CoreWeave first to ship NVIDIA Vera Rubin NVL72, Cognition sees 4.8x throughput vs GB200
AccBalanced · x · 2026-10-01
CoreWeave announced availability of NVIDIA Vera Rubin NVL72 at its Fully Connected conference (4,500+ attendees), with Cognition as the first customer running production workloads on it.
- Cognition measured up to 4.8x total token throughput vs GB200 NVL72 on their SWE-2 inference workloads
- Customers use the same operating model and tooling as their GB200/GB300 NVL72 fleets, with CoreWeave performance engineering enabling production runs within days
- CoreWeave also earned SemiAnalysis' ClusterMAX Platinum rating for the third consecutive time
- Executives credit platform engineering across GPU generations, especially for agentic tasks, long contexts, and high concurrency
More from Infra
- 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
- Colossus 2's 1.2M B200s could generate ~$400B/year in tokens at DeepSeek Flash rates — bookwormengr · 2026-11-16
- BIS issues rule blocking remote access to US AI chips via third-country data centers — teortaxesTex · 2026-11-16