Cerebras is targeting a distinctly different point on the cost/latency curve. They are betting that there will be some high value applications where latency and not just throughput is super important.
It is being used as part of a combined system. For example AWS is pushing for Trainium + WSE 3. The WSE 3 does the decode and the Trainium does the prefill.
Even in nvidia land rubin + LPU does a similar thing.
It has its downsides of course - if your traffic swings prefill heavy to decode heavy, you can't suddenly use your lpu for prefill. With GPUs they're totally interchangeable. Tradeoffs.
There is also the other idea where you run your attention layer on the GPU/TPU/Trainium and the FFN on the SRAM accelerator. Because KV cache is more difficult on cerebras etc, while MOE latency is easier to deal with
