Nvidia Says Vera Rubin Enters Full Production as Microsoft Completes First VR200 NVL72 Rack Bring-Up
Nvidia's Vera Rubin has entered full production, Jensen Huang said at the company's GTC keynote, and Microsoft has completed bring-up of its first Rubin VR200 NVL72 rack with Foxconn. The announcement advances the rollout beyond Dell's earlier delivery of the first Vera Rubin NVL72 rack to CoreWeave.
Huang said the Vera Rubin supply chain is already twice the size of Grace Blackwell. Semianalysis said wafer-level mass production has started, but rack-level mass production has not yet begun and remains in the engineering and quality-sample stage. Dell previously said the CoreWeave system carried 72 Rubin GPUs, 36 Vera CPUs, 3.6 exaFLOPS of FP4 inference, 75 terabytes of fast memory and 260 terabytes per second of NVLink bandwidth.
From the sources (25 posts)
@firstadopterRT @MichaelDell: We have the first @DellTech + @nvidia Vera Rubin NVL72 @CoreWeave. Here we go! 🚀
@mweinbachRT @MichaelDell: We have the first @DellTech + @nvidia Vera Rubin NVL72 @CoreWeave. Here we go! 🚀
@firstadopterDate check. May?!
@_arohan_RT @MichaelDell: We have the first @DellTech + @nvidia Vera Rubin NVL72 @CoreWeave. Here we go! 🚀
@semianalysis_BREAKING NEWS: COREWEAVE & DELL IS THE FIRST CLOUD TO ANNOUNCE THAT THEY HAVE RUBIN VR200 NVL72 WITH FULLY PASSING L11 DIAGS. Next Step is to get multiple racks burnin in a couple & do software level bringup like sglang, vllm, dynam
@scaling01RT @MichaelDell: We have the first @DellTech + @nvidia Vera Rubin NVL72 @CoreWeave. Here we go! 🚀
@jordannanosRT @MichaelDell: We have the first @DellTech + @nvidia Vera Rubin NVL72 @CoreWeave. Here we go! 🚀
@jukan05RT @MichaelDell: We have the first @DellTech + @nvidia Vera Rubin NVL72 @CoreWeave. Here we go! 🚀
@tengyanaiVera Rubin NVL72 first shipment confirmed CoreWeave has ~$100B revenue backlog and a $21B Meta deal that explicitly includes Vera Rubin deployments.. hmm...
@teortaxestexWill Blackwell have been the Nvidia generation with the shortest effective life cycle ever? Feels like we've only just gotten inference with Dynamo and such working efficiently, and maybe half a batch of frontier models have been trained. H
@stocksavvyshay$DELL delivered the world’s first $NVDA Vera Rubin NVL72 rack to $CRWV marking the first confirmed shipment of Nvidia’s next-gen AI rack system. The system includes 72 Rubin GPUs, 36 Vera CPUs, 3.6 exaFLOPS of FP4 inference, 75TB of fast m
@rohanpaul_aiSome cool visuals. Dell Delivers world's first Nvidia Vera Rubin NVL72 rack to CoreWeave. It packs 72 Rubin GPUs, 36 Vera CPUs, 3.6 exaFLOPS of FP4 inference, 75 TB of fast memory, and 260 TB/s NVLink bandwidth
@michaeldellWe have the first @DellTech + @nvidia Vera Rubin NVL72 @CoreWeave. Here we go! 🚀
@stocksavvyshayRT @StockSavvyShay: $DELL delivered the world’s first $NVDA Vera Rubin NVL72 rack to $CRWV marking the first confirmed shipment of Nvidia’s…
@tftc21Dell just delivered the world's first server rack built on Nvidia's next-generation Vera Rubin chips. The customer is CoreWeave, one of the fastest growing AI infrastructure companies in the world. This is the company that most people st
@milkroadaiDell just made history this weekend and it is the culmination of an execution streak that no other company in enterprise technology has matched (Save this). Dell delivered the world's first fully validated NVIDIA Vera Rubin NVL72 rack to C
@tengyanaiJensen: "the more you buy the more you make" "everyone wants to make money" "vera rubin is in full production"
@financialjuiceNvidia Vera Rubin enters full production to power autonomous AI factories globally
@jukan05Vera Rubin is in Full production
@yoolimleenews"Vera Rubin is now in full production," Jensen Huang says in Nvidia GTC keynote
@stockmktnewzNvidia $NVDA CEO just said that Vera Rubin is now in full production The supply chain Nvidia created for Vera Rubin is twice as large as Grace Blackwell
@financialjuiceNvidia Vera BlueField-4 STX delivers autonomous AI storage processing with in-silicon security
@firstadopterVera CPU rack! is in the middle
@semianalysis_BREAKING NEWS: JENSEN JUST ANNOUNCED MICROSOFT HAS FINISHED BRING UP ON THEIR FIRST RUBIN VR200 NVL72 RACK with their ODM partner, Foxconn. Jensen also announced that wafer-level mass production has started. That being said, rack-level mas
@tengyanaiJensen: "vera rubin was not built to run AI. It was built to run agents" "today's nvidia's token cost is the lowest in the world" "nvidia has become the largest networking provider in the world"