Hybrid GPU-CPU Retrieval for Personalized Search at Ultra-Large Scale
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...
Hao-Hao Fu, Ji-Chao Sun, Bai-Ting Zhu et al.
· 0 citations