AMD 投资者关系·· 2026-07-24
AMD and Cerebras Announce Industry-Leading Ultra-Low-Latency and High Throughput AI Inference Solution
AI 导读
AMD与Cerebras宣布建立技术合作,推出将AMD Helios机架级方案与Cerebras Wafer-Scale Engine结合的解耦式AI推理方案,二者作为单一推理工作流运行:AMD Helios负责高吞吐的提示处理与大上下文窗口,Cerebras Wafer-Scale Engine负责超低延迟的解码与token生成。
原文摘录
News Highlights AMD and Cerebras are collaborating to advance a workload-optimized approach to ultra-low-latency AI inference infrastructure. AMD Helios™ and the Cerebras Wafer-Scale Engine will oper…
报错 · 内容有误?请告诉我们。
来源:AMD 投资者关系 · ir.amd.com