overhaul elements of index.rst and inst.rst

docs/conf.py

@@ -65,6 +65,7 @@
     'sphinx.ext.githubpages',
     'linuxdoc.rstFlatTable',
     "notfound.extension",
+    'sphinx_copybutton' #need to add for copyable code blocks.
 	#'recommonmark',
 	#'sphinx_markdown_tables',
 	#'edit_on_github',

docs/examples.rst

@@ -1,17 +1,13 @@
 ##########################
-Examples, Demos, Tutorials 
+Examples
 ##########################
 
-This page introduces various demos, examples, and tutorials currently available with the Ryzen™ AI Software. 
-
-*************************
-Getting Started Tutorials
-*************************
+This page introduces examples currently available with the Ryzen™ AI Software. 
 
 NPU
 ~~~
 
-- :doc:`Getting Started Tutorial for INT8 models <getstartex>` - Uses a custom ResNet model to demonstrate: 
+- :doc:`ResNet50 INT8 example <getstartex>` - Uses a custom ResNet model to demonstrate: 
 
   - Pretrained model conversion to ONNX 
   - Model Quantization using AMD Quark quantizer 

docs/getstartex.rst

@@ -1,7 +1,7 @@
 :orphan:
 
 ########################
-Getting Started Tutorial
+ResNet50 Tutorial
 ########################
 
 This tutorial uses a fine-tuned version of the ResNet model (using the CIFAR-10 dataset) to demonstrate the process of preparing, quantizing, and deploying a model using Ryzen AI Software. The tutorial features deployment using both Python and C++ ONNX runtime code.
@@ -79,9 +79,10 @@ Step 2: Prepare dataset and ONNX model
 
 This example utilizes a custom ResNet model finetuned using the CIFAR-10 dataset
 
-The ``prepare_model_data.py`` script downloads the CIFAR-10 dataset in pickle format (for python) and binary format (for C++). This dataset is used in the subsequent steps for quantization and inference. The script also exports the provided PyTorch model into ONNX format. The following snippet from the script shows how the ONNX model is exported:
+The ``prepare_model_data.py`` script downloads the CIFAR-10 dataset in pickle format (for python) and binary format (for C++). 
+*The CIFAR-10 dataset consists of 60,000 32x32 colour images in 10 classes, with 6,000 images per class. There are 50,000 training images and 10,000 test images.* You can learn more about the CIFAR-10 dataset here: https://www.cs.toronto.edu/~kriz/cifar.html. This dataset is used in the subsequent steps for quantization and inference. The script also exports the provided PyTorch model into ONNX format. The following snippet from the script shows how the ONNX model is exported:
 
-.. code-block::
+.. code-block:: python
 
     dummy_inputs = torch.randn(1, 3, 32, 32)
     input_names = ['input']
@@ -277,12 +278,16 @@ Prerequisites
 Install OpenCV
 --------------
 
-It is recommended to build OpenCV from the source code and use static build. The default installation location is "\install" , the following instruction installs OpenCV in the location "C:\\opencv" as an example. You may first change the directory to where you want to clone the OpenCV repository.
+If using C++, build OpenCV from source code and use static build. The following instructions install OpenCV in the location "C:\\opencv" as an example, but you can change the location as needed.
 
+First navigate to a suitable directory where you add GitHub repositories. First, clone the OpenCV repository:
 .. code-block:: bash
 
    git clone https://github.com/opencv/opencv.git -b 4.6.0
    cd opencv
+
+Then, you can build OpenCV with the following:
+.. code-block:: bash
    cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DCMAKE_CONFIGURATION_TYPES=Release -A x64 -T host=x64 -G "Visual Studio 17 2022" "-DCMAKE_INSTALL_PREFIX=C:\opencv" "-DCMAKE_PREFIX_PATH=C:\opencv" -DCMAKE_BUILD_TYPE=Release -DBUILD_opencv_python2=OFF -DBUILD_opencv_python3=OFF -DBUILD_WITH_STATIC_CRT=OFF -B build
    cmake --build build --config Release
    cmake --install build --config Release
@@ -298,7 +303,10 @@ Run the following command to build the resnet example. Assign ``-DOpenCV_DIR`` t
 
 .. code-block:: bash
 
-   cd getting_started_resnet/cpp
+   cd RyzenAI-SW\tutorial\getting_started_resnet\int8\cpp
+
+.. code-block:: bash
+
    cmake -DCMAKE_EXPORT_COMPILE_COMMANDS=ON -DBUILD_SHARED_LIBS=OFF -DCMAKE_POSITION_INDEPENDENT_CODE=ON -DCMAKE_CONFIGURATION_TYPES=Release -A x64 -T host=x64 -DCMAKE_INSTALL_PREFIX=. -DCMAKE_PREFIX_PATH=. -B build -S resnet_cifar -DOpenCV_DIR="C:/opencv/build" -G "Visual Studio 17 2022"
 
 This should generate the build directory with the ``resnet_cifar.sln`` solution file along with other project files. Open the solution file using Visual Studio 2022 and build to compile. You can also use "Developer Command Prompt for VS 2022" to open the solution file in Visual Studio.

