Cognition runs production workloads on Vera Rubin NVL72 with 4.8x token throughput
nordicinst · x · 2026-09-30
At CoreWeave Fully Connected, CoreWeave announced availability of NVIDIA Vera Rubin NVL72 systems with Spectrum-X 102.4T Ethernet. Cognition, maker of Devin, is the first customer running production workloads, seeing 4.8x higher token throughput across training, RL, and inference. CoreWeave will also offer NVIDIA Vera, the first CPU built for AI agents, and launched CoreWeave Forge for training and evaluating models and agents. NVIDIA's Ian Buck highlighted decade-long infrastructure value, noting V100 GPUs still run customer workloads.
More from Infra
- TSMC reportedly evaluating plans to build chip manufacturing facilities in Texas — Polymarket · 2026-09-30
- Dumping GPUs and tokens can meaningfully speed up AI development — menhguin · 2026-09-30
- 9B Open-Weight Model Drops Agent Accuracy From 96% to 62.3% — TheZachMueller · 2026-09-30
- Jensen Huang: AI data centers add 10-20GW a year and roughly a million jobs — victor_explore · 2026-09-30
- First SGLang Summit set for Nov 12-13 in SF, with Intel CEO and Lilian Weng speaking — BanghuaZ · 2026-09-30
- Interview with Richard Ho, leader of OpenAI's in-house chip project — bookwormengr · 2026-09-30