NXP backend: Update user guide and docs Readme (#14852)

### Summary
This PR updates NXP backend Readmes in backend and examples directories.

### Test plan
- 


cc @robert-kalmar @JakeStevens @digantdesai

Author: roman-janik-nxp

backends/nxp/README.md

@@ -15,7 +15,8 @@ networks, as well as the ability to adapt and scale to new model architectures,
 to AI workloads. ML application development with the eIQ Neutron NPU is fully supported by the 
 [eIQ machine learning software development environment](https://www.nxp.com/design/design-center/software/eiq-ml-development-environment/eiq-toolkit-for-end-to-end-model-development-and-deployment:EIQ-TOOLKIT).
 The eIQ AI SW Stack provides a streamlined development experience for developers and end-users of NXP products.
-eIQ extensions connect broader AI ecosystems to the edge, such as the NVIDIA TAO extension, which enables developers to bring AI models trained and fine-tuned with TAO to NXP-powered edge devices.
+eIQ extensions connect broader AI ecosystems to the edge, such as the NVIDIA TAO extension, which enables developers 
+to bring AI models trained and fine-tuned with TAO to NXP-powered edge devices.
 
 
 ## Supported NXP platforms
@@ -35,37 +36,28 @@ improvements. NXP and the ExecuTorch community is actively developing this codeb
 
 ## Neutron Backend implementation and SW architecture
 Neutron Backend uses the eIQ Neutron Converter as ML compiler to compile the delegated subgraph to Neutron microcode. 
-The Neutron Converter accepts the ML model in LiteRT format, for the **eIQ Neutron N3** class  therefore the Neutron Backend uses the LiteRT flatbuffers format as IR between the ExecuTorch and Neutron Converter ML compiler. 
-
-The Neutron Backend in its early prototype phase, is based on existing NXP products, such as 
-onnx2tflite, known from the NXP's eIQ Toolkit. 
-The **onnx2tflite** is a converter from the ONNX format to LiteRT (formerly known as TFLite).
-It consists of 3 stages: 
-* ONNX Model Parsing
-* Tensor Format Inference, to identify tensors using channel-first layer
-* ONNX to LiteRT Conversion 
-* Optimization Passes, which operate on top of the LiteRT format
-* LiteRT Serialization 
-
-Due to the similarities between ONNX to LiteRT and Edge to LiteRT conversion, the Neutron Backend's 
-currently leverages the Tensor format Inference and LiteRT Optimizer. 
-This shall be considered as temporary solution, intended to be replaced with: 
-* Dim Order (https://github.com/pytorch/executorch/issues/4873)
-* Corresponding ExecuTorch/ATen passes
-
-before reaching higher maturity status by the end of 2025. 
+The Neutron Converter accepts the ML model in LiteRT format, for the **eIQ Neutron N3** class  therefore the Neutron Backend
+uses the LiteRT flatbuffers format as IR between the ExecuTorch and Neutron Converter ML compiler.
 
 ## Layout
-The current code base is as follows:
 * `backend/ir/` - TFLite/LiteRT based IR to represent the Edge Subgraph, taken from onnx2tflite code base and extended to
   support Edge Dialect to LiteRT conversion.
     * `backend/ir/converter` - Neutron Backends conversion from Edge (ATen) Dialect to LiteRT, TFLite. The subfolder
       `node_conveters` is structured as single module for each Edge operator.
-    * `backend/ir/lib` - automatically generated handlers from LiteRT flatbuffers schema
+    * `backend/ir/lib` - automatically generated handlers from LiteRT flatbuffers schema.
     * `backend/ir/tflite_generator` and `backend/ir/tflite_optimizer` handle the serialization
        of the in-memory built subgraph for delegation into LiteRT/TFLite flatbuffers 
        representation. Code taken from the onnx2tflite tool.
-*  `quantizer` - Neutron Backends quantizer implementation. 
+*  `edge_passes` - Various passes operating on Edge dialect level. 
+*  `quantizer` - Neutron Backend quantizer implementation. 
+*  `runtime` - Neutron Backend runtime implementation. For running compiled on device.
+*  `tests/` - Unit tests for Neutron backend.
+    * `tests/converter/node_converter` - Operator level unit tests.
+
+* `examples/nxp/` - Example models and scripts for running them.
+
+## Examples
+Please see this [README.md](https://github.com/pytorch/executorch/blob/main/examples/nxp/README.md).
 