docs/index.rst

@@ -7,19 +7,187 @@ AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing
 .. image:: images/rai-sw.png
    :align: center
 
-***********
-Quick Start
-***********
+.. _hardware-support:
+****************
+Hardware Support
+****************
+Ryzen AI 1.6 Software runs on AMD processors outlined below. For a more detailed list of supported devices, refer to the `processor specifications <https://www.amd.com/en/products/specifications/processors.html>`_ page (scroll to the "AMD Ryzen™ AI" column toward the right side of the table, and select "Available" from the pull-down menu). Support for Linux is coming soon in Ryzen AI 1.6.1.
+
+.. list-table:: Supported Ryzen AI Processor Configurations
+   :header-rows: 1
+   :widths: 25 25 12 22 12 10 10 10
+
+   * - Series
+     - Codename
+     - Abbreviation
+     - Graphics Model
+     - Ryzen™ AI Support
+     - Launch Year
+     - Windows
+     - Linux
+   * - Ryzen AI Max PRO 300 Series
+     - Strix Halo
+     - STX
+     - Radeon 8000S Series
+     - ✅
+     - 2025
+     - ☑️
+     - 
+   * - Ryzen AI PRO 300 Series
+     - Strix Point / Krackan Point
+     - STX/KRK
+     - Radeon 800M Series
+     - ✅
+     - 2025
+     - ☑️
+     - 
+   * - Ryzen AI Max 300 Series
+     - Strix Halo
+     - STX
+     - Radeon 8000S Series
+     - ✅
+     - 2025
+     - ☑️
+     - 
+   * - Ryzen Z2
+     - Z2
+     - Z2
+     - Radeon
+     - ✅
+     - 2025
+     - 
+     - 
+   * - Ryzen AI 300 Series
+     - Strix Point
+     - STX
+     - Radeon 800M Series
+     - ✅
+     - 2025
+     - ☑️
+     - 
+   * - Ryzen Pro 200 Series
+     - Hawk Point
+     - HPT
+     - Radeon 700M Series
+     - ✅
+     - 2025
+     - ☑️
+     - 
+   * - Ryzen 200 Series
+     - Hawk Point
+     - HPT
+     - Radeon 700M Series
+     - ✅
+     - 2025
+     - ☑️
+     - 
+   * - Ryzen PRO 8000 Series
+     - Hawk Point
+     - HPT
+     - Radeon 700M Series
+     - ✅
+     - 2024
+     - ☑️
+     - 
+   * - Ryzen 8000 Series
+     - Hawk Point
+     - HPT
+     - Radeon 700M Series
+     - ✅
+     - 2024
+     - ☑️
+     - 
+   * - Ryzen Pro 7000 Series
+     - Phoenix
+     - PHX
+     - Radeon 700M Series
+     - ✅
+     - 2023
+     - ☑️
+     - 
+   * - Ryzen 7000 Series
+     - Phoenix
+     - PHX
+     - Radeon 700M Series
+     - ✅
+     - 2023
+     - ☑️
+     - 
+
+************
+LLMs Support
+************
+Ryzen AI 1.6 supports running LLMs on the hardware configurations in the table below. 
+
+.. list-table:: LLM Support on Ryzen AI Processors
+   :header-rows: 1
+   :widths: 25 25 25 25 25 25
+
+   * - Processor Series
+     - Codename
+     - CPU
+     - GPU
+     - NPU
+     - Hybrid (NPU + iGPU)
+   * - Ryzen AI 300
+     - STX/KRK
+     - ✓
+     - ✓
+     - ✓
+     - ✓
+   * - Ryzen AI 7000/8000/200
+     - PHX/HPT
+     - ✓
+     - ✓
+     - ✗
+     - ✗
+
+For more details on running LLMs, refer to the :doc:`llm/overview` page.
+
+*******************
+Other Model Support
+*******************
+
+The following table lists which types of models are supported on the different hardware platforms.
+
+.. list-table::
+   :header-rows: 1
+
+   * - Model Type
+     - STX/KRK
+     - PHX/HPT
+   * - CNN INT8
+     - ✓
+     - ✓
+   * - CNN BF16
+     - ✓
+     - 
+   * - NLP BF16
+     - ✓
+     - 
+
+***********************
+Installation & Examples
+***********************
+To get started with installing and using Ryzen AI Software, visit the following:
 
-- :ref:`Supported Configurations <supported-configurations>`
 - :doc:`inst`
 - :doc:`examples`
 
 *************************
 Development Flow Overview
 *************************
 
-The Ryzen AI development flow does not require any modifications to the existing model training processes and methods. The pre-trained model can be used as the starting point of the Ryzen AI flow.
+A typical Ryzen AI flow might look like the following:
+
+1. Begin with a pretrained PyTorch (*.pt) model.
+2. Convert the model to ONNX (*.onnx) format. You can follow the PyTorch documentation here: `Export a PyTorch model to ONNX <https://docs.pytorch.org/tutorials/beginner/onnx/export_simple_model_to_onnx_tutorial.html>`_.
+3. Optionally, quantize the model with `AMD Quark <https://quark.docs.amd.com/latest/>`_ for a reduced model size.
+4. Deploy the model for inference in your application. 
+5. Run the :doc:`ai_analyzer` to assess model performance.
+
+.. note::
+   You may find that you can skip steps 1-3 and deploy a model right away if you already have an ONNX model that fits on your device.
 
 Quantization
