NVIDIA shares Vera Rubin rack designs with the Open Compute Project
At the OCP summit, NVIDIA contributed rack and tray designs and a new optics format built with Cisco for AI data centers.
NVIDIA shared plans for the big racks that hold AI computers. Other companies can use them too. It mostly matters to people who build data centers.
Hype check
The noise matches the real change.
Our editorial opinion, based on the sources below. How we score
Your call: hype or real?
Real = it will matter in daily use. Hype = louder than it is. One vote, and it can’t be changed.
Our view and readers’ views are opinions, not statements of fact about a product.
Why it matters
Open designs help more companies build AI data centers with the same parts. This is infrastructure news, not a product you buy.
Worth knowing: AI data centers are being built from shared, open designs.
The details
- MGX 1.2 adds blind-mate liquid cooling, a liquid-cooled 5,000A busbar and racks up to 250kW.
- NVIDIA also published a Vera CPU rack design for workloads such as tool calling.
- With Cisco it announced USFP optics, aimed at 400Gb/s per lane and about 1.3x better power efficiency.
- Meta is adopting NVIDIA Spectrum-6 102.4Tb/s Ethernet switches for Vera Rubin AI factories.
- NVIDIA, AMD, Google and Meta published Open Data Center Specification v0.7.
Receipts
The company or lab said it. Primary source linked. Open the sources and check us.
Written with the help of AI tools and checked against the sources above. How we work
See a mistake? Tell us and we’ll fix it.
