Merge branch 'master' of https://github.com/openvinotoolkit/openvino …

…into at/npuw-extend-transpose-value-tensors-pass

.github/workflows/build_doc.yml

@@ -78,13 +78,13 @@ jobs:
           echo "PR_NUMBER=$PR_NUMBER" >> $GITHUB_ENV
 
       - name: 'Upload sphinx.log'
-        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # v4.4.3
+        uses: actions/upload-artifact@v4.6.0
         with:
           name: sphinx_build_log_${{ env.PR_NUMBER }}.log
           path: build/docs/sphinx.log
 
       - name: 'Upload docs html'
-        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # v4.4.3
+        uses: actions/upload-artifact@v4.6.0
         with:
           name: openvino_docs_html_${{ env.PR_NUMBER }}.zip
           path: build/docs/openvino_docs_html.zip
@@ -101,7 +101,7 @@ jobs:
 
       - name: 'Upload test results'
         if: failure()
-        uses: actions/upload-artifact@b4b15b8c7c6ac21ea08fcf65892d2ee8f75cf882 # v4.4.3
+        uses: actions/upload-artifact@v4.6.0
         with:
           name: openvino_docs_pytest
           path: build/docs/_artifacts/

README.md

@@ -127,6 +127,7 @@ Learn how to run LLMs and GenAI with [Samples](https://github.com/openvinotoolki
 -   [OpenVINO Execution Provider for ONNX Runtime](https://onnxruntime.ai/docs/execution-providers/OpenVINO-ExecutionProvider.html) - use OpenVINO as a backend with your existing ONNX Runtime code.
 -   [LlamaIndex](https://docs.llamaindex.ai/en/stable/examples/llm/openvino/) - build context-augmented GenAI applications with the LlamaIndex framework and enhance runtime performance with OpenVINO.
 -   [LangChain](https://python.langchain.com/docs/integrations/llms/openvino/) - integrate OpenVINO with the LangChain framework to enhance runtime performance for GenAI applications.
+-   [Keras 3](https://github.com/keras-team/keras) - 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](https://github.com/openvinotoolkit/awesome-openvino) repository to discover a collection of community-made AI projects based on OpenVINO!
 

cmake/developer_package/compile_flags/os_flags.cmake

@@ -104,6 +104,7 @@ macro(ov_check_compiler_supports_sve flags)
     int main() {
         svfloat64_t a;
         a = svdup_n_f64(0);
+        (void)a; // to avoid warnings
         return 0;
     }")
 
@@ -259,7 +260,6 @@ endmacro()
 macro(ov_arm_sve_optimization_flags flags)
     # Check for compiler SVE support
     ov_check_compiler_supports_sve("-march=armv8-a+sve")
-
     if(OV_COMPILER_IS_INTEL_LLVM)
         message(WARNING "Unsupported CXX compiler ${CMAKE_CXX_COMPILER_ID}")
     elseif(CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
@@ -449,6 +449,10 @@ if(CMAKE_CXX_COMPILER_ID STREQUAL "MSVC")
     # Build with multiple processes
     ov_add_compiler_flags(/MP)
 
+    # Specifies both the source character set and the execution character set as UTF-8.
+    # For details, refer to link: https://learn.microsoft.com/en-us/cpp/build/reference/utf-8-set-source-and-executable-character-sets-to-utf-8?view=msvc-170
+    ov_add_compiler_flags(/utf-8)
+
     # Workaround for an MSVC compiler issue in some versions of Visual Studio 2022.
     # The issue involves a null dereference to a mutex. For details, refer to link https://github.com/microsoft/STL/wiki/Changelog#vs-2022-1710
     if(MSVC AND MSVC_VERSION GREATER_EQUAL 1930)

docs/articles_en/about-openvino/compatibility-and-support/supported-devices.rst

@@ -90,16 +90,3 @@ topic (step 3 "Configure input and output").
    | \* **Of the Linux systems, versions 22.04 and 24.04 include drivers for NPU.**
    |  **For Windows, CPU inference on ARM64 is not supported.**
 
-
-.. note::
-
-   With the OpenVINO 2024.0 release, support for GNA has been discontinued. To keep using it
-   in your solutions, revert to the 2023.3 (LTS) version.
-
-   With the OpenVINO™ 2023.0 release, support has been cancelled for:
-
-   - Intel® Neural Compute Stick 2 powered by the Intel® Movidius™ Myriad™ X
-   - Intel® Vision Accelerator Design with Intel® Movidius™
-
-   To keep using the MYRIAD and HDDL plugins with your hardware,
-   revert to the OpenVINO 2022.3 (LTS) version.

docs/articles_en/documentation.rst

@@ -16,6 +16,7 @@ Documentation
    Tool Ecosystem <documentation/openvino-ecosystem>
    OpenVINO Extensibility <documentation/openvino-extensibility>
    OpenVINO™ Security <documentation/openvino-security>
+   Legacy Features <documentation/legacy-features>
 
