Merge branch 'main' into cvml-sdk-updates

Author: danielholanda

.github/scripts/fetch_github_issues.py

@@ -12,7 +12,7 @@
 
 def fetch_github_issues():
     """Fetch GitHub issues from the repository"""
-    repo = "amd/halo_playbooks"
+    repo = "amd/playbooks"
     token = os.environ.get("GITHUB_TOKEN", "")
 
     headers = {

.github/workflows/test-playbooks.yml

@@ -139,7 +139,7 @@ jobs:
       - name: Setup Python
         uses: actions/setup-python@v5
         with:
-          python-version: ${{ matrix.playbook == 'open-webui-chat' && '3.12' || '3.13' }}
+          python-version: ${{ (matrix.playbook == 'open-webui-chat' || matrix.playbook == 'vllm-inference') && '3.12' || '3.13' }}
 
       - name: Install test dependencies
         run: |

README.md

@@ -31,26 +31,26 @@ This is AMD's official repository of playbooks for AMD developer platforms. Each
 | **Running LLMs with PyTorch and AMD ROCm™ software** | Run powerful language models locally with PyTorch and ROCm |
 | **Running and Serving LLMs with LM Studio** | Set up LM Studio to run and serve large language models |
 | **Automating Workflows with n8n and Local LLMs** | Build an AI-powered news summarizer using n8n and Lemonade |
-| **Local LLM Coding with VSCode and Qwen3-Coder** | Use VSCode with locally-running Qwen3-Coder for private code assistance |
+| **Local LLM Coding with VS Code and Qwen3-Coder** | Use VS Code with locally-running Qwen3-Coder for private code assistance |
 | **Generating Images with ComfyUI and Z Image Turbo** | Create AI-generated images using ComfyUI with Z Image Turbo |
+| **Chat with LLMs in Open WebUI** | Set up Open WebUI to chat with local LLMs |
+| **Fine-tune LLMs with PyTorch and AMD ROCm™ software** | Fine-tune large language models using PyTorch and ROCm |
+| **Using Lemonade Across CPU, GPU, and NPU** | Learn how to use the Lemonade framework across CPU, GPU, and NPU |
+| **Optimized Fine-tuning with Unsloth** | Memory-efficient LoRA fine-tuning with Unsloth |
+| **Speech-to-Speech Translation** | Build a real-time speech-to-speech translation system |
 
 ## Coming Soon
 
 | Playbook | Description |
 |----------|-------------|
-| **Chat with LLMs in Open WebUI** | Set up Open WebUI to chat with local LLMs |
-| **Fine-tune LLMs with PyTorch and ROCm** | Fine-tune large language models using PyTorch and ROCm |
-| **Using Lemonade Across CPU, GPU, and NPU** | Learn how to use the Lemonade framework across CPU, GPU, and NPU |
 | **Local Computer Vision with Ryzen™ AI NPU** | Build local perception capabilities using CVML SDK on Ryzen AI and ROCm |
 | **Clustering Two Devices with llama.cpp RPC** | Distributed inference using RPC server across two AMD devices with llama.cpp |
 | **Getting Started with Ollama** | Install Ollama and run LLMs locally from the terminal, desktop app, or REST API |
 | **Getting Started Creating Agents with GAIA** | Build and deploy AI agents using the GAIA framework |
 | **Fine-tuning LLMs with LLaMA-Factory** | LoRA fine-tuning of large language models using LLaMA-Factory |
 | **Custom GPU Kernels with PyTorch ROCm** | Write and optimize custom GPU kernels using PyTorch and ROCm |
-| **Optimized Fine-tuning with Unsloth** | Memory-efficient LoRA fine-tuning with Unsloth |
 | **Quick Start on vLLM** | Run inference and serving using vLLM |
 | **Clustering with RCCL** | Multi-node cluster using two AMD devices with RCCL |
-| **Speech-to-Speech Translation** | Build a real-time speech-to-speech translation system |
 
 ## AMD AI Developer Program
 

assets/banner.png

@@ -25,11 +25,24 @@ This tutorial teaches you how to use ComfyUI with the Z Image Turbo model on you
 ## Installing Dependencies
 
