Saturday, 29 November 2025
29 C
Singapore
18.4 C
Thailand
21.9 C
Indonesia
27.5 C
Philippines

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.

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-learning (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 AMD 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.

Hot this week

Apple is expected to overtake Samsung as the world’s leading smartphone maker

Apple is projected to overtake Samsung as the world’s top smartphone maker, driven by strong iPhone 17 demand and upcoming device launches.

Sony teases A7 V as next addition to its Alpha camera lineup

Sony hints at a possible A7 V launch with a 2 December teaser featuring a bold “V”, sparking rumours of major upgrades to the Alpha series.

OpenAI was blocked from using the term ‘cameo’ in Sora after a temporary court order

A judge blocks OpenAI from using the term “cameo” in Sora until 22 December as Cameo pursues its trademark dispute.

Google denies claims that Gmail data is used to train the Gemini AI model

Google denies claims that Gmail content is used to train its Gemini AI model, offering clarity on Smart Features and user privacy.

Apple expected to launch low-cost MacBook with iPhone chip in early 2026

Apple is expected to launch a low-cost MacBook with an A18 Pro chip in February 2026, aiming to offer a budget-friendly alternative to its existing models.

DeepSeek launches open AI model achieving gold-level scores at the Maths Olympiad

DeepSeek launches Math-V2, the first open AI model to achieve gold-level scores at the International Mathematical Olympiad.

AI browsers vulnerable to covert hacks using simple URL fragments, experts warn

Experts warn AI browsers can be hacked with hidden URL fragments, posing risks invisible to traditional security measures.

Slop Evader filters out AI content to restore pre-ChatGPT internet

Slop Evader filters AI-generated content online, restoring pre-ChatGPT search results for a more human web.

Lara Croft becomes gaming’s best-selling heroine amid new Tomb Raider rumours

Lara Croft becomes gaming’s best-selling heroine as new Tomb Raider rumours fuel excitement.

Related Articles

Popular Categories