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
- Sarvam AI Launches Token Factory: India-Hosted Inference for Open Models — itsOmSarraf_ · 2026-11-16
- US BIS Closes Remote-Access Loophole for Advanced AI Chips in New Rule — apples_jimmy · 2026-11-16
- Jailbroken PS4 runs a 9B open-source model at up to 43 tok/s by talking directly to its 2013-era GPU — AIFlow_ML · 2026-11-16
- Mobile AI Factory: agents auto-build on-device SLMs with 19x less GPU time — pmttyji · 2026-11-16
- Stratechery's Fictional Obituary: Imagining Jensen Huang's 2026 Exit From Nvidia — Gregory_C_Allen · 2026-11-16
- vLLM serves DeepSeek V4.1-Flash at 954K tokens/s per GPU, $38.96/GPU-hour on GB300 NVL72 — bookwormengr · 2026-11-16