Efficient Iterative Retrieval with Heterogeneous Batching
arXiv:2609.25405v1 Announce Type: new Abstract: Modern information retrieval increasingly employs both embedding and generative models to handle complex queries. However, current serving systems suffer from low throughput and poor GPU utilization because they execute these models in isolation. Coar…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-09-23 04:00 · arXiv cs.AI
Efficient Iterative Retrieval with Heterogeneous Batching