Wiwynn Unveils AI Servers with NVIDIA GB300 NVL72 at GTC 2025

Mar 19, 2025
Wiwynn showcases its latest AI servers featuring the NVIDIA GB300 NVL72 platform and advanced liquid-cooling systems at GTC 2025.

Wiwynn has showcased its latest AI server innovations at GTC 2025, featuring the NVIDIA GB300 NVL72 platform, announced in a press release. These servers, developed in collaboration with Wistron, are powered by the NVIDIA Blackwell Ultra platform, offering increased AI FLOPS and over 20TB of HBM3e memory.

The servers incorporate a fully liquid-cooled design, integrating NVIDIA ConnectX-8 SuperNIC and the NVIDIA Quantum-X800 InfiniBand and Spectrum-X Ethernet networking platforms. This setup achieves superior thermal efficiency and AI computing acceleration, optimizing performance for AI reasoning and video inference applications.

Additionally, Wiwynn introduced its UMS100L rack-level liquid cooling management system, designed for DLC racks and immersion cooling tanks. This system features advanced leakage detection and real-time monitoring, ensuring the safety and efficiency of data center operations.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.