[DOCS] Running inference comments (#25285)

### Details:
 - *item1*
 - *...*

### Tickets:
 - 145078

---------

Co-authored-by: Karol Blaszczak <[email protected]>

docs/articles_en/assets/snippets/compile_model_npu.cpp

@@ -0,0 +1,12 @@
+#include <openvino/runtime/core.hpp>
+
+int main() {
+{
+    //! [compile_model_default_npu]
+    ov::Core core;
+    auto model = core.read_model("model.xml");
+    auto compiled_model = core.compile_model(model, "NPU");
+    //! [compile_model_default_npu]
+}
+    return 0;
+}

docs/articles_en/assets/snippets/compile_model_npu.py

@@ -0,0 +1,18 @@
+# Copyright (C) 2018-2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+import openvino as ov
+from snippets import get_model
+
+
+def main():
+    model = get_model()
+
+    core = ov.Core()
+    if "NPU" not in core.available_devices:
+        return 0
+
+    #! [compile_model_default_npu]
+    core = ov.Core()
+    compiled_model = core.compile_model(model, "NPU")
+    #! [compile_model_default_npu]

docs/articles_en/openvino-workflow/running-inference/inference-devices-and-modes.rst

@@ -36,7 +36,7 @@ different conditions:
 |    :doc:`Heterogeneous Execution (HETERO) <inference-devices-and-modes/hetero-execution>`
 |    :doc:`Automatic Batching Execution (Auto-batching) <inference-devices-and-modes/automatic-batching>`
 
-
+To learn how to change the device configuration, read the :doc:`Query device properties article <inference-devices-and-modes/query-device-properties>`.
 
 Enumerating Available Devices
 #######################################
@@ -83,3 +83,10 @@ Accordingly, the code that loops over all available devices of the "GPU" type on
          :language: cpp
          :fragment: [part3]
 
+Additional Resources
+####################
+
+* `OpenVINO™ Runtime API Tutorial <./../../notebooks/openvino-api-with-output.html>`__
+* `AUTO Device Tutorial <./../../notebooks/auto-device-with-output.html>`__
+* `GPU Device Tutorial <./../../notebooks/gpu-device-with-output.html>`__
+* `NPU Device Tutorial <./../../notebooks/hello-npu-with-output.html>`__

docs/articles_en/openvino-workflow/running-inference/inference-devices-and-modes/npu-device.rst

@@ -30,6 +30,25 @@ of the model into a proprietary format. The compiler included in the user mode d
 platform specific optimizations in order to efficiently schedule the execution of network layers and
 memory transactions on various NPU hardware submodules.
 
+To use NPU for inference, pass the device name to the ``ov::Core::compile_model()`` method:
+
+.. tab-set::
+
+   .. tab-item:: Python
+      :sync: py
+
+      .. doxygensnippet:: docs/articles_en/assets/snippets/compile_model_npu.py
+         :language: py
+         :fragment: [compile_model_default_npu]
+
+   .. tab-item:: C++
+      :sync: cpp
+
+      .. doxygensnippet:: docs/articles_en/assets/snippets/compile_model_npu.cpp
+         :language: cpp
+         :fragment: [compile_model_default_npu]
+
+
 Model Caching
 #############################
 

docs/articles_en/openvino-workflow/running-inference/integrate-openvino-with-your-application.rst

@@ -226,9 +226,12 @@ Compile the model for a specific device using ``ov::Core::compile_model()``:
 The ``ov::Model`` object represents any models inside the OpenVINO™ Runtime.
 For more details please read article about :doc:`OpenVINO™ Model representation <integrate-openvino-with-your-application/model-representation>`.
 
+OpenVINO includes experimental support for NPU, learn more in the
+:doc:`NPU Device section <./inference-devices-and-modes/npu-device>`
+
 The code above creates a compiled model associated with a single hardware device from the model object.
 It is possible to create as many compiled models as needed and use them simultaneously (up to the limitation of the hardware).
-To learn how to change the device configuration, read the :doc:`Query device properties <inference-devices-and-modes/query-device-properties>` article.
+To learn more about supported devices and inference modes, read the :doc:`Inference Devices and Modes <./inference-devices-and-modes>` article.
 
 Step 3. Create an Inference Request
 ###################################
@@ -432,6 +435,7 @@ To build your project using CMake with the default build tools currently availab
 Additional Resources
 ####################
 
+* `OpenVINO™ Runtime API Tutorial <./../../notebooks/openvino-api-with-output.html>`__
 * See the :doc:`OpenVINO Samples <../../learn-openvino/openvino-samples>` page for specific examples of how OpenVINO pipelines are implemented for applications like image classification, text prediction, and many others.
 * Models in the OpenVINO IR format on `Hugging Face <https://huggingface.co/models>`__.
 * :doc:`OpenVINO™ Runtime Preprocessing <optimize-inference/optimize-preprocessing>`