ASUS Rolls Out NVIDIA GB300 NVL72 Rack Solution to Usher in the Next Era of Datacenters
Accelerating data center transformation with 30-minute deployment and end-to-end services
- Rack-scale AI power: 36 NVIDIA® Grace CPUs and 72 NVIDIA Blackwell Ultra GPUs deliver ultra-fast, trillion-parameter performance
- Sustainable design: NVIDIA® MGX 48U rack with liquid cooling and modular architecture for efficient scalability
- Rapid deployment: Full-rack rollout in 30 minutes via ASUS Infrastructure Deployment Center
- ASUS Professional Services: End-to-end lifecycle support ensures optimized design, integration, and long-term reliability
TAIPEI, Taiwan, October 30, 2025 — ASUS today announced the rollout of XA GB721-E2, built on NVIDIA® GB300 NVL72 rack-scale system. Designed for large-scale model training, high-throughput inference, and advanced AI/HPC workloads, the system combines breakthrough performance, sustainable liquid cooling, and serviceability at rack scale to help enterprises and research institutions accelerate innovation.
Rack-scale performance with NVIDIA Grace Blackwell Ultra GPU
NVIDIA GB300 NVL72 systems integrate 36 NVIDIA Grace CPUs and 72 NVIDIA Blackwell Ultra GPUs in a single NVIDIA NVLink domain, delivering ultra-low-latency, high-bandwidth GPU-to-GPU communication for trillion-parameter workloads. Together with NVIDIA Quantum-X800 InfiniBand platform or NVIDIA Spectrum-X Ethernet platform and NVIDIA ConnectX-8 SuperNIC, the system is engineered for high-throughput inference and cluster-scale expansion, fully support the recent need of enterprise AI factory innovation.
Comprehensive infrastructure design
To meet the power, thermal, and scalability requirements of modern data centers, the system features a comprehensive infrastructure design that integrates liquid cooling, balanced storage architecture, and modular network topology. Within a 48U NVIDIA MGX compliant rack, it incorporates nine NVIDIA NVLink switch trays and 18 compute trays, supported by manifold-based cooling for predictable performance, streamlined serviceability, and long-term sustainability.
Complementing this architecture, ASUS storage solutions offer flexible configurations to meet diverse workload requirements — from all-flash hot-tier storage for AI and HPC, to hybrid and unified systems for enterprise data management, backup, and scalability. This adaptability allows customers to build balanced infrastructures optimized for performance, efficiency, and evolving operational needs.
Streamlined infrastructure orchestration through ACC and AIDC
As part of the ASUS AI POD, the XA-GB721-E2 leverages the ASUS Control Center (ACC) and the ASUS Infrastructure Deployment Center (AIDC) to provide a turnkey rack-scale deployment and management solution. These platforms support zero-touch onboarding, centralized orchestration, and accelerated rollout — bringing full systems online in as little as 30 minutes. By combining automation with lifecycle management, ASUS enables customers to move rapidly from installation to production-scale computing with assurance and efficiency.
Professional services with customer-first precision
Deploying large-scale infrastructure involves challenges in validation, integration, and optimization — from sustaining storage pipelines and designing efficient liquid-cooling systems to configuring reliable network topologies. To meet these needs, ASUS offers Professional Services that span the entire lifecycle, working closely with customers to adapt designs and optimize every layer. With a customer-first approach, ASUS delivers precise, attentive support that enables organizations to scale computing environments sustainably while maintaining peak efficiency and long-term reliability.
