Cerebras launches disaggregated inference with AMD, delivering 5x more tokens per megawatt

AccBalanced · x · 2026-11-22

Cerebras announced disaggregated inference with AMD, billed as the first production-scale deployment combining GPU and non-GPU systems: AMD Instinct GPUs handle prefill while Cerebras CS-3 systems handle decode. Production data shows 5x more tokens per megawatt than CS-3 alone, at Cerebras speeds.

Original post →

More from Infra

Infra channel →