Wiwynn Showcases AI Servers Featuring NVIDIA GB300 NVL72 Platform and Liquid-Cooling Innovations at GTC 2025

San Jose, Cal. – March 18, 2025 — Wiwynn, an innovative cloud IT infrastructure provider for data centers, is showcasing its latest innovations at GTC 2025 (booth #1804). Wiwynn will highlight its AI servers, developed in collaboration with Wistron, powered by the NVIDIA Blackwell Ultra platform. Additionally, Wiwynn will have its advanced rack-level liquid cooling management system, UMS100L, on display demonstrating leadership in AI GPU servers to address the growing demand of computing and cooling capabilities in the era of GenAI. Key highlights include:

• NVIDIA GB300 NVL72: Wiwynn and Wistron are among the first in line with NVIDIA GB300 NVL72 Accelerated by NVIDIA Blackwell Ultra with increased AI FLOPS and over 20TB of HBM3e memory, GB300 NVL72 leads the new era of AI and the next wave of accelerated computing. Featuring the cutting-edge fully liquid cooling design, NVIDIA ConnectX^®-8 SuperNIC and the networking platform integration of NVIDIA Quantum-X800 InfiniBand and NVIDIA Spectrum-X™ Ethernet, GB300 NVL72 achieve superior rack-level thermal efficiency and AI computing acceleration, unleashing the optimal performance to enable breakthrough performance for AI reasoning, agentic AI and video inference applications.
  
  
• NVIDIA HGX™ B300 NVL16: debut a brand-new 10U HGX system built with NVIDIA Blackwell Ultra based HGX™ B300 NVL16, leads the new era of AI with optimized compute and increased memory, delivering breakthrough performance. By supporting power delivery options of both power supply units (PSU) and busbars, Wiwynn and Wistron enable datacenters to deploy this cutting-edge solution rapidly within their existing infrastructure.
  
  
• NVIDIA Spectrum-4: Building on the extensive development of optimized Ethernet connectivity solutions with the NVIDIA Spectrum-4 MAC, the companies are showcasing the revolutionary NVIDIA Spectrum-X™ Ethernet for AI networking platform with integration of SONiC and NVIDIA^® Cumulus^®. The innovative network solution is designed to power multi-tenant, hyperscale AI clouds through advanced Ethernet connectivity and enable flexibility of usage scenarios for datacenters.
  
  
• UMS100L: the purpose-built rack-level liquid cooling management system is designed for DLC racks, immersion cooling tanks, and data center facilities, compatible with various in-row CDUs and sidecars. It features advanced leakage detection, real-time monitoring, and rapid containment capabilities, ensuring the safety of critical equipment and data-driven decisions for datacenters.

"In today's AI revolution, optimizing computing power requires comprehensive integration at the rack level – from GPUs, computing systems and cooling to power and networking," said William Lin, President at Wiwynn. "As one of the first in line with NVIDIA GB300 NVL72 readiness, we're excited to showcase our innovative liquid-cooled, fan-less design AI rack solution and advanced HGX and networking platforms in collaboration with NVIDIA and Wistron. Our expertise in system integration and cooling technology enables us to deliver high-performance AI computing solutions with time-to-market and keep our customers at the forefront of the AI era."

“Our collaboration is driving innovation in AI factories, enhancing performance, scalability, and sustainability to meet the evolving needs of AI,” said Kaustubh Sanghani, vice president of GPU products at NVIDIA. “Combining Wiwynn infrastructure with NVIDIA accelerated computing technologies, such as the NVIDIA GB300 NVL72 platform, enables data centers to handle AI reasoning models to power a new age of computing.”

About Wiwynn

Wiwynn is an innovative cloud IT infrastructure provider of high-quality computing and storage products, plus rack solutions for leading data centers. We are committed to the vision of “unleash the power of digitalization; ignite the innovation of sustainability”. The Company aggressively invests in next-generation technologies to provide the best TCO (Total Cost of Ownership), workload and energy-optimized IT solutions from cloud to edge.