Laser: Unlocking Layer-Level Scheduling for Efficient Multi-SLO LLM Serving
Jianxiong Liao, Quanxing Dong, Yunkai Liang, Zhi Zhou, Xu Chen
2026Year
1Citations
Abstract
Engaging applications with diverse SLO requirements has become indispensable for production-scale LLM serving systems. However, existing systems rely on iteration-level scheduling, which enforces inflexible, unified execution across multi-SLO workloads, significantly constraining the serving efficiency.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Your agent calls
Lunesearch_papers
Free to start. No credit card required.
Terminal
Install the CLIlune papers get ea828430-0eba-482c-a2c5-dce301023801Related papers
- Libra: Flexible Request Partitioning and Scheduling for Serving Unbalanced and Dynamic LLM WorkloadsChaoyi Ruan, Yinhe Chen, Dongqi Tian, Yandong Shi et al.NSDI 2026 · 5 citations
- JITServe: SLO-aware LLM Serving with Imprecise Request InformationWei Zhang, Zhiyu Wu, Yi Mu, Rui Ning et al.NSDI 2026 · 29 citations
- AdaServe: Accelerating Multi-SLO LLM Serving with SLO-Customized Speculative DecodingZikun Li, Zhuofu Chen, Remi Delacourt, Gabriele Oliaro et al.EuroSys 2026
- Janus: Multi-LLM Serving at Production ScaleTianbao Zhou, Yi Wang, Yu Zhou, Zirui Liu et al.SOSP 2026
- DuetServe: Harmonizing Prefill and Decode for LLM Serving via Adaptive GPU MultiplexingLei Gao, Chaoyi Jiang, Hossein Entezari Zarch, Daniel Wong et al.ICML 2026 · 4 citations
