HPE Ships First Nvidia Grace Blackwell SystemHPE Ships First Nvidia Grace Blackwell System

Hewlett Packard Enterprise (HPE) has shipped its first Nvidia Blackwell-based solution, the Nvidia GB200 NVL72.

HPE designed the rack-scale system to help service providers and large enterprises deploy large, complex AI clusters with advanced, direct liquid cooling solutions for efficiency and performance.

“AI service providers and large enterprise model builders are under tremendous pressure to offer scalability, extreme performance, and fast time-to-deployment,” said Trish Damkroger, senior vice president and general manager of HPC & AI infrastructure solutions, HPE.

HPE's Trish Damkroger

The two companies launched Nvidia AI Computing by HPE, a portfolio of co-developed products and services designed around generative AI, at HPE Discover in June 2024.

The Nvidia GB200 NVL72 features shared-memory, low-latency architecture with GPU technology designed for extremely large AI models of more than 1 trillion parameters, in one memory space. GB200 NVL72 offers integration of NVIDIA CPUs, GPUs, compute and switch trays, networking, and software for performance to address heavily parallelizable workloads. These include gen AI model training and inferencing, along with Nvidia software applications.

“Engineers, scientists and researchers need cutting-edge liquid cooling technology to keep up with increasing power and compute requirements,” said Bob Pette, VP of enterprise platforms at Nvidia. “Building on continued collaboration between HPE and Nvidia, HPE’s first shipment of Nvidia GB200 NVL72 will help service providers and large enterprises efficiently build, deploy and scale large AI clusters.”

Related:HPE Partners 'Stand Out in Crowded Market' with Latest Server Launch

Nvidia's Bob Pette

HPE said it tailored its HPC & AI Custom Support Services, including onsite support, customized and sustainability services, to meet customer needs.

HPE Looking to Pull Ahead of AI Rivals

This week HPE also announced eight new HPE ProLiant Compute Gen12 servers. The latest additions feature new security capabilities, optimized performance for complex workloads and management features enhanced by AI. The new servers will feature upcoming Intel Xeon 6 processors for data center and edge environments.

HPE CEO Antonio Neri has claimed the vendor is uniquely positioned to become an AI leader. He pointed to HPE’s super-computing capabilities, data center services, more than 300 liquid cooling patents to help make running AI systems sustainable, networking from its currently on-hold $14 billion Juniper Networks acquisition, and servers as its AI differentiators.