CoreWeave Inc. (NASDAQ: CRWV) announced it has become the first AI cloud provider to deploy and validate NVIDIA's Vera Rubin NVL72 system, according to a company statement.

The deployment includes completion of system-level validation for the entire rack-scale architecture. The NVIDIA Vera Rubin NVL72 features 72 NVIDIA Rubin GPUs and 36 NVIDIA Vera CPUs per rack, connected via a 260 TB/s NVIDIA NVLink 6th-generation fabric.

According to NVIDIA specifications, the system delivers up to 10 times better inference per watt, requires up to one-fourth fewer GPUs, and costs one-tenth per million tokens compared to NVIDIA Blackwell architecture.

CoreWeave developed several infrastructure components for the deployment, including Valvey, a programmable per-rack valve assembly for liquid cooling management, and Racky, a unified rack control appliance. The system supports both NVIDIA Quantum-X800 InfiniBand and NVIDIA Spectrum-X Ethernet with RDMA over Converged Ethernet, providing 1.6 Tb/s of backend bandwidth per GPU.

"Vera Rubin is the most capable AI platform NVIDIA has ever built," said Ian Buck, vice president of Hyperscale and High-Performance Computing at NVIDIA. "CoreWeave has consistently been at the frontier of deploying each new generation of NVIDIA architecture at scale."

The deployment utilizes Dell Technologies PowerEdge XE9812 servers and features Micron 7600 SSDs in what the company describes as one of the first liquid-cooled NVMe storage solutions deployed at rack-scale.

CoreWeave completed its public listing on NASDAQ in March 2025, according to the company statement.