It sounds like this might mean they could do real prefix caching?
Cerebras would be much more interesting to me if cache hits resulted in a commensurate savings on my end.
Have they solved the issue yet where they need to keep running ghost tokens to keep the board hot to prevent it from cracking, which causes massive energy draw in idle, and reduces lifetime by 3 times the estimate?
https://culperresearch.com/wp-content/uploads/2026/10/Culper...
5x throughput more than b4, same 10x tokens/s as compared to standard.
looks like disagg/wide ep is applicable to cerebras chips as well. kind of amazing.
https://www.cerebras.ai/blog/how-we-deploy-trillion-paramete...