################################
 
-There are three states a model in OpenVINO can be: saved on disk, loaded but not compiled
-(``ov.Model``) or loaded and compiled (``ov.CompiledModel``).
+A model in OpenVINO can be represented in three ways: saved on disk, loaded but not compiled
+(``ov.Model``), and loaded and compiled (``ov.CompiledModel``).
 
 | **Saved on disk**
-|    A model in this state consists of one or more files that fully represent the neural
-     network. A model can be stored in different ways. For example:
+|    One or more files saved on a drive, fully representing the neural network.
+     Different model formats are stored in different ways, for example:
 |       OpenVINO IR: pair of .xml and .bin files
 |       ONNX: .onnx file
 |       TensorFlow: directory with a .pb file and two subfolders or just a .pb file
@@ -88,7 +86,7 @@ There are three states a model in OpenVINO can be: saved on disk, loaded but not
      applying quantization or even adding preprocessing steps before compiling the model.
 
 | **Loaded and compiled**
-|   This state is achieved when one or more devices are specified for a model object to
+|   This representation is achieved when one or more devices are specified for a model object to
     run on (``ov.CompiledModel``), allowing device optimizations to be made and enabling
     inference.