Difference between revisions of "Edge AI SDK"

From ESS-WIKI
Jump to: navigation, search
 
(5 intermediate revisions by the same user not shown)
Line 1: Line 1:
  
&nbsp; <span style="font-size:larger;">'''Advantech&nbsp;Edge AI SDK'''&nbsp;offers a consistent development experience for Advantech Edge AI Box (adnd Embedded IPC)</span>. <span style="font-size:larger;">It provides&nbsp;a suitable runtime framework based on platforms like&nbsp;'''Intel x86_64 and&nbsp;NVIDIA Jetson, '''along with AI Accelerators like&nbsp;Intel Arch GPU,&nbsp;Hailo VPU and&nbsp;NVIDIA Card. The SDK&nbsp;also features&nbsp;real-time monitoring, benchmarks,&nbsp; and AI inference examples for hardware.&nbsp;Developers&nbsp;can effortlessly&nbsp;set&nbsp;up an&nbsp;Edge AI environment, allowing&nbsp;them to kickstart their AI applications quickly on&nbsp;Advantech Edge AI platforms&nbsp;with various&nbsp; AI Accelerators.</span>
+
'''Advantech’s [https://campaign.advantech.online/en/edgeaisdk/ Edge AI SDK]''' offers a comprehensive platform designed for seamless edge AI development. With pre-configured hardware and perfectly tuned software, it provides a plug-and-play experience, enabling cost-effective customization of LLMs, efficient toolkit compatibility, and effortless management of large-scale edge deployments. Simplify your journey to AI innovation with tools that ensure reliability, scalability, and ease of use.
 +
 
 +
Advantech's Edge AI SDK encompasses three main components:
 +
 
 +
•<u>[https://genai-studio.gitbook.io/docs GenAI Studio]</u>: Facilitates cost-effective creation, evaluation, and integration of custom LLMs on-premises.
 +
 
 +
•<u>[https://ess-wiki.advantech.com.tw/view/Edge_AI_SDK/InferenceKit Inference Kit]</u>: Enables rapid optimization and assessment of efficient AI runtimes compatible with embedded operating systems.
 +
 
 +
•<u>[https://campaign.advantech.online/en/DeviceOn/index.html Orchestration Platform]</u>: Provides efficient management of AI model and application updates across extensive edge deployments, integrating MLOps for streamlined operations, powered by [https://campaign.advantech.online/en/DeviceOn/index.html DeviceOn].
  
 
&nbsp;
 
&nbsp;
  
[[File:EdgeAISuite SW Stack.jpg|center|900x600px|Edge AI Suite SW Stack]]
+
[[File:Edge AI SDK Overview.png|center|900x600px|Edge AI SDK Overview]]
  
 
&nbsp;
 
&nbsp;
Line 16: Line 24:
 
{| border="0" cellpadding="5" cellspacing="0" style="width:100%;"
 
{| border="0" cellpadding="5" cellspacing="0" style="width:100%;"
 
|-
 
|-
| style="background-color: rgb(54, 100, 177); text-align:center; font-size:larger;" | <font color="#ffffff">'''Edge AI SDK'''</font>
+
| style="background-color: rgb(54, 100, 177); text-align:center; font-size:larger;" | [https://genai-studio.gitbook.io/docs <font color="#ffffff">'''GenAI Studio'''</font>]
|-
 
| style="vertical-align: top;line-height:20px;" |
 
'''[[Edge_AI_SDK/User_Guide_300|User Guide (3.x.0)]]'''<br/> '''[[Edge_AI_SDK/User_Guide_201|User Guide (2.0.1)]]'''
 
 
 
----
 
'''Intel''' '''[[Edge_AI_SDK/AI_Framework/OpenVINO|OpenVINO]]'''<br>
 
'''NVIDIA''' '''[[Edge_AI_SDK/AI_Framework/JetsonOrin#JetPack|JetPack]]''', '''[[Edge_AI_SDK/AI_Framework/Nvidia_x86_64#CUDA|CUDA]]''' <br>
 
'''Hailo''' '''[[Edge_AI_SDK/AI_Framework/Hailo#Hailo_AI_Suite|Hailo AI Suite]]'''
 
----
 
'''[[Edge_AI_SDK/DeviceOn|DeviceOn]]'''
 
 
 
 
|}
 
|}
  
 +
&nbsp;
  
 
| style="width:33%; vertical-align: top;padding-left: 15px;" |  
 
| style="width:33%; vertical-align: top;padding-left: 15px;" |  
 
{| border="0" cellpadding="5" cellspacing="0" style="width:100%;"
 
