# Queue management for slo-oriented large language model serving

arXiv: https://arxiv.org/abs/2407.00047 · HTML: https://mlsanity.com/paper/2407.00047/

## Key facts

- Cited by 36 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 21 of its 55 references that are in the map.
- First posted on arXiv 5 Jun 2024.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time](https://mlsanity.com/paper/2305.17118/) (2023)
- [Clipper: A Low-Latency Online Prediction Serving System](https://mlsanity.com/paper/1612.03079/) (2016)
- [Can Foundation Models Wrangle Your Data?](https://mlsanity.com/paper/2205.09911/) (2022)
- [S-LoRA: Serving Thousands of Concurrent LoRA Adapters](https://mlsanity.com/paper/2311.03285/) (2023)
- [Serving DNNs like Clockwork: Performance Predictability from the Bottom Up](https://mlsanity.com/paper/2006.02464/) (2020)
- [A Comprehensive Survey on Process-Oriented Automatic Text Summarization with Exploration of LLM-Based Methods](https://mlsanity.com/paper/2403.02901/) (2024)
- [Recent Advances in Recurrent Neural Networks](https://mlsanity.com/paper/1801.01078/) (2017)
- [SpotServe: Serving Generative Large Language Models on Preemptible Instances](https://mlsanity.com/paper/2311.15566/) (2023)
- [TensorFlow-Serving: Flexible, High-Performance ML Serving](https://mlsanity.com/paper/1712.06139/) (2017)
- [TurboTransformers: An Efficient GPU Serving System For Transformer Models](https://mlsanity.com/paper/2010.05680/) (2020)
- [Efficient Interactive LLM Serving with Proxy Model-based Sequence Length Prediction](https://mlsanity.com/paper/2404.08509/) (2024)
- [Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services](https://mlsanity.com/paper/2404.16283/) (2024)
- [FIRM: An Intelligent Fine-Grained Resource Management Framework for SLO-Oriented Microservices](https://mlsanity.com/paper/2008.08509/) (2020)
- [LAB: Large-Scale Alignment for ChatBots](https://mlsanity.com/paper/2403.01081/) (2024)
- [RelayAttention for Efficient Large Language Model Serving with Long System Prompts](https://mlsanity.com/paper/2402.14808/) (2024)
- [Perseus: Characterizing Performance and Cost of Multi-Tenant Serving for CNN Models](https://mlsanity.com/paper/1912.02322/) (2019)

