Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale

2026-09-17

AI Summary

本文提出一种混合GPU-CPU共服务系统，通过协调而非新模型来解决个性化与大规模库存覆盖之间的矛盾，提高超大规模个性化搜索的效果。

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 intensive, while CPU compute cannot execute the same interaction-heavy model on the latency-critical path. We present a hybrid GPU-CPU co-serving system that resolves the paradox through orchestration rather than a new model class. A high-depth GPU pathway fuses retrieval and interaction pre-ranking over a curated online pool on the order of a billion documents, while a high-breadth CPU pathway searches an independently selected online inventory roughly twenty times larger with lightweight personalized scoring. Either or both pathways can run per request; candidates are deduplicated before shared downstream ranking. The system is deployed in production. A full-system A/B test against the legacy CPU-only configuration improves model-scored relevance and substantive engagement, while separate pathway experiments show positive value at their own deployment scopes. Retrieval logs show that the pathways contribute structurally distinct candidates, production serving measurements characterize their latency, and a matched capacity plan quantifies the economic rationale for assigning modeling depth to GPUs and inventory breadth to CPUs. Together, these results validate a practical, independently evolvable depth-breadth architecture for ultra-large-scale personalized search.

Problem

• embedding-based retrieval
• personalization-scale paradox
• GPU-CPU co-serving system
• latency-critical path
• inventory breadth

Innovation

• Hybrid GPU-CPU
• personalized search
• ultra-large scale
• retrieval and interaction pre-ranking
• economic rationale