Difference between revisions of "Edge AI SDK/InferenceKit"
From ESS-WIKI
Eric.liang (talk | contribs) (Created page with " <span style="font-size:larger;">'''Advantech Edge AI SDK''' offers a consistent development experience for Advantech Edge AI Box (adnd Embedded IPC)</span>....") |
Eric.liang (talk | contribs) |
||
| (11 intermediate revisions by 2 users not shown) | |||
| Line 1: | Line 1: | ||
| − | + | <span style="font-size:larger;">'''Advantech's Edge AI SDK/Inference Kit''' offers a consistent development experience for Advantech Edge AI Box (adnd Embedded IPC)</span>. <span style="font-size:larger;">It provides a suitable runtime framework based on platforms like '''Intel x86_64 and NVIDIA Jetsons, '''along with AI Accelerators like Intel Arch GPU, Hailo VPU and NVIDIA Card. The SDK also features real-time monitoring, benchmarks, and AI inference examples for hardware. Developers can effortlessly set up an Edge AI environment, allowing them to edge ai workflow their AI applications quickly on Advantech Edge AI platforms with various AI Accelerators.</span> | |
| | ||
| − | [[File: | + | [[File:Inference Kit.png|center|900x600px|Edge AI Suite SW Stack]] |
| − | + | | |
| + | [[File:EdgeAISDK-Introduction-Video.jpg|center|900x600px|EdgeAISDK-Introduction-Video.jpg|link=https://edgeaisuite.blob.core.windows.net/video/Edge%20AI%20SDK%20How%20to%20Video-2025-03.mp4]] | ||
| | ||
| Line 16: | Line 17: | ||
{| 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">''' | + | | style="background-color: rgb(54, 100, 177); text-align:center; font-size:larger;" | <font color="#ffffff">'''Inference Kit'''</font> |
|- | |- | ||
| style="vertical-align: top;line-height:20px;" | | | style="vertical-align: top;line-height:20px;" | | ||
| Line 22: | Line 23: | ||
---- | ---- | ||
| − | '''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> | + | '''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]]'''<br/>'''Qualcomm''' '''[[Edge_AI_SDK/AI_Framework/Qualcomm#QCS6490_AI_Suite|QCS6490 AI Suite]]'''<br/> |
| − | '''Hailo''' '''[[Edge_AI_SDK/AI_Framework/Hailo#Hailo_AI_Suite|Hailo AI Suite]]''' | ||
| − | |||
| − | '''[[Edge_AI_SDK/ | ||
|} | |} | ||
| + | | ||
| style="width:33%; vertical-align: top;padding-left: 15px;" | | | style="width:33%; vertical-align: top;padding-left: 15px;" | | ||
| Line 37: | Line 36: | ||
|- | |- | ||
| style="vertical-align: top;line-height:20px;" | | | 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/> | + | '''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]]''' |
| − | '''[[Edge_AI_SDK/AI_System/AFE-R360|AFE-R360]]''' | ||
---- | ---- | ||
| − | '''NVIDIA Jetson'''<br/> '''[[Edge_AI_SDK/AI_System/AIR-030|AIR-030]]''' | + | '''NVIDIA Jetson'''<br/> '''[[Edge_AI_SDK/AI_System/AIR-030|AIR-030]]'''<br/> |
| + | |||
| + | ---- | ||
| + | |||
| + | '''Qualcomm'''<br/> '''[[Edge_AI_SDK/AI_System/AOM-2721|AOM-2721]]'''<br/> | ||
|} | |} | ||
| Line 66: | Line 68: | ||
|} | |} | ||
| − | + | | |
{| border="0" cellpadding="0" cellspacing="5" style="width: 100%;" | {| border="0" cellpadding="0" cellspacing="5" style="width: 100%;" | ||
Revision as of 07:02, 1 April 2025
Advantech's Edge AI SDK/Inference Kit offers a consistent development experience for Advantech Edge AI Box (adnd Embedded IPC). It provides a suitable runtime framework based on platforms like Intel x86_64 and NVIDIA Jetsons, along with AI Accelerators like Intel Arch GPU, Hailo VPU and NVIDIA Card. The SDK also features real-time monitoring, benchmarks, and AI inference examples for hardware. Developers can effortlessly set up an Edge AI environment, allowing them to edge ai workflow their AI applications quickly on Advantech Edge AI platforms with various AI Accelerators.
|