Saved in:
Bibliographic Details
Main Authors: He, Junhao, You, Feiran, Du, Hongyang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2601.21622
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912859064107008
author He, Junhao
You, Feiran
Du, Hongyang
author_facet He, Junhao
You, Feiran
Du, Hongyang
contents Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and do not scale well to multi-accelerator clusters used for serving modern Large Language Models (LLMs). We present StarSD, a one-for-many speculative decoding framework that uses a single draft model to serve multiple target models across distributed nodes via a star topology. StarSD decouples drafting and verification, enabling effective sharing of draft computation, and preventing distributed accelerators from remaining idle under bursty workloads. We provide a system-level analysis that characterizes when and why a single draft model can remain fully utilized by multiple verifiers, yielding predictable latency and utilization gains. Extensive experiments in real-world distributed inference settings demonstrate that StarSD simplifies deployment and supports flexible resource allocation across heterogeneous accelerators, while maintaining output quality. These results indicate that StarSD is a practical and scalable framework for bringing speculative decoding to modern cloud and edge inference infrastructures.
format Preprint
id arxiv_https___arxiv_org_abs_2601_21622
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle StarSD: One-for-Many Speculative Decoding
He, Junhao
You, Feiran
Du, Hongyang
Systems and Control
Speculative decoding accelerates autoregressive generation by separating token proposal from verification, but most existing approaches are designed for single-node execution and do not scale well to multi-accelerator clusters used for serving modern Large Language Models (LLMs). We present StarSD, a one-for-many speculative decoding framework that uses a single draft model to serve multiple target models across distributed nodes via a star topology. StarSD decouples drafting and verification, enabling effective sharing of draft computation, and preventing distributed accelerators from remaining idle under bursty workloads. We provide a system-level analysis that characterizes when and why a single draft model can remain fully utilized by multiple verifiers, yielding predictable latency and utilization gains. Extensive experiments in real-world distributed inference settings demonstrate that StarSD simplifies deployment and supports flexible resource allocation across heterogeneous accelerators, while maintaining output quality. These results indicate that StarSD is a practical and scalable framework for bringing speculative decoding to modern cloud and edge inference infrastructures.
title StarSD: One-for-Many Speculative Decoding
topic Systems and Control
url https://arxiv.org/abs/2601.21622