 <!-- @os:windows -->
-<!-- @require:comfyui,driver -->
+<!-- @require:driver,comfyui -->
 <!-- @os:end -->
 
 <!-- @os:linux -->
-<!-- @require:comfyui,rocm,driver,pytorch -->
+
+<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
+#### Create a Virtual Environment
+On Linux, open a terminal in the directory of your choice and run the following prompt to create a venv:
+
+```bash
+sudo apt update
+sudo apt install -y python3-venv
+python3 -m venv llm-env
+source llm-env/bin/activate
+```
+<!-- @device:end -->
+
+<!-- @require:driver,rocm,pytorch,comfyui -->
 <!-- @os:end -->
 
 <!-- @os:windows -->
@@ -301,7 +314,7 @@ To launch ComfyUI on Windows, simply click the ComfyUI shortcut on your Desktop.
 
 To launch ComfyUI:
 
-1. Navigate to `/usr/local/bin/ComfyUI/` (or to the appropriate folder if installed manually)
+1. Ensure you are within the ComfyUI directory. 
 2. Run `python3 main.py --use-pytorch-cross-attention`
 
 ComfyUI starts a local web server. Open your browser to `http://127.0.0.1:8188` to access the interface.

playbooks/core/comfyui-image-gen/README.md

@@ -32,7 +32,7 @@ LM Studio is a powerful GUI-based wrapper for [llama.cpp](https://github.com/ggm
 Learn how to start chatting with a ChatGPT-grade LLM completely locally.  
 
 1. Open LMStudio. 
-2. Press `Ctrl + L` to open the Model Loader, select `Manually chose model load parameters`, and click on `GPT-OSS 120B`
+2. Press `Ctrl + L` to open the Model Loader, select `Manually choose model load parameters`, and click on `GPT-OSS 120B`
 3. Make sure "show advanced settings" is checked.  
 4. Change `Context Length` as desired. Higher context length means more model memory, but more system memory used. Recommended for this playbook is 4096.
 5. Make sure `GPU Offload` is set to maximum and `Flash Attention` is On
@@ -80,7 +80,7 @@ LM Studio also offers an OpenAI compliant endpoint in the form of LM Studio Serv
 
 To set up LM Studio Server, use the following instructions:
 
-1. On the left hand side, click on the `Developer` tab (command line icon) or `CTRL + 2` and then click on `Server Settings`.  
+1. On the left hand side, click on the `Developer` tab (command line icon) or `Ctrl + 2` and then click on `Server Settings`.  
 2. (Optional): If you want to serve the model over your LAN, check `Serve on Local Network`. If you want to use with a website or extensive calling within VS Code, check `Enable CORS`. 
 3. On the upper left corner, make sure the server is running by clicking on the toggle button in front of `Status`.
 4. An OpenAI compliant endpoint will now be running. The address is typically at http://127.0.0.1:1234  
@@ -120,7 +120,7 @@ This model will now be accessible through the LM Studio Server endpoint and will
 Having just created the OpenAI Compatible endpoint, let's look at how to integrate this into a Python developer environment (such as VSCode) and use your system as a local API Provider. 
 
 1. Create a Python virtual environment:
-<!-- @device:halo_box_ -->
+<!-- @device:halo_box -->
 <!-- @os:windows -->
     On Windows, open a terminal in the directory of your choice and follow the commands to create a venv.
     ```bash
@@ -186,22 +186,22 @@ Having just created the OpenAI Compatible endpoint, let's look at how to integra
     )
     print("Attempting to connect to local LM Studio server...")
 