{| border="0" cellpadding="5" cellspacing="0" style="width:100%;"
 
|-
 
|-
| style="background-color: rgb(54, 100, 177); text-align:center; font-size:larger;" | <font color="#ffffff">'''[[Edge_AI_SDK/InferenceKit|Inference Kit]]'''</font>
+
| style="background-color: rgb(54, 100, 177); text-align:center; font-size:larger;" | [https://ess-wiki.advantech.com.tw/view/Edge_AI_SDK/InferenceKit <font color="#ffffff">'''Inference Kit'''</font>]
|-
 
| style="vertical-align: top;line-height:20px;" |
 
'''Intel'''<br/> '''[[Edge_AI_SDK/AI_System/ARK-3534|ARK-3534]]'''<br/> '''[[Edge_AI_SDK/AI_System/AIR-150|AIR-150]]'''<br/> '''[[Edge_AI_SDK/AI_System/AIR-510|AIR-510]]'''<br/>
 
'''[[Edge_AI_SDK/AI_System/AFE-R360|AFE-R360]]'''
 
 
 
----
 
 
 
'''NVIDIA Jetson'''<br/> '''[[Edge_AI_SDK/AI_System/AIR-030|AIR-030]]'''
 
 
 
 
|}
 
|}
  
Line 49: Line 38:
 
{| border="0" cellpadding="5" cellspacing="0" style="width:100%;"
 
{| border="0" cellpadding="5" cellspacing="0" style="width:100%;"
 
|-
 
|-
| style="background-color: rgb(54, 100, 177); text-align:center; font-size:larger;" | <font color="#ffffff">'''AI Accelerator'''</font>
+
| style="background-color: rgb(54, 100, 177); text-align:center; font-size:larger;" | [https://campaign.advantech.online/en/DeviceOn/index.html <font color="#ffffff">'''Orchestration Platform'''</font>]
|-
 
| style="vertical-align: top;line-height:20px;" |
 
'''Intel'''<br/> '''[[Edge_AI_SDK/Accelerator/EAI-3100|EAI-3100]]'''
 
 
 
----
 
 
 
'''Hailo'''<br/> '''[[Edge_AI_SDK/Accelerator/Hailo-8|Hailo-8]]'''
 
 
 
----
 
 
 
'''NVIDIA'''<br/> '''[[Edge_AI_SDK/Accelerator/RTX-A5000|RTX-A5000]]'''
 
 
 
 
|}
 
|}
  
 
|}
 
|}
  
 +
&nbsp;
  
 
+
&nbsp;
{| border="0" cellpadding="0" cellspacing="5" style="width: 100%;"
 
|-
 
| style="width: 50%; vertical-align: top;padding-left: 15px; text-align: left;" | [[Edge_AI_SDK/Download|<span style="display:inline-block;width:100%; height: 40px; text-align:center; text-decoration:none;border:1px solid #3664B1;font-size:16px;color:#3664B1;line-height:36px;padding:0;margin: auto;">'''Download'''</span>]]
 
| style="width: 50%; vertical-align: top;padding-left: 15px; text-align: left;" | [[Edge_AI_SDK/Q&A|<span style="display:inline-block;width:100%; height: 40px; text-align:center; text-decoration:none;border:1px solid #3664B1;font-size:16px;color:#3664B1;line-height:36px;padding:0;margin: auto;">'''FAQ & Tips'''</span>]]
 
|}
 
  
 
|}
 
|}

Latest revision as of 10:03, 17 January 2025

Advantech’s Edge AI SDK offers a comprehensive platform designed for seamless edge AI development. With pre-configured hardware and perfectly tuned software, it provides a plug-and-play experience, enabling cost-effective customization of LLMs, efficient toolkit compatibility, and effortless management of large-scale edge deployments. Simplify your journey to AI innovation with tools that ensure reliability, scalability, and ease of use.

Advantech's Edge AI SDK encompasses three main components:

GenAI Studio: Facilitates cost-effective creation, evaluation, and integration of custom LLMs on-premises.

Inference Kit: Enables rapid optimization and assessment of efficient AI runtimes compatible with embedded operating systems.

Orchestration Platform: Provides efficient management of AI model and application updates across extensive edge deployments, integrating MLOps for streamlined operations, powered by DeviceOn.

 

Edge AI SDK Overview

 

GenAI Studio

 

Inference Kit
Orchestration Platform