Agentic coding is an unforgiving workload. Long contexts. High concurrency. @Cognition measured @NVIDIA Vera Rubin NVL72 against their own GB200 NVL72 baseline. Up to 4.8x the total token throughput for inference. 3.8x the output token throughput for RL. ▻ ↧ First Vera Rubin NVL72 Customer Sees 4.8x Throughput CoreWeave Now in limited availability on CoreWeave, NVIDIA Vera Rubin NVL72 boosts token throughput for Cognition's inference and reinforcement learning workloads.
published
Agentic coding is an unforgiving workload. Long contexts. High concurrency. @Cognition measured @NVIDIA Vera Rubin NVL72 against their own GB200 NVL72 baseline. Up to 4.8x the total token throughput for inference. 3.8x the output token throughput for RL. ▻
Open the original public source →
Latest documented BWB result
$MELI market result
Long $MELI CDS Expiring next Friday $1900/$1950 for $16 (which gives me $34 profit)
Historical results are not a promise of future performance. Trading involves substantial risk.This public post is a timestamped information archive, not personalized financial advice. Alerts can change as markets move. Join Billy's private group for the complete daily stream and follow-through.