@inproceedings{marzollo-etal-2026-sssd,
title = "{SSSD}: Simply-Scalable Speculative Decoding",
author = "Marzollo, Michele and
Zhuang, Jiawei and
Roemer, Niklas and
Zwingenberger, Niklas and
Muller, Lorenz K and
Cavigelli, Lukas",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-long.1530/",
doi = "10.18653/v1/2026.acl-long.1530",
pages = "33123--33139",
ISBN = "979-8-89176-390-6",
abstract = "Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial speedups typically rely on an additional trained draft model or auxiliary model components, increasing deployment and maintenance complexity. This added complexity reduces flexibility, particularly when serving workloads shift to tasks, domains, or languages that are not well represented in the draft model{'}s training data.We introduce Simply-Scalable Speculative Decoding (SSSD), a training-free method that combines lightweight n-gram matching with hardware-aware speculation. Relative to standard autoregressive decoding, SSSD reduces latency by up to 2.9{\texttimes}. It achieves performance on par with leading training-based approaches across a broad range of benchmarks, while requiring substantially lower adoption effort{---}no data preparation, training or tuning are needed{---}and exhibiting superior robustness under language and domain shift, as well as in long-context settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="marzollo-etal-2026-sssd">
<titleInfo>
<title>SSSD: Simply-Scalable Speculative Decoding</title>
</titleInfo>
<name type="personal">
<namePart type="given">Michele</namePart>
<namePart type="family">Marzollo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiawei</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niklas</namePart>
<namePart type="family">Roemer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niklas</namePart>
<namePart type="family">Zwingenberger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lorenz</namePart>
<namePart type="given">K</namePart>
<namePart type="family">Muller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lukas</namePart>
<namePart type="family">Cavigelli</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</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">979-8-89176-390-6</identifier>
</relatedItem>
<abstract>Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial speedups typically rely on an additional trained draft model or auxiliary model components, increasing deployment and maintenance complexity. This added complexity reduces flexibility, particularly when serving workloads shift to tasks, domains, or languages that are not well represented in the draft model’s training data.We introduce Simply-Scalable Speculative Decoding (SSSD), a training-free method that combines lightweight n-gram matching with hardware-aware speculation. Relative to standard autoregressive decoding, SSSD reduces latency by up to 2.9×. It achieves performance on par with leading training-based approaches across a broad range of benchmarks, while requiring substantially lower adoption effort—no data preparation, training or tuning are needed—and exhibiting superior robustness under language and domain shift, as well as in long-context settings.</abstract>
<identifier type="citekey">marzollo-etal-2026-sssd</identifier>
<identifier type="doi">10.18653/v1/2026.acl-long.1530</identifier>
<location>
<url>https://aclanthology.org/2026.acl-long.1530/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>33123</start>
<end>33139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SSSD: Simply-Scalable Speculative Decoding
%A Marzollo, Michele
%A Zhuang, Jiawei
%A Roemer, Niklas
%A Zwingenberger, Niklas
%A Muller, Lorenz K.
%A Cavigelli, Lukas
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-390-6
%F marzollo-etal-2026-sssd
%X Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial speedups typically rely on an additional trained draft model or auxiliary model components, increasing deployment and maintenance complexity. This added complexity reduces flexibility, particularly when serving workloads shift to tasks, domains, or languages that are not well represented in the draft model’s training data.We introduce Simply-Scalable Speculative Decoding (SSSD), a training-free method that combines lightweight n-gram matching with hardware-aware speculation. Relative to standard autoregressive decoding, SSSD reduces latency by up to 2.9×. It achieves performance on par with leading training-based approaches across a broad range of benchmarks, while requiring substantially lower adoption effort—no data preparation, training or tuning are needed—and exhibiting superior robustness under language and domain shift, as well as in long-context settings.
%R 10.18653/v1/2026.acl-long.1530
%U https://aclanthology.org/2026.acl-long.1530/
%U https://doi.org/10.18653/v1/2026.acl-long.1530
%P 33123-33139
Markdown (Informal)
[SSSD: Simply-Scalable Speculative Decoding](https://aclanthology.org/2026.acl-long.1530/) (Marzollo et al., ACL 2026)
ACL
- Michele Marzollo, Jiawei Zhuang, Niklas Roemer, Niklas Zwingenberger, Lorenz K Muller, and Lukas Cavigelli. 2026. SSSD: Simply-Scalable Speculative Decoding. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 33123–33139, San Diego, California, United States. Association for Computational Linguistics.