# Locality-aware Fair Scheduling in LLM Serving

arXiv: https://arxiv.org/abs/2501.14312 · HTML: https://mlsanity.com/paper/2501.14312/

## Key facts

- Cited by 15 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.
- First posted on arXiv 24 Jan 2025.

## Placed in

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

## Built on by (most cited first, 15 of 15)

- [ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production](https://mlsanity.com/paper/2505.09999/) (2025)
- [PrefillOnly: An Inference Engine for Prefill-only Workloads in Large Language Model Applications](https://mlsanity.com/paper/2505.07203/) (2025)
- [DualMap: Enabling Both Cache Affinity and Load Balancing for Distributed LLM Serving](https://mlsanity.com/paper/2602.06502/) (2026)
- [FairBatching: Fairness-Aware Batch Formation for LLM Inference](https://mlsanity.com/paper/2510.14392/) (2025)
- [Staggered Batch Scheduling: Co-optimizing Time-to-First-Token and Throughput for High-Efficiency LLM Inference](https://mlsanity.com/paper/2512.16134/) (2025)
- [CascadeInfer: Length-Aware Scheduling of LLM Serving with Low Latency and Load Balancing](https://mlsanity.com/paper/2512.19179/) (2025)
- [Efficient Remote KV Cache Reuse with GPU-native Video Codec](https://mlsanity.com/paper/2602.09725/) (2026)
- [Scheduling Mixed RL Rollouts Beyond Prefix Locality](https://mlsanity.com/paper/2608.11152/) (2026)
- [Alchemist: Towards the Design of Efficient Online Continual Learning System](https://mlsanity.com/paper/2503.01066/) (2025)
- [FMplex: Model Virtualization for Serving Extensible Foundation Models](https://mlsanity.com/paper/2606.09643/) (2026)
- [Recency/Frequency Adaptive KV Caching for Large Language Model Serving](https://mlsanity.com/paper/2606.21238/) (2026)
- [PEEK: Predictive Queue-Informed KV Cache Management for LLM Serving](https://mlsanity.com/paper/2607.02525/) (2026)
- [Token Latency Fairness: Performance Isolation for Multi-Tenant LLM Serving](https://mlsanity.com/paper/2609.18112/) (2026)
- [Ask the Tool, Don't Guess: Agent Tool Calls Hold Their Progress, and the Serving System Should Read It](https://mlsanity.com/paper/2609.18849/) (2026)
- [Inference Auctions](https://mlsanity.com/paper/2609.40070/) (2026)

## Abstract (arXiv)

Large language model (LLM) inference workload dominates a wide variety of modern AI applications, ranging from multi-turn conversation to document analysis. Balancing fairness and efficiency is critical for managing diverse client workloads with varying prefix patterns. Unfortunately, existing fair scheduling algorithms for LLM serving, such as Virtual Token Counter (VTC), fail to take prefix locality into consideration and thus suffer from poor performance. On the other hand, locality-aware scheduling algorithms in existing LLM serving frameworks tend to maximize the prefix cache hit rate without considering fair sharing among clients. This paper introduces the first locality-aware fair scheduling algorithm, Deficit Longest Prefix Match (DLPM), which can maintain a high degree of prefix locality with a fairness guarantee. We also introduce a novel algorithm, Double Deficit LPM (D2LPM), extending DLPM for the distributed setup that can find a balance point among fairness, locality, and load-balancing. Our extensive evaluation demonstrates the superior performance of DLPM and D2LPM in ensuring fairness while maintaining high throughput (up to 2.87× higher than VTC) and low per-client (up to 7.18× lower than state-of-the-art distributed LLM serving system) latency.