Skip to content
NeurIPS 2026 planner

Poster · Sydney

Replicas-as-Variables: A Planner for Throughput-Optimal Routing in LLM Deployment

When
Tue 8 Dec 2026, 10:00–13:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 1
Authors
Shaojiang Wang, Geer Yang, Wenbo Wang, Bin Wu, Pengcheng Wang
Organisations
Chinese Academy of Sciences, Institute of Computing Technology, Tsinghua University
QRS classification
Language models

Open in scheduleOfficial page