Reproduce “Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Hao Fu, Jichao Sun, Baiting Zhu, Qiaoling Liu, Yan Shi, Cheng Lu, Liu Liu, Yubo Wang and 10 more
The authors present a hybrid personalized search system pairing GPU retrieval and interaction pre-ranking over a curated billion-scale pool with lightweight CPU retrieval over an inventory roughly twenty times larger. The paths feed shared downstream ranking. In a nine-day production test, the system improved DCG@20 by 4.51% and GSRR by 2.01% versus legacy all-CPU, but not component effects.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.