## Built on by (most cited first, 30 of 36)

- [Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning](https://mlsanity.com/paper/2505.04021/) (2025)
- [Demystifying Cost-Efficiency in LLM Serving over Heterogeneous GPUs](https://mlsanity.com/paper/2502.00722/) (2025)
- [SLO-aware GPU Frequency Scaling for Energy Efficient LLM Inference Serving](https://mlsanity.com/paper/2408.05235/) (2024)
- [ModServe: Modality- and Stage-Aware Resource Disaggregation for Scalable Multimodal Model Serving](https://mlsanity.com/paper/2502.00937/) (2025)
- [AdaSpec: Adaptive Speculative Decoding for Fast, SLO-Aware Large Language Model Serving](https://mlsanity.com/paper/2503.05096/) (2025)
- [Throughput-Optimal Scheduling Algorithms for LLM Inference and AI Agents](https://mlsanity.com/paper/2504.07347/) (2025)
- [Taming the Titans: A Survey of Efficient LLM Inference Serving](https://mlsanity.com/paper/2504.19720/) (2025)
- [AIBrix: Towards Scalable, Cost-Effective Large Language Model Inference Infrastructure](https://mlsanity.com/paper/2504.03648/) (2025)
- [Nexus:Proactive Intra-GPU Disaggregation of Prefill and Decode in LLM Serving](https://mlsanity.com/paper/2507.06608/) (2025)
- [HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location](https://mlsanity.com/paper/2501.14808/) (2025)
- [Multi-Bin Batching for Increasing LLM Inference Throughput](https://mlsanity.com/paper/2412.04504/) (2024)
- [ElasticMM: Efficient Multimodal LLMs Serving with Elastic Multimodal Parallelism](https://mlsanity.com/paper/2507.10069/) (2025)
- [Scorpio: Serving Right Requests at the Right Time for Heterogeneous SLOs in LLM Inference](https://mlsanity.com/paper/2505.23022/) (2025)
- [OrbitFlow: SLO-Aware Long-Context LLM Serving with Fine-Grained KV Cache Reconfiguration](https://mlsanity.com/paper/2601.10729/) (2026)
- [FastSwitch: Optimizing Context Switching Efficiency in Fairness-aware Large Language Model Serving](https://mlsanity.com/paper/2411.18424/) (2024)
- [WarmServe: Enabling One-for-Many GPU Prewarming for Multi-LLM Serving](https://mlsanity.com/paper/2512.09472/) (2025)
- [FineServe: Precision-Aware KV Slab and Two-Level Scheduling for Heterogeneous Precision LLM Serving](https://mlsanity.com/paper/2509.06261/) (2025)
- [Towards Resiliency in Large Language Model Serving with KevlarFlow](https://mlsanity.com/paper/2601.22438/) (2026)
- [FlowPrefill: Decoupling Preemption from Prefill Scheduling Granularity to Mitigate Head-of-Line Blocking in LLM Serving](https://mlsanity.com/paper/2602.16603/) (2026)
- [AGFT: An Adaptive GPU Frequency Tuner for Real-Time LLM Inference Optimization](https://mlsanity.com/paper/2508.01744/) (2025)
- [Astrolabe: Balancing Load in LLM Serving with Randomized Prediction-Guided Scheduling](https://mlsanity.com/paper/2508.03611/) (2025)
- [RepetitionCurse: Measuring and Understanding Router Imbalance in Mixture-of-Experts LLMs under DoS Stress](https://mlsanity.com/paper/2512.23995/) (2025)
- [SuperInfer: SLO-Aware Rotary Scheduling and Memory Management for LLM Inference on Superchips](https://mlsanity.com/paper/2601.20309/) (2026)
- [TimelyLLM: Segmented LLM Serving System for Time-sensitive Robotic Applications](https://mlsanity.com/paper/2412.18695/) (2024)
- [Efficient Serving of LLM Applications with Probabilistic Demand Modeling](https://mlsanity.com/paper/2506.14851/) (2025)
- [PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models](https://mlsanity.com/paper/2602.11530/) (2026)
- [RouteBalance: Fused Model Routing and Load Balancing for Heterogeneous LLM Serving](https://mlsanity.com/paper/2606.17949/) (2026)
- [Mind the Delay: Latency-aware Query Routing for Heterogeneous LLM pools](https://mlsanity.com/paper/2607.18253/) (2026)
- [Crossflow: Prefill-Decode Elasticity for Agentic LLM Serving](https://mlsanity.com/paper/2609.27085/) (2026)
- [SAIR: Cost-Efficient Multi-Stage ML Pipeline Autoscaling via In-Context Reinforcement Learning](https://mlsanity.com/paper/2601.22397/) (2026)

## Abstract (arXiv)

Large language model (LLM) serving is becoming an increasingly critical workload for cloud providers. Existing LLM serving systems focus on interactive requests, such as chatbots and coding assistants, with tight latency SLO requirements. However, when such systems execute batch requests that have relaxed SLOs along with interactive requests, it leads to poor multiplexing and inefficient resource utilization. To address these challenges, we propose QLM, a queue management system for LLM serving. QLM maintains batch and interactive requests across different models and SLOs in a request queue. Optimal ordering of the request queue is critical to maintain SLOs while ensuring high resource utilization. To generate this optimal ordering, QLM uses a Request Waiting Time (RWT) Estimator that estimates the waiting times for requests in the request queue. These estimates are used by a global scheduler to orchestrate LLM Serving Operations (LSOs) such as request pulling, request eviction, load balancing, and model swapping. Evaluation on heterogeneous GPU devices and models with real-world LLM serving dataset shows that QLM improves SLO attainment by 40-90% and throughput by 20-400% while maintaining or improving device utilization compared to other state-of-the-art LLM serving systems. QLM's evaluation is based on the production requirements of a cloud provider. QLM is publicly available at https://www.github.com/QLM-project/QLM.