Cerebras launches disaggregated inference
Cerebras launches disaggregated inference
Cerebras says it has put disaggregated inference into production, with GPUs handling prefill and Cerebras systems handling decode, delivering five times more tokens per megawatt at the same Cerebras speeds in a measured deployment on its Inference Cloud. The company says it plans to deploy the approach across hundreds of megawatts by the end of 2027 and is offering partners a reference architecture plus an end-to-end software stack or a decode-only SDK. Early-access partners named include Amazon Web Services, Fireworks AI, Gimlet Labs and General Compute.
Documents Cerebras's production disaggregation results and partner integration options, useful for readers tracking inference capacity and power efficiency.
Source: Cerebras Blog · cerebras.ai