AMD partners with big chip co. Cerebras for ultra-low-latency and high throughput AI inference system

AMD partners with big chip co. Cerebras for ultra-low-latency and high throughput AI inference system

AMD and Cerebras combine Helios (high-throughput prompts) with Wafer-Scale Engine (low-latency token gen) in disaggregated inference, Q2 2026. The dual-engine architecture gives IT managers a Nvidia alternative for latency-critical workloads.