 ============

docs/inst.rst

@@ -1,16 +1,16 @@
 .. include:: /icons.txt
 
-#########################
-Installation Instructions
-#########################
+#################################
+Windows Installation Instructions
+#################################
 
 
 
 *************
 Prerequisites
 *************
 
-The Ryzen AI Software supports AMD processors with a Neural Processing Unit (NPU). Refer to the release notes for the full list of :ref:`supported configurations <supported-configurations>`.
+The Ryzen AI Software supports AMD processors with a Neural Processing Unit (NPU). For a list of supported hardware configurations, refer to :ref:`hardware-support`.
 
 The following dependencies must be installed on the system before installing the Ryzen AI Software:
 
@@ -21,21 +21,32 @@ The following dependencies must be installed on the system before installing the
    * - Dependencies
      - Version Requirement
    * - Windows 11
-     - build >= 22621.3527
-   * - Visual Studio
-     - 2022
-   * - cmake
-     - version >= 3.26
-   * - Python distribution (Miniforge preferred)
-     - Latest version
+     - >= 22621.3527
+   * - `Visual Studio Community <https://apps.microsoft.com/detail/xpdcfjdklzjlp8?hl=en-US&gl=US>`_
+     - 2022 with `Desktop Development with C++` checked
+   * - `cmake <https://cmake.org/download/>`_
+     - >= 3.26
+   * - `Python (Miniforge preferred) <https://conda-forge.org/download/>`_
+     - >= 3.10
+   * - :ref:`install-driver` 
+     - >= 32.0.203.280
 
 |
 
 |warning| **IMPORTANT**:
 
-- Visual Studio 2022 Community: ensure that `Desktop Development with C++` is installed
+- Miniforge: Ensure that the proper miniforge paths are set in the System PATH variable. Open Windows PowerShell by right clicking and "Run as administrator" to set system path environment varibles. After opening a command prompt, you can use the following code to add the appropriate environment variables, substituting your actual paths:
+.. code-block:: powershell
 
-- Miniforge: ensure that the following path is set in the System PATH variable: ``path\to\miniforge3\condabin`` or ``path\to\miniforge3\Scripts\`` or ``path\to\miniforge3\`` (The System PATH variable should be set in the *System Variables* section of the *Environment Variables* window).
+  $existingPath = [System.Environment]::GetEnvironmentVariable('Path', 'Machine')
+
+.. code-block:: powershell
+
+  $newPaths = "C:\Users\<user>\miniforge3\Scripts;C:\Users\<user>\miniforge3\condabin"
+
+.. code-block:: powershell
+
+  [System.Environment]::SetEnvironmentVariable('Path', "$existingPath;$newPaths", 'Machine')
 
 |
 
@@ -45,17 +56,14 @@ The following dependencies must be installed on the system before installing the
 Install NPU Drivers
 *******************
 
-- Download and Install the NPU driver version: 32.0.203.280 or newer using the following links: 
+- Under "Task Manager" in Windows, go to Performance -> NPU0 to check the driver version. 
+- If needed, download the NPU driver version: 32.0.203.280 or the latest 32.0.203.304 here:
 
   - :download:`NPU Driver (Version 32.0.203.280) <https://account.amd.com/en/forms/downloads/ryzenai-eula-public-xef.html?filename=NPU_RAI1.5_280_WHQL.zip>`
   - :download:`NPU Driver (Version 32.0.203.304) <https://account.amd.com/en/forms/downloads/ryzen-ai-software-platform-xef.html?filename=NPU_RAI1.6_304_WHQL.zip>`
-
-- Install the NPU drivers by following these steps:
-
-  - Extract the downloaded ZIP file.
-  - Open a terminal in administrator mode and execute the ``.\npu_sw_installer.exe`` file.
-
-- Ensure that NPU MCDM driver (Version:32.0.203.280, Date:5/16/2025) or (Version:32.0.203.304, Date:10/07/2025) is correctly installed by opening Task Manager -> Performance -> NPU0.
+- Extract the downloaded ZIP file.
+- Right click and "Run as administrator" on ``npu_sw_installer.exe``.
+- Check that the NPU driver (Version:32.0.203.280, Date:5/16/2025) or (Version:32.0.203.304, Date:10/07/2025) was correctly installed by opening Task Manager -> Performance -> NPU0.
 
 
 .. _install-bundled:
@@ -72,7 +80,7 @@ Install Ryzen AI Software
   - Provide the destination folder for Ryzen AI installation (default: ``C:\Program Files\RyzenAI\1.6.0``)
   - Specify the name for the conda environment (default: ``ryzen-ai-1.6.0``)
 
-The Ryzen AI Software packages are now installed in the conda environment created by the installer.
+The Ryzen AI Software packages should now installed in the conda environment created by the installer.
 
 .. note::
    **The LLM flow requires an additional patch installation.** See the next section (:ref:`apply-patch`) for instructions.