Wiwynn Unveils Double-Wide Rack for Next-Gen AI at OCP Global Summit 2025

Oct 13, 2025
Wiwynn introduced a double-wide rack architecture at the OCP Global Summit 2025 to support larger, high-power AI accelerators with integrated HVDC power and advanced liquid cooling systems.

At the OCP Global Summit 2025 in San Jose, Wiwynn unveiled a new double-wide rack architecture designed for next-generation AI workloads, announced in a press release. The system addresses the industry's shift toward larger and higher-power AI chips by combining HVDC power delivery, liquid cooling, and optimized signal integrity in a wider rack format.

The double-wide design accommodates up to four large AI accelerators per compute tray, supporting chips up to 9.5-reticle size with 12× HBM and substrates measuring 120×150 mm. The architecture maintains high-speed interconnects and reduces signal loss through shorter routing paths. It also includes a co-designed switch tray and reinforced chassis to maintain mechanical stability.

To handle increased power demands, the system integrates an HVDC power rack that converts AC to ±400/800 VDC and distributes power via busbars, improving efficiency and scalability. Additionally, Wiwynn introduced a liquid-cooled busbar to manage high current levels and maintain system reliability.

The company’s liquid cooling solutions target 4 kW-class chip thermal capacity, featuring cold plates, in-row cooling distribution units, and liquid-cooling management systems. Wiwynn stated that the architecture is engineered to support next-generation accelerators such as AMD Instinct MI400 GPUs.

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.