aiqbench takeChips & Infra
aiqbench analysis
ASUS is scaling volume production of NVIDIA Vera Rubin NVL72 systems while introducing a comprehensive AI Factory reference architecture designed to mitigate deployment risks through automated validation and thermal engineering. The showcased rack-scale solution integrates 72 Rubin GPUs with liquid cooling and advanced networking to support frontier model training and high-throughput inference workloads.
4
Sources coveringHPCwire, NVIDIA, CoreWeave, SiliconANGLE
ASUS Ramps Up NVIDIA Vera Rubin NVL72 Shipments, Showcases AI Factory Reference Architecture at SC26
HPCwire1 min read

Other coverage of this story
- HPCwire · this article
- NVIDIA · NVIDIA Vera Rubin NVL72 Leads Agentic Inference Performance on MLPerf Endpoints v1.0
- CoreWeave · CoreWeave Becomes First Cloud Provider to Deliver Multi-Rack NVIDIA Vera Rubin Results in MLPerf® Training v6.1
- SiliconANGLE · At SC26, Nvidia debuts new Rubin HPC chip, scientific research libraries
Related coverage

Chips & Infra
Achieve Productive AI Capacity Faster and More Predictably with NVIDIA DSX POD
NVIDIA · Oct 21, 2026
AI Products
NewPhotonics and Tower Semiconductor Ramp Up Optical Engine Production
Quantum Zeitgeist · Sep 18, 2026

Quantum Computing
QCi scales Quantum Computing Inc. to nearly 10,000 variables with Dirac-3S
Quantum Zeitgeist · Oct 1, 2026

Quantum Computing
ZuriQ and Rhonexum Form Multi-Year Partnership to Integrate Cryogenic Control ICs into 2D Trapped-Ion Processors
Quantum Computing Report · Oct 23, 2026