Highlights:

1. Inspur announced that its edge computing servers NE5260M5 and NF5280M5 now support the NVIDIA EGX platform and have obtained the NGC-Ready for Edge certification, allowing users to quickly deploy and efficiently run AI workloads in edge and micro data centers.

2. At only 1/2 the size of a standard 2U server and with high scalability, NE5260M5 has been implemented by the China Mobile Research Institute in large-scale applications in edge computing pilot and test scenarios.

SAN JOSE, California, January 2, 2019 – Recently at GTC China 2019 Inspur announced that its edge computing servers NE5260M5 and NF5280M5 now support the NVIDIA EGX, a high-performance cloud native platform. The servers have also obtained the NGC-Ready for Edge certification, which, in combination with the NVIDIA EGX stack optimized for edge computing, allows customers quickly deploy and efficiently run AI workloads in edge and micro data centers.

Inspur edge servers integrated with the NVIDIA EGX platform enable AI computing, edge computing, and container clouds, which help customers build efficient cloud-to-edge AI infrastructure, allowing AI to broaden its transformative reach into industries and users’ lives at large. The NGC-Ready for Edge certified Inspur AI servers and NVIDIA EGX stack can accelerate the most demanding edge AI workloads and development of new edge AI services for customers in various industries, as well as deliver real-time intelligence in retail stores, manufacturing plants, hospitals, and smart cities.

The two servers announced at the conference have been specially designed for edge computing scenarios. Among them, NE5260M5 is only 1/2 the size of a standard 2U server and can be wall-mounted. Small but highly scalable, it can be equipped with up to 6 Tesla T4 GPUs, guaranteeing sufficient performance to meet the needs of various edge AI applications, and has been implemented by the China Mobile Research Institute in large-scale applications in edge computing pilot and test scenarios. The NF5280M5 on the other hand features Inspur’s proprietary spatial layering technology and extremely flexible configuration. With unique I/O expansion modules, it can equip up to 8 Tesla T4 GPUs, making it ideal for complex compute-intensive AI workloads at the edge of networks.

In addition to announcing the support of the edge servers for NVIDIA EGX, Inspur also showcased an extensive range of AI server arrays at GTC China. At present, with AI servers that fully address data centers and edge computing and the ability to develop AI algorithms and management software, Inspur is ready to deliver full-stack AI solutions to its customers.

About Inspur

Inspur is a leading provider of data center infrastructure, cloud computing, and AI solutions, ranking among the world’s top 3 server manufacturers. Through engineering and innovation, Inspur delivers cutting-edge computing hardware design and extensive product offerings to address important technology arenas like open computing, cloud data center, AI and deep learning. Performance-optimized and purpose-built, our world-class solutions empower customers to tackle specific workloads and real-world challenges.