信息通信技术与政策2025，Vol.51Issue(10)：2-6,5.DOI:10.12267/j.issn.2096-5931.2025.10.001
大模型推理驱动下的算存协同发展研究
Research on the development of compute-storage collaboration driven by large model inference
周兰 1陈磊1
作者信息
- 1. 中国信息通信研究院信息化与工业化融合研究所,北京 100191
- 折叠
摘要
Abstract
With the continuous enhancement of large model capabilities and the deepening of inference applications,the scale of data processing has expanded drastically,and data processing requirements have become increasingly diversified,this has imposed higher demands on the collaborative between storage and computing power.In response to the new demands on storage systems by larger data volumes,larger model sizes,and longer context windows in current large model inference scenarios,this study first conducts an in-depth analysis of the implementation mechanisms,key technologies,and practical applications of both"computing-in-place-of-storage"and"storage-in-place-of-computing",Subsequently,by integrating the current technological and industrial foundation as well as application scenario requirements,this paper proposes that based on access latency and bandwidth demands,a hierarchical and systematic collaborative storage model for the future development of computing-storage synergy is important.This paper aims to explore the specific implementation mechanisms and evolutionary pathways of compute-storage collaboration,providing valuable references for promoting the improvement of intelligent computing cluster utilization efficiency and better supporting the development of large model inference.关键词
大模型推理/AI存储/键值缓存/算存协同Key words
large model inference/AI storage/KV Cache/computing-storage collaboration分类
计算机与自动化引用本文复制引用
周兰,陈磊..大模型推理驱动下的算存协同发展研究[J].信息通信技术与政策,2025,51(10):2-6,5.
