Salute Launches Direct-to-Chip Liquid Cooling Operations Service for AI Data Centers

Nov 3, 2025
Salute has introduced a new Direct-to-Chip liquid cooling operations service for AI and HPC data centers, announced at NVIDIA GTC Washington DC. The service aims to help operators manage high-density, liquid-based environments safely and efficiently.

Salute has launched what it calls the data center industry's first comprehensive service for Direct-to-Chip (DTC) liquid cooling operations, introduced at NVIDIA GTC Washington DC, announced in a press release. The service is designed to support artificial intelligence (AI) and high-performance computing (HPC) facilities that require efficient heat management for high-density computing workloads.

The company’s DTC operational model aims to help data center operators manage the elevated risks associated with liquid cooling, including leaks, temperature spikes, and downtime. Salute’s service includes design and operational assessments that create facility-specific operational models for safe and reliable DTC liquid cooling.

Several major operators, including Applied Digital, Compass Datacenters, and SDC, have already adopted Salute as their partner for DTC liquid operations. By integrating this service, these companies aim to ensure operational continuity and protect their AI infrastructure investments.

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.