Delta Unveils Power and Cooling Solutions for AI Data Centers at NVIDIA GTC 2025

Mar 20, 2025
Delta Electronics has introduced new power and cooling solutions for AI data centers at NVIDIA GTC 2025, including Power Capacitance Shelves and liquid-to-liquid Coolant Distribution Units.

Delta Electronics has unveiled its latest power and cooling solutions for AI data centers at the NVIDIA GTC 2025 conference. Announced in a press release, these innovations include Power Capacitance Shelves and 1.5MW liquid-to-liquid Coolant Distribution Units (CDU), designed to enhance performance and energy efficiency in NVIDIA-enabled AI and HPC data centers.

The new Power Capacitance Shelf features built-in lithium-ion capacitors, offering high power density and a long hold-up time to stabilize power supply for AI and cloud computing servers. Additionally, Delta's liquid cooling solutions, such as the 1.5MW L2L CDU, are tailored to manage the thermal challenges of high-density racks.

Delta also showcased its AI-based Smart Manufacturing Demo Line, which integrates with NVIDIA Omniverse and Isaac Sim platforms to improve productivity and flexibility in manufacturing processes. This demonstration highlights Delta's commitment to advancing smart manufacturing through AI technologies.

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.