NVIDIA Vera Rubin NVL72 and HGX™ Rubin NVL8 Solutions
Aivres Platforms based on NVIDIA Vera Rubin NVL72 and HGX™ Rubin NVL8 to Power AI Factories
Reshaping the Future of Trillion-Parameter AI at Light-Speed
Aivres solutions based on NVIDIA Vera Rubin NVL72 and HGX Rubin NVL8 are built for next-generation AI, featuring extreme co-design integrating Rubin GPUs, Vera CPUs, NVLink 6, ConnectX-9, BlueField-4, and Spectrum-X to deliver fully optimized AI and HPC application performance with the fastest time to insights.
NVIDIA Vera Rubin NVL72 Solution
KRS8000V4 Rack-Scale Agentic AI Supercomputer
The Aivres KRS8000V4 rack-scale AI solution is based on the NVIDIA Vera Rubin NVL72 architecture, integrating 36 NVIDIA Vera CPUs and 72 NVIDIA Rubin GPUs into a fully liquid-cooled design. Optimized for trillion-parameter LLM training, large-scale inference, and emerging agentic AI workloads, KRS8000V4 builds on the architectural advancements of NVIDIA Rubin to deliver significantly improved GPU efficiency and inference cost economics, establishing a scalable foundation for next-generation AI factories.
2U NVIDIA HGX™ Rubin NVL8 Server
KR2288 Ultra-Dense Liquid-Cooling AI System
KR2288 delivers 400 PFLOPs extreme performance density in compact 2U, with a full liquid-cooled design that enables maximum energy efficiency and lower data center PUE for hyperscale deployments in AI and HPC. Its modular cold plate and front-loading M.2 designs offer ease of maintenance and future upgrades.
5U NVIDIA HGX™ Rubin NVL8 Server
KR5288 Rubin Flexible Hybrid-Cooling AI System
KR5288 Rubin features hybrid air and liquid cooling design compatible with traditional air-cooled data center architectures. It supports flexible scale-out with easy deployment without modifying power supply, cooling, or racks, allowing users to seamlessly deploy the NVIDIA Rubin platform.