 
 This section provides reference documents that guide you through the OpenVINO toolkit workflow, from preparing models, optimizing them, to deploying them in your own deep learning applications.

docs/articles_en/documentation/legacy-features.rst

@@ -0,0 +1,112 @@
+Legacy Features and Components
+==============================
+
+.. meta::
+   :description: A list of deprecated OpenVINO™ components.
+
+Since OpenVINO has grown very rapidly in recent years, a number of its features
+and components have been replaced by other solutions. Some of them are still
+supported to assure OpenVINO users are given enough time to adjust their projects,
+before the features are fully discontinued.
+
+This section will give you an overview of these major changes and tell you how
+you can proceed to get the best experience and results with the current OpenVINO
+offering.
+
+
+Discontinued:
+#############
+
+.. dropdown:: OpenVINO Development Tools Package
+
+   |   *New solution:* OpenVINO Runtime includes all supported components
+   |   *Old solution:* `See how to install Development Tools <https://docs.openvino.ai/2024/documentation/legacy-features/install-dev-tools.html>`__
+   |
+   |   OpenVINO Development Tools used to be the OpenVINO package with tools for
+       advanced operations on models, such as Model conversion API, Benchmark Tool,
+       Accuracy Checker, Annotation Converter, Post-Training Optimization Tool,
+       and Open Model Zoo tools. Most of these tools have been either removed,
+       replaced by other solutions, or moved to the OpenVINO Runtime package.
+
+.. dropdown:: Model Optimizer / Conversion API
+
+   |   *New solution:* :doc:`Direct model support and OpenVINO Converter (OVC) <../openvino-workflow/model-preparation>`
+   |   *Old solution:* `Legacy Conversion API <https://docs.openvino.ai/2024/documentation/legacy-features/transition-legacy-conversion-api.html>`__
+   |
+   |   The role of Model Optimizer and later the Conversion API was largely reduced
+       when all major model frameworks became supported directly. For converting model
+       files explicitly, it has been replaced with a more light-weight and efficient
+       solution, the OpenVINO Converter (launched with OpenVINO 2023.1).
+
+.. dropdown:: Open Model ZOO
+
+   |   *New solution:* users are encouraged to use public model repositories such as `Hugging Face <https://huggingface.co/OpenVINO>`__
+   |   *Old solution:* `Open Model ZOO <https://docs.openvino.ai/2024/documentation/legacy-features/model-zoo.html>`__
+   |
+   |   Open Model ZOO provided a collection of models prepared for use with OpenVINO,
+       and a small set of tools enabling a level of automation for the process.
+       Since the tools have been mostly replaced by other solutions and several
+       other model repositories have recently grown in size and popularity,
+       Open Model ZOO will no longer be maintained. You may still use its resources
+       until they are fully removed. `Check the OMZ GitHub project <https://github.com/openvinotoolkit/open_model_zoo>`__
+
+.. dropdown:: Multi-Device Execution
+
+   |   *New solution:* :doc:`Automatic Device Selection <../openvino-workflow/running-inference/inference-devices-and-modes/auto-device-selection>`
+   |   *Old solution:* `Check the legacy solution <https://docs.openvino.ai/2024/documentation/legacy-features/multi-device.html>`__
+   |
+   |   The behavior and results of the Multi-Device Execution mode are covered by the ``CUMULATIVE_THROUGHPUT``
+       option of the Automatic Device Selection. The only difference is that ``CUMULATIVE_THROUGHPUT`` uses
+       the devices specified by AUTO, which means that adding devices manually is not mandatory,
+       while with MULTI, the devices had to be specified before the inference.
+
+.. dropdown:: Caffe, and Kaldi model formats
+
+   |   *New solution:* conversion to ONNX via external tools
+   |   *Old solution:* model support discontinued with OpenVINO 2024.0
+   |      `The last version supporting Apache MXNet, Caffe, and Kaldi model formats <https://docs.openvino.ai/2023.3/mxnet_caffe_kaldi.html>`__
+   |      :doc:`See the currently supported frameworks <../openvino-workflow/model-preparation>`
+
+.. dropdown:: Post-training Optimization Tool (POT)
+
+   |   *New solution:* Neural Network Compression Framework (NNCF) now offers the same functionality
+   |   *Old solution:* POT discontinued with OpenVINO 2024.0
+   |      :doc:`See how to use NNCF for model optimization <../openvino-workflow/model-optimization>`
+   |      `Check the NNCF GitHub project, including documentation <https://github.com/openvinotoolkit/nncf>`__
+
+.. dropdown:: Inference API 1.0
+
+   |   *New solution:* API 2.0 launched in OpenVINO 2022.1
+   |   *Old solution:* discontinued with OpenVINO 2024.0
+   |      `2023.2 is the last version supporting API 1.0 <https://docs.openvino.ai/archives/index.html#:~:text=2023.2,Release%20Notes>`__
+
+.. dropdown:: Compile tool
+
+   |   *New solution:* the tool is no longer needed
+   |   *Old solution:* discontinued with OpenVINO 2023.0
+   |      If you need to compile a model for inference on a specific device, use the following script:
+
+      .. tab-set::
+
+         .. tab-item:: Python
+            :sync: py
+
+            .. doxygensnippet:: docs/articles_en/assets/snippets/export_compiled_model.py
+               :language: python
+               :fragment: [export_compiled_model]
+
+         .. tab-item:: C++
+            :sync: cpp
+
+            .. doxygensnippet:: docs/articles_en/assets/snippets/export_compiled_model.cpp
+               :language: cpp
+               :fragment: [export_compiled_model]
+
+.. dropdown:: TensorFlow integration (OVTF)
+
+   |   *New solution:* Direct model support and OpenVINO Converter (OVC)
+   |   *Old solution:* discontinued in OpenVINO 2023.0
+   |
+   |   OpenVINO now features a native TensorFlow support, with no need for explicit model
+       conversion.
+

