Nvidia handed its rack design to the open hardware community, because building the factory is now the hard part.
- Nvidia contributed its Vera Rubin MGX rack and compute-tray designs to the Open Compute Project on October 12.
- The third-generation tray has no cables, no hoses and no fans. Liquid cooling reaches the busbar, which carries 5,000 amps without making the rack bigger.
- A single rack now reaches 250 kilowatts, and more than 50 partners build against the same footprint. The design keeps the single-wide OCP footprint and cools to a 45C inlet, which lowers the chiller load.
- With Cisco, Nvidia described USFP, a pluggable optical module that pushes a lane to 400Gb/s and reaches 12.8Tb/s per switch.
- Nvidia, AMD, Google and Meta also published an open specification for the data center that houses it all, spelling out power, cooling and layout.
Read the full analysis for the three questions to ask before buying AI capacity.
Get the next one before it is old news
Independent analysis of cloud-native infrastructure, Kubernetes and data center economics. No vendor spin.