Advantech Launches AIR-310: Scalable Edge AI Inference System in a Compact and Ultra-thin Design

Publisher:EE小广播Latest update time:2024-10-30 Source: EEWORLDKeywords:Advantech Reading articles on mobile phones Scan QR code
Read articles on your mobile phone anytime, anywhere

In the fall of 2024, edge computing solutions provider Advantech launched AIR-310, a compact edge AI inference system with MXM GPU cards. Powered by 12th/13th/14th generation Intel Core 65W processors, AIR-310 delivers up to 12.99 TFLOPS of scalable AI performance in a 1.5U height chassis (215 x 225 x 55 mm) through an NVIDIA Quadro 2000A GPU card. Despite its compact size, it offers versatile connectivity with 3 LAN ports and 4 USB 3.0 ports for seamless integration of sensors and cameras for visual AI applications. The system includes intelligent fan management, an operating temperature range of -20 - 55°C, and is shock-resistant, capable of withstanding 3G vibration and 30G shock. AIR-310 can be equipped with Intel Arc A370 and NVIDIA A2000 GPUs, and has passed IEC 61000-6-2, IEC 61000-6-4 and CB/UL standards certification, ensuring stable operation 24/7 in harsh environments such as space-constrained or mobile devices. AIR-310 supports Windows 11, Linux Ubuntu 24.04 and Edge AI SDK, enabling accelerated reasoning deployment for applications such as factory defect detection, real-time video monitoring, GenAI/LLM and medical robot imaging.


image.png


Scalable AI to provide multi-tasking capabilities for vision applications


With high-performance computing and scalable AI capabilities, AIR-310 excels in handling multi-task applications. In commercial complexes, it improves safety by integrating vision and language models into surveillance systems, enabling real-time analysis of visual and text data for more accurate threat detection, improved monitoring, and proactive response. In the medical field, AIR-310 also supports currently advanced imaging applications, capable of reconstructing and analyzing CT scans and X-rays for accurate diagnosis and preoperative evaluation. It can improve medical efficiency and surgical accuracy by generating detailed reports on detected abnormalities and planning surgical pathways.


Companion software supports simplified visual AI and GenAI/LLM inference deployment


The AIR-310 MXM GPU system features a compact design with strong computing power and long lifecycle support. By using a variety of GPU cards, developers can easily leverage software ecosystems such as Intel OpenVINO, NVIDIA CUDA, and TensorRT to accelerate the development and deployment of AI models. AIR-310 seamlessly integrates with the latest Windows 11 and Linux Ubuntu 24.04 operating systems, making it suitable for multiple industries. It also supports Advantech's Edge AI SDK (version 3.0.0), providing a comprehensive environment for developing and running visual AI and GenAI/LLM inference applications. The SDK eliminates compatibility issues between software and hardware and includes code-free AI inference performance evaluation capabilities, greatly reducing setup time and accelerating the development process.


AIR-310 is available now. For more information, please contact Advantech Embedded Service Hotline 400-001-9088.


Keywords:Advantech Reference address:Advantech Launches AIR-310: Scalable Edge AI Inference System in a Compact and Ultra-thin Design

Previous article:Texas Instruments (TI)'s new programmable logic portfolio enables engineers to go from concept to prototype in minutes
Next article:When AI meets edge computing, Advantech promotes the transformation of the embedded industry with Edge AI

Latest Industrial Control Articles
Change More Related Popular Components

EEWorld
subscription
account

EEWorld
service
account

Automotive
development
circle

About Us Customer Service Contact Information Datasheet Sitemap LatestNews


Room 1530, 15th Floor, Building B, No.18 Zhongguancun Street, Haidian District, Beijing, Postal Code: 100190 China Telephone: 008610 8235 0740

Copyright © 2005-2024 EEWORLD.com.cn, Inc. All rights reserved 京ICP证060456号 京ICP备10001474号-1 电信业务审批[2006]字第258号函 京公网安备 11010802033920号