Difference between revisions of "Edge AI SDK/AI Framework/AMD"

From ESS-WIKI
Jump to: navigation, search
(→‎Vision Application)
 
(26 intermediate revisions by 4 users not shown)
Line 1: Line 1:
 +
 
= RyzenAI SDK =
 
= RyzenAI SDK =
  
 +
AMD Ryzen™ AI software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen AI powered PCs1. Ryzen AI software enables applications to run on the neural processing unit (NPU) built in the AMD XDNA™ architecture, the first dedicated AI processing silicon on a Windows x86 processor2, and supports an integrated GPU (iGPU).
  
−
AMD Ryzen™ AI software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen AI powered PCs1. Ryzen AI software enables applications to run on the neural processing unit (NPU) built
+
Ryzen™ AI software enables developers to efficiently port their pre-trained PyTorch or TensorFlow models to run on the integrated GPU (iGPU) or Neural Processing Unit (NPU) available in select Ryzen AI-powered laptops. Applications are deployed using ONNX Runtime, giving the user easy inferencing across the different hardware.
−
in the AMD XDNA™ architecture, the first dedicated AI processing silicon on a Windows x86 processor2, and supports an integrated GPU (iGPU).
 
−
 
 
−
 
 
−
Ryzen™ AI software enables developers to efficiently port their pre-trained PyTorch or TensorFlow models to run on the integrated GPU (iGPU) or Neural Processing Unit (NPU) available in select Ryzen AI-powered laptops.  
 
−
Applications are deployed using ONNX Runtime, giving the user easy inferencing across the different hardware.
 
−
 
 
  
 
AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs. Ryzen AI software enables applications to run on the neural processing unit (NPU) built in the AMD XDNA™ architecture, as well as on the integrated GPU. This allows developers to build and deploy models trained in PyTorch or TensorFlow and run them directly on laptops powered by Ryzen AI using ONNX Runtime and the Vitis™ AI Execution Provider (EP).
 
AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs. Ryzen AI software enables applications to run on the neural processing unit (NPU) built in the AMD XDNA™ architecture, as well as on the integrated GPU. This allows developers to build and deploy models trained in PyTorch or TensorFlow and run them directly on laptops powered by Ryzen AI using ONNX Runtime and the Vitis™ AI Execution Provider (EP).
  
−
Addressing Various AI Workloads 
+
Addressing Various AI Workloads  -Large Language Models -Image and Video Generation -Recommendation -Computer Vision
−
-Large Language Models  
 
−
-Image and Video Generation  
 
−
-Recommendation  
 
−
-Computer Vision
 
  
 
= Application =
 
= Application =
 +
 
=== <span style="font-size:larger;">Vision Application</span> ===
 
=== <span style="font-size:larger;">Vision Application</span> ===
  
−
{| border="1" cellpadding="1" cellspacing="1" style="width: 500px;"
+
{| border="1" cellpadding="1" cellspacing="1" style="width: 900px;"
 +
|-
 +
| style="width: 154px;" | Application
 +
| style="width: 179px;" | Model
 +
| style="width: 179px;" | AIMB-2210 FPS (video file)
 +
|-
 +
| style="width: 154px;" | Object Detection
 +
| style="width: 154px;" | yolov8-onnx-FP32 (CPU)
 +
| style="width: 154px;" | 25
 +
|-
 +
| style="width: 154px;" | Object Detection
 +
| style="width: 154px;" | yolov8-onnx-FP32 (iGPU)
 +
| style="width: 154px;" | 35
 
|-
 
|-
−
| style="width: 137px;" | Application
+
| style="width: 154px;" | Object Detection
−
| style="width: 150px;" | Model
+
| style="width: 154px;" | yolovX-onnx-int (NPU)
−
| style="width: 225px;" | AI Comput Units
+
| style="width: 154px;" | 65
 
|-
 
|-
−
| style="width: 137px;" | Object Detection
+
| style="width: 154px;" | Face Detection
−
| style="width: 150px;" | yolov8/X
+
| style="width: 154px;" | yolov8-onnx-FP32 (CPU)
−
| style="width: 225px;" | CPU (v8), iGPU(v8), NPU (X)
+
| style="width: 154px;" | 35
 