-        try:
-            # Create a simple chat completion request
-            completion = client.chat.completions.create(
-                model="local-model", # The model identifier is optional in local mode
-                messages=[
-                    {"role": "system", "content": "You are a helpful coding assistant."},
-                    {"role": "user", "content": "Explain Python decorators in 1 sentence"}
-                ],
-                temperature=0.7,
-            )
-            # Print the response
-            print("\nConnection Successful! Server Response:\n")
-            print(completion.choices[0].message.content)
-
-        except Exception as e:
-            print(f"\nConnection Failed: {e}. Ensure LM Studio server is running on port 1234.")
+    try:
+        # Create a simple chat completion request
+        completion = client.chat.completions.create(
+            model="local-model", # The model identifier is optional in local mode
+            messages=[
+                {"role": "system", "content": "You are a helpful coding assistant."},
+                {"role": "user", "content": "Explain Python decorators in 1 sentence"}
+            ],
+            temperature=0.7,
+        )
+        # Print the response
+        print("\nConnection Successful! Server Response:\n")
+        print(completion.choices[0].message.content)
+
+    except Exception as e:
+        print(f"\nConnection Failed: {e}. Ensure LM Studio server is running on port 1234.")
     ```
 <!-- @os:windows -->
 <!-- @test:id=lmstudio-ping-endpoint-windows timeout=300 hidden=True -->

playbooks/core/lmstudio-rocm-llms/README.md

@@ -23,7 +23,7 @@ This tutorial uses PyTorch powered by AMD ROCm™ software to run models that ca
 
 ### Create a Virtual Environment
 
-<!-- @device:halo_box_ -->
+<!-- @device:halo_box -->
 <!-- @os:windows -->
 On Windows, open a terminal in the directory of your choice and follow the commands to create a venv with ROCm+Pytorch already installed.
 <!-- @test:id=create-venv timeout=60 -->
@@ -86,10 +86,10 @@ source llm-env/bin/activate
 
 ### Installing Basic Dependencies
 <!-- @os:linux -->
-<!-- @require:rocm,pytorch,driver -->
+<!-- @require:driver,rocm,pytorch -->
 <!-- @os:end -->
 <!-- @os:windows -->
-<!-- @require:pytorch,driver -->
+<!-- @require:driver,pytorch -->
 <!-- @os:end -->
 
 ### Installing Additional Dependencies

playbooks/core/pytorch-rocm-llms/README.md

@@ -17,47 +17,24 @@ SPDX-License-Identifier: MIT
 <!-- @os:end -->
 
 <!-- @os:linux -->
-
-#### Create a Virtual Environment
-<!-- @device:halo_box_ -->
-On Linux, open a terminal in the directory of your choice and run the following prompt to create a venv with ROCm+Pytorch already installed:
-
-```bash
-sudo apt update
-sudo apt install -y python3-venv
-python3 -m venv llm-env --system-site-packages
-source llm-env/bin/activate
-```
-<!-- @device:end -->
-
-<!-- @device:halo,stx,krk,rx7900xt,rx9070xt -->
-On Linux, open a terminal in the directory of your choice and run the following prompt to create a venv:
-
-```bash
-sudo apt update
-sudo apt install -y python3-venv
-python3 -m venv llm-env
-source llm-env/bin/activate
-```
-<!-- @device:end -->
-
 #### Clone ComfyUI
 ```bash
 git clone https://github.com/Comfy-Org/ComfyUI.git
 ```
 
-#### Optionally checkout a specific version
+#### (Optional) Checkout a specific version
 ```bash
-git checkout v0.17.2
+git checkout v0.19.2
 ```
 
 #### Install ComfyUI requirements
 
 With the Python virtual environment activated, run:
 ```bash
+cd ComfyUI
 pip install -r requirements.txt
 ```
 
-> **Note**: See [ComfyUI GitHub](https://github.com/comfyanonymous/ComfyUI) for more information.
+> **Note**: See [ComfyUI GitHub](https://github.com/comfy-org/ComfyUI) for more information.
 
 <!-- @os:end -->

playbooks/dependencies/comfyui.md

@@ -4,9 +4,8 @@ Copyright Advanced Micro Devices, Inc.
 SPDX-License-Identifier: MIT
 -->
 
-### AMD GPU Driver
-
 <!-- @os:windows -->
+### AMD GPU Driver
 
 Update to the latest AMD GPU driver using `AMD Software: Adrenalin Edition™`.
 
@@ -22,10 +21,12 @@ Get-CimInstance Win32_VideoController | Select-Object Name, DriverVersion
 <!-- @os:end -->
 
 <!-- @os:linux -->
+<!-- @device:rx7900xt,rx9070xt -->
+### AMD GPU Driver
 
 Download and install the latest AMD GPU driver for Linux:
 
-1. Visit the [AMD Linux Drivers](https://amd.com/en/support/download/linux-drivers.html) page.
+1. Visit the [AMD Linux Drivers](https://www.amd.com/en/support/download/linux-drivers.html) page.
 2. Follow the installation instructions provided on the download page.
 
