超大规模个性化搜索的混合GPU-CPU检索系统
原标题：Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale
AI 摘要
该论文提出一种混合 GPU-CPU 协同服务系统，用于超大规模个性化搜索。系统通过 GPU 路径在约十亿文档的精选库存上融合检索与交互预排序，CPU 路径在约二十倍大的库存上进行轻量级个性化评分，两条路径可按请求独立运行并去重后共享下游排序。生产环境 A/B 测试显示，相比原有纯 CPU 配置，模型评分相关性和实质互动均有提升，验证了深度-广度分离架构的实用价值。
正文节选
Hybrid GPU–CPU Retrieval for Personalized Search at Ultra-Large Scale Abstract. Embedding-based retrieval on user-generated content at the trillion-document scale exposes a sharp conflict between two production demands: deep, expressive personalization for queries with rich user intent, and broad coverage of a massive inventory under fixed latency and resource budgets. We characterize this as the personalization–scale paradox: hosting the full serving inventory in GPU memory is too resource inte