back to top
Saturday, July 27, 2024

ASUS’s new AI Pod brings cutting-edge NVIDIA processors to power generative AI

At Computex 2024, ASUS will unveil its latest AI server, the ESC AI Pod, which features cutting-edge NVIDIA processors and advanced cooling solutions.

Published:

Published:

Trending Stories

- Advertisement -

At Computex 2024, ASUS unveiled its latest innovation in AI servers, the ASUS ESC AI Pod, powered by the most recent NVIDIA processors. NVIDIA's founder and CEO, Jensen Huang, was present to introduce this remarkable advancement.

The ASUS ESC AI Pod is an advanced, full-rack solution featuring NVIDIA's Blackwell technology, combining GPUs, CPUs, and switches. It is equipped with the NVIDIA GB200 Grace Blackwell Superchip and fifth-generation NVIDIA NVLink technology, offering unparalleled AI computing performance. The system supports liquid-to-air and liquid-to-liquid cooling solutions, ensuring optimal performance even under intense workloads.

Kaustubh Sanghani, vice president of GPU product management at NVIDIA, remarked, “At Computex, ASUS will showcase a wide range of servers powered by NVIDIA's AI platform, designed to meet the unique demands of modern enterprises.”

Versatile server lineup

ASUS also introduced a comprehensive lineup of servers based on the NVIDIA MGX architecture. These include the 2U ESC NM1-E1 and ESC NM2-E1, featuring NVIDIA GB200 NVL2 servers, and the 1U ESR1-511N-M1. Utilising NVIDIA's GH200 Grace Hopper Superchip, these servers are tailored for large-scale AI and high-performance computing (HPC) applications. They facilitate rapid data transfers, deep- (DL) training and inference, data analytics, and other compute-intensive tasks.

In the HPC domain, ASUS presented the latest HGX servers. The ESC N8, powered by the 5th Gen Intel Xeon Scalable processors and NVIDIA Blackwell Tensor Core GPUs, and the ESC N8A, powered by EPYC 9004 and NVIDIA Blackwell GPUs, both feature enhanced thermal solutions. These designs ensure optimal performance and lower Power Usage Effectiveness (PUE), catering specifically to AI and data science applications requiring heavy computational workloads.

Networking capabilities

ASUS's AI server solutions integrate NVIDIA BlueField-3 SuperNICs and Data Processing Units (DPUs). These components adhere to the standards set by NVIDIA's Spectrum-X Ethernet networking platform, providing exceptional networking capabilities essential for generative AI infrastructures. ASUS promises “best-of-breed” networking for AI applications, marking a significant step forward in AI server technology.

Computex 2024 has highlighted ASUS's commitment to pushing the boundaries of AI technology. With the new ESC AI Pod and a robust lineup of NVIDIA-powered servers, ASUS is poised to meet the ever-growing demands of AI and HPC applications, offering enterprises unparalleled performance and versatility.

Tech Edition has partnerships that involve sponsored content. While this financial support helps us with daily operations, it doesn't affect the integrity of our reviews. We remain committed to delivering honest and insightful content to our readers.

Tech Edition is now on Telegram! Join our channel here and catch all the latest tech news!



Emma Job
Emma Job
Emma is a freelance news editor at Tech Edition. With a decade's experience in content writing, she revels in both crafting and immersing herself in narratives. From tracking down viral trends to delving into the most recent news stories, her goal is to deliver insightful and timely content to her readers.

Featured Content

Top picks for wet & dry vacuums: Enhance your home cleaning in Singapore

Discover the best wet & dry vacuums for 2024, featuring top models like the Dreame H14 and Dyson WashG1, each offering unique cleaning technologies and customisable modes for superior floor care.

Related Stories