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

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.