SOURCE-LINKED INTELLIGENCE

Efficient Iterative Retrieval with Heterogeneous Batching

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

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. Coarse-grained partitioning, such as dedicating GPUs to specific tasks, fails to adapt to dynamic workloads and creates computational "bubbles". To address these, we present Orthrus, a serving system that performs heterogeneous batching within a unified inference loop. The primary challenge lies in unifying embedding and generation workloads with conf

Read original source ↗ Open in workspace

recordType

paper

region

Global