信息通信技术与政策2026，Vol.52Issue(2)：18-23,6.DOI:10.12267/j.issn.2096-5931.2026.02.003
基于广域分布式推理网络的PD分离架构与实现
PD separation architecture and implementation based on wide-area distributed inference network
王飞飞 1邓桓 1唐静 1王巍 1苏越2
作者信息
- 1. 中国电信股份有限公司研究院,北京 102209
- 2. 中国信息通信研究院云计算与数字化研究所,北京 100191
- 折叠
摘要
Abstract
With the explosive growth in demand for large models inference,traditional centralized or static multi-data center deployment models face severe challenges in latency,data compliance,and resource elasticity.This paper proposes a cloud-edge collaborative wide-area distributed inference network architecture,focusing on building a new intelligent-computing service system for the emerging computing-power internet.The architecture introduces a prefill-decode separation mechanism:the latency-sensitive prefill stage is offloaded to edge nodes closer to data sources,while the high-throughput decode stage is deployed in the central cloud,enabling secure collaboration over a wide-area network.关键词
广域分布式推理/预填充和解码分离/大模型推理Key words
wide-area distributed inference/prefill-decode separation/large model inference分类
信息技术与安全科学引用本文复制引用
王飞飞,邓桓,唐静,王巍,苏越..基于广域分布式推理网络的PD分离架构与实现[J].信息通信技术与政策,2026,52(2):18-23,6.
