Hot Chips 2026: Cerebras lays out the future of wafer-scale AI — Nexus system architecture triples rack-scale performance, CS-6 wafer to incorporate stacked DRAM
TL;DR
At Hot Chips 2026, Cerebras revealed the next two generations of its wafer-scale accelerator roadmap. It also discussed the benefits of its new Nexus rack design for the CS-4 rack-scale accelerator and the performance of the three WS-3T wafer-scale engines contained within.
Nauti's Take
The opportunity sits in the memory question: stacking DRAM directly on the wafer could remove the exact bottleneck that inference workloads hit today. The risk is the gap between roadmap and shipping hardware, because CS-6 is an announcement rather than a product.
Relevant for anyone planning inference capacity outside Nvidia, while everyone else can treat this as a watch item for now.
Sources