Slicast
Saturday, September 26, 2026
DarkSubscribe
Slicast
AI Infrastructure · News & Analysis
Home › Data Centers › Report
Data Centers · Report

Supermicro's NVIDIA Vera Rubin NVL72 GPU systems are now shipping with 1.8 MW in-row liquid cooling and a 1,152-GPU scalable unit.

Vera Rubin production ramps, delivering 1,152-GPU systems with integrated 1.8 MW cooling to data centers at scale.
Trade pressSlicast · September 25, 2026 at 15:01 UTC · US · Source: StorageReview.com
importance 75
Read the original
Companies in this story
NvidiaCapex history →
In-depth analysis
CommentaryNvidia vs Alibaba Zhenwu V900: Memory Claims and China's AI Chip Independence, September 2026CommentaryWhy Nvidia's AI Energy Management Alliance Signals That Grid Capacity, Not Silicon, Now Constrains AI Scale
Related reports
Data CentersSpaceX's Colossus 2 AI data center will receive 220,000 NVIDIA GB300 GPUs next week, with two additional tranches of the same quantity arriving later this year, totaling approximately 660,000 new GPUs.2026-09-26Data CentersSupermicro begins shipping NVIDIA Vera Rubin NVL72 GPU server racks, marking production availability of NVIDIA's latest high-density GPU platform for AI data centers.2026-09-24Data CentersNVIDIA launches DSX Ready qualification program to certify data center power and cooling hardware for AI-era infrastructure.2026-09-23Data CentersCivo plans to deploy 40 edge data centers across Britain to power sovereign AI, with the first site in Hertfordshire (March 2027) housing NVIDIA Vera Rubin systems and a longer-term ambition to scale to 1 GW capacity.2026-09-23Data CentersMitsubishi Electric outlines a 'Chip-to-Grid' blueprint for AI factories powered by NVIDIA, integrating on-site power management, cooling, and grid-integration infrastructure.2026-09-23
Supermicro's NVIDIA Vera Rubin NVL72 GPU… · Slicast