Hacker News AIT2·Infra
78 pts
Cerebras has moved disaggregated inference into production, assigning prompt prefill to GPUs and output decode to its wafer-scale engines, yielding five times more tokens per megawatt at the same ultrafast speeds. The setup now runs on Cerebras Inference Cloud and is available to infrastructure partners for their own datacenters, alongside CS-4 and a planned 700MW of capacity.