Metraipolis › archive › dc_3f07cc35429b

Efficient Iterative Retrieval with Heterogeneous Batching — arXiv:2609.25405

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.25405
License (as archived)
CC0-1.0
Archived
2026-10-08T13:44:57.819Z
SHA-256 of the archived text
0e7c11baf1ba1c09a44c3812340037031938b059da037981ec03804359ad2bca
Stable URL of this page
https://metraipolis.com/documento/dc_3f07cc35429b

How to cite

Efficient Iterative Retrieval with Heterogeneous Batching — arXiv:2609.25405 — arXiv (en), https://arxiv.org/abs/2609.25405 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3f07cc35429b (Metraipolis archive dc_3f07cc35429b, sha256 0e7c11baf1ba1c09a44c3812340037031938b059da037981ec03804359ad2bca)
BibTeX
@misc{dc3f07cc35429b,
  title = {Efficient Iterative Retrieval with Heterogeneous Batching — arXiv:2609.25405},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.25405},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3f07cc35429b; sha256 0e7c11baf1ba1c09a44c3812340037031938b059da037981ec03804359ad2bca},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25405. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 conflicting computational patterns while optimizing batch composition for high performance. Orthrus addresses these challenges through chunked embedding with incremental pooling and by adjusting batch composition in a workload-aware manner. Evaluation on four A100 GPUs shows that, relative to baseline deployments, Orthrus achieves 1.28$\times$--4.52$\times$ higher throughput on controlled workloads and up to 55.8% lower end-to-end p99 latency on an iterative-RAG benchmark. We release our code at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.25405 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T13:18:38.079Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).