CoreWeave announces NVIDIA Vera Rubin cloud availability
CoreWeave announces NVIDIA Vera Rubin cloud availability.
NVIDIA Blog reports: In its early tests, Cognition saw Vera Rubin NVL72 deliver up to a 4.8x increase in total token throughput for SWE-2 inference workloads over GB200 NVL72.
Cognition runs training, reinforcement learning and production inference for Devin on CoreWeave.
- Key number
- In its early tests, Cognition saw Vera Rubin NVL72 deliver up to a 4.8x increase in total token throughput for SWE-2 inference workloads over GB200 NVL72
- Downside / limitation
- The reported early benchmark is attributed to Cognition; it is not an independently reproduced market-wide performance result
