paper-with-me

Papers

Learning-Augmented Online Scheduling with Parsimonious Preemption

2026-05-22 · Mugen Blue, Sungjin Im, Alexander Lindermayr arxiv

Learning-augmented algorithms have emerged as a powerful paradigm to surpass traditional worst-case lower bounds by integrating potentially noisy predictions. While this framework has seen success in online scheduling, existing work primarily optimizes job latency while relying on frequent, ``blind'' preemptions. This ignores the fundamental trade-off between algorithmic performance and preemption complexity. We provide the first systematic study of learning-augmented scheduling that curbs preemption while optimizing latency. We establish that the gap between theoretical latency bounds and preemption overhead can be bridged with solid analytical foundations. Our results include $O(1)$-competitive algorithms for single and unrelated parallel machines with only $O(1)$ preemptions per job under accurate predictions, with overhead scaling logarithmically with the prediction error. By providing the first bounded-preemption guarantees for unrelated and malleable machines, we extend the theoretical reach of the learning-augmented framework to more constrained and realistic settings. Finally, our algorithms are validated through experiments.

📄 PDF Abstract BibTeX arXiv:2605.23255

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Don't Stop Me Now: Embedding Based Scheduling for LLMs

2024-10-01 · Rana Shahout, Eran Malach, Chunwei Liu, Weifan Jiang 외

Efficient scheduling is crucial for interactive Large Language Model (LLM) applications, where low request completion time directly impacts user engagement. Size-based scheduling algorithms like Shortest Remaining Proces…

BlockingLarge Language ModelScheduling

FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving

2026-02-18 · Chia-chi Hsieh, Zan Zong, Xinyang Chen, Jianjiang Li 외 arxiv

The growing demand for large language models (LLMs) requires serving systems to handle many concurrent requests with diverse service level objectives (SLOs). This exacerbates head-of-line (HoL) blocking during the comput…

Computational Efficiency

Topology-aware Preemptive Scheduling for Co-located LLM Workloads

2024-11-18 · Ping Zhang, Lei Su, Jinjie Yang, Xin Chen

Hosting diverse large language model workloads in a unified resource pool through co-location is cost-effective. For example, long-running chat services generally follow diurnal traffic patterns, which inspire co-locatio…

Language ModelingLanguage ModellingLarge Language ModelScheduling

Parsimonious Learning-Augmented Online Metric Matching

2026-05-26 · Yongho Shin, Phanu Vajanopath arxiv

Learning-augmented algorithms have received significant attention in recent years, particularly in the context of online optimization. Motivated by the high computational cost of generating predictions, a growing line of…

Towards Multi-Model LLM Schedulers: Empirical Insights into Offloading and Preemption

2026-05-19 · Mert Yildiz, Pietro Spadaccino, Alexey Rolich, Francesca Cuomo 외 arxiv

Modern deployments of Large Language Models (LLMs) increasingly require serving multiple models with diverse architectures, sizes, and specialization on shared, heterogeneous hardware. This setting introduces new challen…