This paper introduces SLOs-Serve, a system designed for serving multi-stage large language model (LLM) requests with application- and stage-specific service level objectives (SLOs). The key idea behind SLOs-Serve is to customize the allocation of tokens to meet these SLO requirements. SLOs-Serve uses a multi-SLO dynamic programming-based algorithm to continuously optimize token allocations under SLO constraints by exploring the full design space of chunked prefill and (optional) speculative decoding. Leveraging this resource planning algorithm, SLOs-Serve effectively supports multi-SLOs and multi-replica serving with dynamic request routing while being resilient to bursty arrivals. Our evaluation across 6 LLM application scenarios (including summarization, coding, chatbot, tool calling, and reasoning) demonstrates that SLOs-Serve improves per-GPU serving capacity by 2.2x on average compared to prior state-of-the-art systems.
@article{arxiv.2504.08784,
title = {SLOs-Serve: Optimized Serving of Multi-SLO LLMs},
author = {Siyuan Chen and Zhipeng Jia and Samira Khan and Arvind Krishnamurthy and Phillip B. Gibbons},
journal= {arXiv preprint arXiv:2504.08784},
year = {2025}
}