docs/articles_en/learn-openvino/llm_inference_guide.rst

@@ -55,7 +55,10 @@ options:
       as well as conversion on the fly. For integration with the final product it may offer
       lower performance, though.
 
-
+Note that the base version of OpenVINO may also be used to run generative AI. Although it may
+offer a simpler environment, with fewer dependencies, it has significant limitations and a more
+demanding implementation process. For reference, see
+`the article on generative AI usage of OpenVINO 2024.6 <https://docs.openvino.ai/2024/learn-openvino/llm_inference_guide/llm-inference-native-ov.html>`__.
 
 The advantages of using OpenVINO for generative model deployment:
 

docs/articles_en/learn-openvino/openvino-samples/benchmark-tool.rst

@@ -8,7 +8,10 @@ Benchmark Tool
                  devices.
 
 
-This page demonstrates how to use the Benchmark Tool to estimate deep learning inference performance on supported devices.
+This page demonstrates how to use the Benchmark Tool to estimate deep learning inference
+performance on supported devices. Note that the MULTI plugin mentioned here is considered
+a legacy tool and currently is just a mapping of the
+:doc:`AUTO plugin <../../openvino-workflow/running-inference/inference-devices-and-modes/auto-device-selection>`.
 
 .. note::
 

docs/articles_en/openvino-workflow/model-preparation/convert-model-keras.rst

@@ -0,0 +1,87 @@
+Converting a Keras Model
+========================
+
+
+.. meta::
+   :description: Learn how to convert a model from the
+                 Keras format to the OpenVINO Model.
+
+
+This document explains the process of converting Keras 3 models to the OpenVINO Intermediate Representation (IR) format.
+For instructions on converting Keras 2 models, refer to :doc:`TensorFlow Model Conversion <convert-model-tensorflow>`.
+
+To convert a Keras 3 model, first export it to a lightweight TensorFlow SavedModel artifact,
+and then convert it to an OpenVINO model, using the ``convert_model`` function.
+Here is a code example of how to do this:
+
+.. code-block:: py
+   :force:
+
+   import keras_hub
+   import openvino as ov
+
+   model = keras_hub.models.BertTextClassifier.from_preset(
+       "bert_base_en_uncased",
+       num_classes=4,
+       preprocessor=None,
+   )
+
+   # export to SavedModel
+   model.export("bert_base")
+
+   # convert to OpenVINO model
+   ov_model = ov.convert_model("bert_base")
+
+
+.. note::
+
+   The resulting OpenVINO IR model can be saved to drive with no additional, Keras-specific steps.
+   Use the standard ``ov.save_model(ov_model,'model.xml')`` command. 
+
+Alternatively, a model exported to TensorFlow SavedModel format can also be converted to OpenVINO IR using the ``ovc`` tool. Here is an example:
+
+.. code-block:: sh
+   :force:
+
+   ovc bert_base
+
+
+Run inference in Keras 3 with the OpenVINO backend
+##################################################
+
+Starting with release 3.8, Keras provides native integration with the OpenVINO backend for accelerated inference.
+This integration enables you to leverage OpenVINO performance optimizations directly within the Keras workflow, enabling faster inference on OpenVINO supported hardware.
+
+To switch to the OpenVINO backend in Keras 3, set the ``KERAS_BACKEND`` environment variable to ``"openvino"``
+or specify the backend in the local configuration file at ``~/.keras/keras.json``.
+Here is an example of how to infer a model (trained with PyTorch, JAX, or TensorFlow backends) in Keras 3, using the OpenVINO backend:
+
+.. code-block:: py
+   :force:
+
+   import os
+
+   os.environ["KERAS_BACKEND"] = "openvino"
+   import numpy as np
+   import keras
+   import keras_hub
+
+   features = {
+       "token_ids": np.ones(shape=(2, 12), dtype="int32"),
+       "segment_ids": np.array([[0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 0, 0]] * 2),
+       "padding_mask": np.array([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0]] * 2),
+   }
+
+   # take a model from KerasHub
+   bert = keras_hub.models.BertTextClassifier.from_preset(
+       "bert_base_en_uncased",
+       num_classes=4,
+       preprocessor=None,
+   )
+
+   predictions = bert.predict(features)
+
+.. note::
+
+   The OpenVINO backend may currently lack support for some operations.
+   This will be addressed in upcoming Keras releases as operation coverage is being expanded.