 ## Help & Improvements
 If you have problems or questions or have suggestions for ways to make

examples/nxp/README.md

@@ -1,20 +1,46 @@
-# PyTorch Model Delegation to Neutron Backend
+# ExecuTorch Neutron Backend examples
+This directory contains examples demonstrating the use of ExecuTorch AoT flow to convert a PyTorch model to ExecuTorch
+format and delegate the model computation to eIQ Neutron NPU using the eIQ Neutron Backend.
 
-In this guide we will show how to use the ExecuTorch AoT flow to convert a PyTorch model to ExecuTorch format and delegate the model computation to eIQ Neutron NPU using the eIQ Neutron Backend.
+## Layout
+* `experimental/` - contains CifarNet model example.
+* `models` - various example models.
+* `aot_neutron_compile.py` - script with end-to-end ExecuTorch AoT Neutron Backend workflow.
+* `README.md` - this file.
+* `run_aot_example.sh` - utility script for aot_neutron_compile.py.
+* `setup.sh` - setup script for Neutron Converter installation.
 
-First we will start with an example script converting the model. This example show the CifarNet model preparation. It is the same model which is part of the `example_cifarnet`
+## Setup
+Please finish tutorial [Setting up ExecuTorch](https://pytorch.org/executorch/main/getting-started-setup).
 
-The steps are expected to be executed from the executorch root folder.
-1. Run the setup.sh script to install the neutron-converter:
+Run the setup.sh script to install the neutron-converter:
 ```commandline
-$ examples/nxp/setup.sh
+$ ./examples/nxp/setup.sh
 ```
 
-2. Now run the `aot_neutron_compile.py` example with the `cifar10` model 
-```commandline
-$ python -m examples.nxp.aot_neutron_compile --quantize \
-    --delegate --neutron_converter_flavor SDK_25_09 -m cifar10 
-```
+## Supported models
+* CifarNet
+* MobileNetV2
+
+## PyTorch Model Delegation to Neutron Backend
+First we will start with an example script converting the model. This example show the CifarNet model preparation. 
+It is the same model which is part of the `example_cifarnet` in 
+[MCUXpresso SDK](https://www.nxp.com/design/design-center/software/development-software/mcuxpresso-software-and-tools-/mcuxpresso-software-development-kit-sdk:MCUXpresso-SDK).
+
+The NXP MCUXpresso software and tools offer comprehensive development solutions designed to help accelerate embedded 
+system development of applications based on MCUs from NXP. The MCUXpresso SDK includes a flexible set of peripheral 
+drivers designed to speed up and simplify development of embedded applications.
+
+The steps are expected to be executed from the `executorch` root folder.
+
+1. Run the `aot_neutron_compile.py` example with the `cifar10` model 
+    ```commandline
+    $ python -m examples.nxp.aot_neutron_compile --quantize \
+        --delegate --neutron_converter_flavor SDK_25_09 -m cifar10 
+    ```
 
-3. It will generate you `cifar10_nxp_delegate.pte` file which can be used with the MXUXpresso SDK `cifarnet_example` project, presented [here](https://mcuxpresso.nxp.com/mcuxsdk/latest/html/middleware/eiq/executorch/docs/nxp/topics/example_applications.html#how-to-build-and-run-executorch-cifarnet-example).
-To get the MCUXpresso SDK follow this [guide](https://mcuxpresso.nxp.com/mcuxsdk/latest/html/middleware/eiq/executorch/docs/nxp/topics/getting_mcuxpresso.html), use the MCUXpresso SDK v25.03.00. 
+2. It will generate you `cifar10_nxp_delegate.pte` file which can be used with the MCUXpresso SDK `cifarnet_example` 
+project, presented [here](https://mcuxpresso.nxp.com/mcuxsdk/latest/html/middleware/eiq/executorch/docs/nxp/topics/example_applications.html#how-to-build-and-run-executorch-cifarnet-example).
+This project will guide you through the process of deploying your PTE model to the device.
+To get the MCUXpresso SDK follow this [guide](https://mcuxpresso.nxp.com/mcuxsdk/latest/html/middleware/eiq/executorch/docs/nxp/topics/getting_mcuxpresso.html),
+use the MCUXpresso SDK v25.09.00.