|-
 
|-
−
| style="width: 137px;" | Face Detection
+
| style="width: 154px;" | Face Detection
−
| style="width: 150px;" |  
+
| style="width: 154px;" | yolov8-onnx-FP32 (iGPU)
−
| style="width: 225px;" | CPU, iGPU, NPU
+
| style="width: 154px;" | 45
 
|-
 
|-
 +
| style="width: 154px;" | Face Detection
 +
| style="width: 154px;" | RetinaFace-onnx-int (NPU)
 +
| style="width: 154px;" | 65
 
|}
 
|}
  
−
= Benchmark =
+
<span style="font-size:small;">To Run NPU (YolovX)</span>
 +
 
 +
[[File:Ryzen8000 npu yolovX.png|800px|Ryzen8000 npu yolovX.png]]
 +
 
 +
=== <span style="font-size:larger;">Generate AI</span> ===
 +
<span style="font-size:larger;">Delete model</span>
 +
 
 +
1. On Lemonade Model Management - Installed Models, select a model and delete it.
 +
 
 +
*Lemonade Model Management&nbsp;: [http://localhost:23953/#model-management http://localhost:23953/#model-management]
 +
 
 +
<span style="font-size:larger;">[[File:Image 1757555415360.png|none|900x600px|image_1757555415360.png]]</span>
 +
 
 +
More Info refer GenAI&nbsp;[https://ess-wiki.advantech.com.tw/view/Edge_AI_SDK/GenAIChatbot Link]<br/> &nbsp;
 +
 
 +
= Benchmark (Vision AI) =
  
 +
<span style="font-size:larger;">You can refer the [https://github.com/amd/RyzenAI-SW/tree/main/onnx-benchmark link]to test the performance with the benchmark tool</span>
  
 +
=== <span style="font-size:larger;">mobilenet-ssd V2</span> ===
  
 +
[[File:Ryzen8000 benchmark.png|400px|Ryzen8000 benchmark.png]]
  
 
= System Monitoring =
 
= System Monitoring =
 +
 +
[[File:Ryzen8000 sys.png|800px|Ryzen8000 sys.png]]

Latest revision as of 10:52, 25 September 2025

RyzenAI SDK

AMD Ryzen™ AI software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen AI powered PCs1. Ryzen AI software enables applications to run on the neural processing unit (NPU) built in the AMD XDNA™ architecture, the first dedicated AI processing silicon on a Windows x86 processor2, and supports an integrated GPU (iGPU).

Ryzen™ AI software enables developers to efficiently port their pre-trained PyTorch or TensorFlow models to run on the integrated GPU (iGPU) or Neural Processing Unit (NPU) available in select Ryzen AI-powered laptops. Applications are deployed using ONNX Runtime, giving the user easy inferencing across the different hardware.

AMD Ryzen™ AI Software includes the tools and runtime libraries for optimizing and deploying AI inference on AMD Ryzen™ AI powered PCs. Ryzen AI software enables applications to run on the neural processing unit (NPU) built in the AMD XDNA™ architecture, as well as on the integrated GPU. This allows developers to build and deploy models trained in PyTorch or TensorFlow and run them directly on laptops powered by Ryzen AI using ONNX Runtime and the Vitis™ AI Execution Provider (EP).

Addressing Various AI Workloads  -Large Language Models -Image and Video Generation -Recommendation -Computer Vision

Application

Vision Application

Application Model AIMB-2210 FPS (video file)
Object Detection yolov8-onnx-FP32 (CPU) 25
Object Detection yolov8-onnx-FP32 (iGPU) 35
Object Detection yolovX-onnx-int (NPU) 65
Face Detection yolov8-onnx-FP32 (CPU) 35
Face Detection yolov8-onnx-FP32 (iGPU) 45
Face Detection RetinaFace-onnx-int (NPU) 65

To Run NPU (YolovX)

Ryzen8000 npu yolovX.png

Generate AI

Delete model

1. On Lemonade Model Management - Installed Models, select a model and delete it.

image_1757555415360.png

More Info refer GenAI Link
 

Benchmark (Vision AI)

You can refer the linkto test the performance with the benchmark tool

mobilenet-ssd V2

Ryzen8000 benchmark.png

System Monitoring

Ryzen8000 sys.png

Retrieved from "https://ess-wiki.advantech.com.tw/wiki/index.php?title=Edge_AI_SDK/AI_Framework/AMD&oldid=40946"