Cerebras Architecture

Wafer-sized chip, extrame-scale ML model, accelerate unstructured sparsity, distributed static random-access memory, interconnect

https://www.cerebras.net/blog/cerebras-cs-3-vs-nvidia-b200-2024-ai-accelerators-compared https://www.cerebras.net/blog/cerebras-cs3 https://www.cerebras.net/blog/cerebras-architecture-deep-dive-first-look-inside-the-hw/sw-co-design-for-deep-learning