brannin mcbee
@branninmcbee
We stood up an NVIDIA Vera Rubin NVL72 cluster in days from rack handover to production, delivering it to Cognition to run agentic workloads. The first Vera Rubins powering customer innovation are live on CoreWeave. $CRWV
NVIDIA AI Infrastructure@NVIDIAAIInfra · Sep 30NVIDIA Vera Rubin NVL72 is live on @CoreWeave, and the results speak for themselves.
@cognition tested it on real-world software engineering workloads and saw 4.8x higher token throughput vs. GB200 NVL72.
From Volta to Vera Rubin, CoreWeave delivers every NVIDIA platform to
@cognition tested it on real-world software engineering workloads and saw 4.8x higher token throughput vs. GB200 NVL72.
From Volta to Vera Rubin, CoreWeave delivers every NVIDIA platform to
Open quoted post →
1 36