PulseAugur
EN
LIVE 22:56:51

Nvidia showcases Vera Rubin NVL72 AI infrastructure running OpenAI workloads

Nvidia has provided a behind-the-scenes look at its Engineering SuperLab, showcasing the Vera Rubin NVL72 rack system. This advanced infrastructure is designed for engineers to test and develop next-generation AI platforms, including running workloads for OpenAI. The lab features demonstrations of the Vera CPU, the NVL72 rack's assembly process, and an 800VDC power delivery system. The NVL72 rack itself is equipped with high-bandwidth components like ConnectX-9 NICs, Bluefield-4 DPUs, and Nvidia's sixth-gen NVLink, capable of delivering substantial data transfer speeds. AI

IMPACT Provides insight into the hardware infrastructure supporting large-scale AI model training and development.

RANK_REASON The article provides a behind-the-scenes look at Nvidia's infrastructure and testing facilities, rather than announcing a new product or research breakthrough.

Read on Tom's Hardware →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

Nvidia showcases Vera Rubin NVL72 AI infrastructure running OpenAI workloads

COVERAGE [1]

  1. Tom's Hardware TIER_1 English(EN) · Jake Roach ·

    Behind the scenes at Nvidia's Engineering SuperLab — Vera Rubin NVL72 running OpenAI workloads, 800VDC demonstrated, and more

    Nvidia gave Tom’s Hardware an exclusive look inside its previously undisclosed Engineering SuperLab near Nvidia HQ, where we saw Vera Rubin NVL72 in action.