Pith. sign in

REVIEW 6 cited by

Locality-aware Fair Scheduling in LLM Serving

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.14312 v1 pith:4OWXBMWV submitted 2025-01-24 cs.DC cs.LG

classification cs.DCcs.LG
keywords prefixfairfairnessschedulingservingdlpmlocalitylocality-aware
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

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 (D$^2$LPM), 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 D$^2$LPM in ensuring fairness while maintaining high throughput (up to 2.87$\times$ higher than VTC) and low per-client (up to 7.18$\times$ lower than state-of-the-art distributed LLM serving system) latency.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Efficient Remote KV Cache Reuse with GPU-native Video Codec

    cs.DC 2026-02 conditional novelty 7.0 of 10

    KVCodec uses GPU-native video codecs and pipelined fetching to compress and transmit KV caches, delivering up to 3.51x faster TTFT than prior methods while preserving accuracy.

  2. FMplex: Model Virtualization for Serving Extensible Foundation Models

    cs.DC 2026-06 unverdicted novelty 6.0 of 10

    FMplex is a serving system that virtualizes FM backbones for sharing across tasks, claiming up to 80% lower latency and 6x more tasks hosted versus prior approaches.

  3. CascadeInfer: Length-Aware Scheduling of LLM Serving with Low Latency and Load Balancing

    cs.DC 2025-12 conditional novelty 6.0 of 10

    CascadeInfer partitions LLM instances into length-specialized groups, uses dynamic programming for stage partitioning, and applies runtime refinement plus decentralized load balancing to cut latency and raise throughput.

  4. MQFQ-Sticky: Fair Queueing For Serverless GPU Functions

    cs.DC 2025-07 conditional novelty 6.0 of 10

    MQFQ-Sticky applies multi-queue fair queuing and anticipatory scheduling to GPU serverless functions, reporting 2x-20x latency reductions and fairer GPU service than FCFS, batching, or SJF policies.

  5. Recency/Frequency Adaptive KV Caching for Large Language Model Serving

    cs.DC 2026-06 unverdicted novelty 5.0 of 10

    Presents a recency/frequency adaptive KV caching approach that achieves up to 10.8% higher hit rate and 12.6% lower TTFT compared to vLLM on synthetic workloads.

  6. ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production

    cs.DC 2025-05 unverdicted novelty 5.0 of 10

    ServeGen characterizes production LLM inference workloads across model types and generates realistic per-client composed workloads that reduce under-provisioning by 50% in a production validation.

Pith tools