causal
GPU coherence caps cluster size per chip generation
A single pre-training cluster cannot exceed roughly 200,000 Hoppers that are coherent, meaning all GPUs share memory and act as one system, so progress requires waiting for the next chip generation to scale further.
causalpending
Speaker
GavinEvidence Quote
“after xAI figured out how to get 200,000 Hoppers coherent, you had to wait for the next generation of chips”
Created: 11/20/2026, 2:50:27 AM
Your notes
Loading notes...