docs/articles_en/openvino-workflow/model-preparation/convert-model-to-ir.rst

@@ -14,6 +14,7 @@ Convert to OpenVINO IR
    Convert from TensorFlow Lite <convert-model-tensorflow-lite>
    Convert from PaddlePaddle <convert-model-paddle>
    Convert from JAX/Flax <convert-model-jax>
+   Convert from Keras <convert-model-keras>
 
 
 

docs/notebooks/latent-consistency-models-image-generation-with-output.rst

@@ -694,7 +694,7 @@ generative models as it already includes all the core functionality.
 
 ``openvino_genai.Text2ImagePipeline`` class supports inference of
 `Diffusers
-models <https://github.com/openvinotoolkit/openvino.genai/blob/master/src/docs/SUPPORTED_MODELS.md#text-2-image-models>`__.
+models <https://github.com/openvinotoolkit/openvino.genai/blob/master/SUPPORTED_MODELS.md#image-generation-models>`__.
 For pipeline initialization, we should provide directory with converted
 by Optimum Intel pipeline and specify inference device. Optionally, we
 can provide configuration for LoRA Adapters using ``adapter_config``.

docs/notebooks/multilora-image-generation-with-output.rst

@@ -210,7 +210,7 @@ generative models as it already includes all the core functionality.
 
 ``openvino_genai.Text2ImagePipeline`` class supports inference of
 `Diffusers
-models <https://github.com/openvinotoolkit/openvino.genai/blob/master/src/docs/SUPPORTED_MODELS.md#text-2-image-models>`__.
+models <https://github.com/openvinotoolkit/openvino.genai/blob/master/SUPPORTED_MODELS.md#image-generation-models>`__.
 For pipeline initialization, we should provide directory with converted
 by Optimum Intel pipeline and specify inference device. Optionally, we
 can provide configuration for LoRA Adapters using ``adapter_config``.

samples/python/benchmark/bert_benchmark/bert_benchmark.py

@@ -11,7 +11,7 @@
 
 import openvino as ov
 import datasets
-from openvino.runtime import get_version
+from openvino import get_version
 from transformers import AutoTokenizer
 from transformers.onnx import export
 from transformers.onnx.features import FeaturesManager

samples/python/benchmark/sync_benchmark/sync_benchmark.py

@@ -10,8 +10,8 @@
 
 import numpy as np
 import openvino as ov
-from openvino.runtime import get_version
-from openvino.runtime.utils.types import get_dtype
+from openvino import get_version
+from openvino.utils.types import get_dtype
 
 
 def fill_tensor_random(tensor):

samples/python/benchmark/throughput_benchmark/throughput_benchmark.py

@@ -10,8 +10,8 @@
 
 import numpy as np
 import openvino as ov
-from openvino.runtime import get_version
-from openvino.runtime.utils.types import get_dtype
+from openvino import get_version
+from openvino.utils.types import get_dtype
 
 
 def fill_tensor_random(tensor):

samples/python/model_creation_sample/model_creation_sample.py

@@ -9,7 +9,7 @@
 
 import numpy as np
 import openvino as ov
-from openvino.runtime import op, opset1, opset8
+from openvino import op, opset1, opset8
 
 from data import digits
 

src/bindings/python/constraints.txt

@@ -21,6 +21,5 @@ h5py>=3.1.0,<3.13.0
 docopt~=0.6.2
 paddlepaddle==2.6.2
 tensorflow>=1.15.5,<2.18.0
-six~=1.16.0
 protobuf>=3.18.1,<6.0.0
 onnx==1.17.0

src/bindings/python/src/openvino/properties/intel_npu/__init__.py

@@ -0,0 +1,9 @@
+# -*- coding: utf-8 -*-
+# Copyright (C) 2018-2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# Properties
+import openvino._pyopenvino.properties.intel_npu as __intel_npu
+from openvino.properties._properties import __make_properties
+
+__make_properties(__intel_npu, __name__)