 <!-- @test:id=amd-gpu-visible-linux timeout=60 hidden=True -->
@@ -39,4 +40,5 @@ test -d /opt/rocm
 test -e /opt/rocm/lib/libroctx64.so.4 -o -e /opt/rocm/lib/libroctx64.so
 ```
 <!-- @test:end --> 
+<!-- @device:end -->
 <!-- @os:end -->

playbooks/dependencies/driver.md

@@ -6,54 +6,47 @@ SPDX-License-Identifier: MIT
 
 ### ROCm
 
-<!-- @device:halo_box,halo,stx -->
-#### 1. Install AMD ROCm™ software on Linux (Ubuntu 24.04)
-
-These steps install the **system ROCm 7.2.1 runtime** on Ubuntu 24.04.
-> Note: ROCm is a **system-wide install** on Linux.
-
+**Add the current user to the render and video groups.** 
 ```bash
-sudo apt update
-wget https://repo.radeon.com/amdgpu-install/7.2.1/ubuntu/noble/amdgpu-install_7.2.1.70201-1_all.deb
-sudo apt install ./amdgpu-install_7.2.1.70201-1_all.deb
-sudo amdgpu-install -y --usecase=rocm --no-dkms
+sudo usermod -a -G render,video $LOGNAME
 ```
-
-#### 2. Set the correct user permissions
+**Restart your system to apply the settings.**
 ```bash
-sudo usermod -aG render,video $USER
+sudo reboot
 ```
-
-#### 3. Reboot the system
+**Install ROCm in the created virtual environment.**
+> **Note**: Ensure the virtual environment is active before proceeding.
+<!-- @device:halo,halo_box -->
 ```bash
-sudo reboot
+python -m pip install --upgrade pip
+python -m pip install --index-url https://repo.amd.com/rocm/whl/gfx1151/ "rocm[libraries,devel]"
+
 ```
-This is important for the runtime stack and permissions to settle.
+<!-- @device:end -->
 
-#### 4. Verify that ROCm is installed correctly and usable
+<!-- @device:krk -->
 
-<!-- @test:id=verify-linux-rocm-installation timeout=180 -->
 ```bash
-# Check ROCm path (paths should exist)
-ls -l /opt/rocm
-ls -l /opt/rocm/lib/libroctx64.so*
+python -m pip install --upgrade pip
+python -m pip install --index-url https://repo.amd.com/rocm/whl/gfx1152/ "rocm[libraries,devel]"
 
-# Check ROCm device files (Device files owned by the render group should be visible)
-ls -l /dev/kfd
-ls -l /dev/dri/renderD* 
+```
+<!-- @device:end -->
 
-# Check user groups ($USER should be listed in both render and video)
-id
-groups
+<!-- @device:stx -->
 
-# Check ROCm with rocminfo ('Permission denied' error should NOT be seen)
-rocminfo | sed -n '1,120p'
+```bash
+python -m pip install --upgrade pip
+python -m pip install --index-url https://repo.amd.com/rocm/whl/gfx1150/ "rocm[libraries,devel]"
 
-# Check installed ROCm version
-cat /opt/rocm/.info/version
 ```
-<!-- @test:end -->
-
-Refer this [official documentation](https://rocm.docs.amd.com/projects/radeon-ryzen/en/latest/docs/install/installryz/native_linux/install-ryzen.html) for more info.
+<!-- @device:end -->
 
+<!-- @device:rx7900xt,rx9070xt -->
+```bash
+python -m pip install --upgrade pip
+python -m pip install --index-url https://repo.amd.com/rocm/whl/gfx120x-all/ "rocm[libraries,devel]"
+```
 <!-- @device:end -->
+
+For further installation help, please see this [link](https://rocm.docs.amd.com/en/7.12.0-preview/install/rocm.html?fam=ryzen&gpu=max-pro-395&os=ubuntu&os-version=24.04&i=pip).