ASUS Reveals Optimized Liquid-Cooling Solutions and Strategic Partner Framework

Purpose-built equipment combining advanced thermal efficiency, scalable architectures, and a globally validated partner framework

• ASUS Optimized Liquid-Cooling Solutions: Direct-to-chip, in-row CDU, and hybrid designs for ultra-dense AI racks
• Strategic ecosystem: Global infrastructure and trusted component partners delivering scalable solutions
• Proven performance: Industry-leading SPEC CPU^® and MLPerf^™ results with real-world validation of world-class AI performance

TAIPEI, Taiwan, February 23, 2026 — ASUS today announced ASUS Optimized Liquid-Cooling Solutions and a strategic partner framework designed to address the escalating thermal, power, and density challenges of next-generation AI and high-performance computing data centers.

ASUS Optimized Liquid-Cooling Solutions for next-generation AI compute density

As AI and HPC workloads push compute density and power consumption beyond the capabilities of traditional air cooling, optimized liquid-cooling solutions by ASUS will provide the critical thermal management required for the next-generation NVIDIA Vera Rubin NVL72 system based data centers. By efficiently dissipating heat from high-performance CPUs, GPUs, and accelerator-dense racks, ASUS significantly reduces energy consumption, lowers PUE, and optimizes TCO while supporting unprecedented rack density.

ASUS Optimized Liquid-Cooling Solutions offer a comprehensive portfolio spanning direct-to-chip (D2C), in-row CDU–based cooling, and hybrid configurations, enabled through collaboration with global infrastructure leaders. Leveraging a strategic framework of partners — including Schneider and Vertiv, alongside precision components from Auras Technology, Cooler Master, and other industry leaders —ASUS provides purpose-built cooling solutions that ensure optimal stability and performance at scale. With 2,156 No. 1 SPEC CPU^® records and 248 No. 1 MLPerf^™results, ASUS continues to demonstrate leadership in real-world compute density and AI performance.

Real-world deployment: ASUS powers liquid-cooled AI supercomputer at NCHC

A flagship example of liquid-cooling expertise by ASUS is its recent deployment for the National Center for High-performance Computing, National Institutes of Applied Research (NCHC, NIAR) in Taiwan. The system features a dual-compute architecture, including the Nano4NVIDIA HGXH200 cluster and NVIDIA GB200 NVL72 system — Taiwan’s first fully liquid-cooled AI supercomputer deployment of this architecture.

Designed and engineered by ASUS from the ground up, the system implements direct liquid-cooling (DLC) technology to achieve an exceptional power-usage effectiveness (PUE) of just 1.18. This deployment seamlessly integrates high performance with sustainable design, demonstrating the strength of ASUS in thermal and energy management for large-scale AI infrastructure.

Join ASUS at GTC 2026

ASUS announced its participation as a Diamond Sponsor (Booth #421) at NVIDIA GTC 2026 from March 16–19 in San Jose, USA. Under the theme Trusted AI, Total Flexibility, ASUS is collaborating with NVIDIA and global infrastructure giants to showcase a robust, next-generation liquid-cooling ecosystem. Come explore with us and witness the next evolution of AI infrastructure.