HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location

Ting Sun, Penghan Wang, Fan Lai

Keywords: LLM Inference, Request Scheduling, Machine Learning Systems

TL;DR: Colocating online and offline LLM inference requests in the same inference engine.

Abstract: Large language models (LLMs) have facilitated a wide range of applications with distinct service-level objectives (SLOs), from latency-sensitive online tasks like interactive chatbots to throughput-oriented offline workloads like data synthesis. The existing deployment model, which dedicates machines to each workload, simplifies SLO management but often leads to poor resource utilization. This paper introduces HyGen, an interference-aware LLM serving system that enables efficient co-location of online and offline workloads while preserving SLOs. HyGen incorporates two key innovations: (1) performance control mechanisms, including a latency predictor to estimate batch execution time and an SLO-aware profiler to quantify latency interference, and (2) SLO-aware offline scheduling policies that maximize serving throughput and prevent starvation. Our evaluation on production workloads shows that HyGen achieves up to 3.9-5.8× throughput gains over online and hybrid serving baselines, while ensuring latency SLOs. The code of HyGen is publicly available at https://github.com/UIUC-MLSys/HyGen.

Primary Area: Infrastructure (e.g., libraries, improved implementation and scalability, distributed solutions)

Submission Number: 15013