@inproceedings{liu-etal-2026-quartz,
title = "{QUARTZ}: Quantile-Aware Routing and Queueing for {TTFT} {SLO}s in {LLM} Serving",
author = "Liu, Zhipeng and
Zheng, Yifan and
Kong, Fanqi and
Zhao, Ziming",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1888/",
pages = "37886--37896",
ISBN = "979-8-89176-395-1",
abstract = "Large Language Model (LLM) serving systems increasingly face strict time-to-first-token (TTFT) service-level objectives (SLOs), yet TTFT remains highly sensitive to router-side queueing effects. Prefill costs scale with prompt length, decode lengths are uncertain, and prefix locality creates strong performance skew across requests. Despite major advances in continuous batching and KV-cache management, today{'}s routers are often agnostic to request cost, which makes them vulnerable to head-of-line blocking and tail-latency amplification under mixed workloads. We propose \textit{QUARTZ}, a quantile-aware routing and queueing layer for LLM serving that predicts conservative quantile-based request-cost proxies, rather than point estimates, using lightweight router-visible signals. QUARTZ uses these quantiles together with backlog-aware router signals to guide worker selection and admission decisions that better align with TTFT tail SLOs while preserving fairness. We implement QUARTZ as a router upgrade for SGLang and evaluate it on representative interactive and retrieval-augmented workloads. The results show reductions in TTFT tail latency and SLO violations across heterogeneous workloads."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-quartz">
<titleInfo>
<title>QUARTZ: Quantile-Aware Routing and Queueing for TTFT SLOs in LLM Serving</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fanqi</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ziming</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Large Language Model (LLM) serving systems increasingly face strict time-to-first-token (TTFT) service-level objectives (SLOs), yet TTFT remains highly sensitive to router-side queueing effects. Prefill costs scale with prompt length, decode lengths are uncertain, and prefix locality creates strong performance skew across requests. Despite major advances in continuous batching and KV-cache management, today’s routers are often agnostic to request cost, which makes them vulnerable to head-of-line blocking and tail-latency amplification under mixed workloads. We propose QUARTZ, a quantile-aware routing and queueing layer for LLM serving that predicts conservative quantile-based request-cost proxies, rather than point estimates, using lightweight router-visible signals. QUARTZ uses these quantiles together with backlog-aware router signals to guide worker selection and admission decisions that better align with TTFT tail SLOs while preserving fairness. We implement QUARTZ as a router upgrade for SGLang and evaluate it on representative interactive and retrieval-augmented workloads. The results show reductions in TTFT tail latency and SLO violations across heterogeneous workloads.</abstract>
<identifier type="citekey">liu-etal-2026-quartz</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1888/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>37886</start>
<end>37896</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T QUARTZ: Quantile-Aware Routing and Queueing for TTFT SLOs in LLM Serving
%A Liu, Zhipeng
%A Zheng, Yifan
%A Kong, Fanqi
%A Zhao, Ziming
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F liu-etal-2026-quartz
%X Large Language Model (LLM) serving systems increasingly face strict time-to-first-token (TTFT) service-level objectives (SLOs), yet TTFT remains highly sensitive to router-side queueing effects. Prefill costs scale with prompt length, decode lengths are uncertain, and prefix locality creates strong performance skew across requests. Despite major advances in continuous batching and KV-cache management, today’s routers are often agnostic to request cost, which makes them vulnerable to head-of-line blocking and tail-latency amplification under mixed workloads. We propose QUARTZ, a quantile-aware routing and queueing layer for LLM serving that predicts conservative quantile-based request-cost proxies, rather than point estimates, using lightweight router-visible signals. QUARTZ uses these quantiles together with backlog-aware router signals to guide worker selection and admission decisions that better align with TTFT tail SLOs while preserving fairness. We implement QUARTZ as a router upgrade for SGLang and evaluate it on representative interactive and retrieval-augmented workloads. The results show reductions in TTFT tail latency and SLO violations across heterogeneous workloads.
%U https://aclanthology.org/2026.findings-acl.1888/
%P 37886-37896
Markdown (Informal)
[QUARTZ: Quantile-Aware Routing and Queueing for TTFT SLOs in LLM Serving](https://aclanthology.org/2026.findings-acl.1888/) (Liu et al., Findings 2026)
ACL