English
Related papers

Related papers: Online Speculative Decoding

200 papers

Speculative decoding is commonly used for reducing the inference latency of large language models. Its effectiveness depends highly on the speculation lookahead (SL)-the number of tokens generated by the draft model at each iteration. In…

Computation and Language · Computer Science 2024-11-08 Jonathan Mamou , Oren Pereg , Daniel Korat , Moshe Berchansky , Nadav Timor , Moshe Wasserblat , Roy Schwartz

Speculative decoding (SD) has emerged as a widely used paradigm to accelerate LLM inference without compromising quality. It works by first employing a compact model to draft multiple tokens efficiently and then using the target LLM to…

Computation and Language · Computer Science 2025-03-07 Heming Xia , Yongqi Li , Jun Zhang , Cunxiao Du , Wenjie Li

Speculative Decoding has gained popularity as an effective technique for accelerating the auto-regressive inference process of Large Language Models. However, Speculative Decoding entirely relies on the availability of efficient draft…

Computation and Language · Computer Science 2025-06-06 Ofir Zafrir , Igor Margulis , Dorin Shteyman , Shira Guskin , Guy Boudoukh

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs…

Computation and Language · Computer Science 2025-12-29 Jikai Wang , Jianchao Tan , Yuxuan Hu , Jiayu Qin , Yerui Sun , Yuchen Xie , Xunliang Cai , Juntao Li , Min Zhang

Inference from large autoregressive models like Transformers is slow - decoding K tokens takes K serial runs of the model. In this work we introduce speculative decoding - an algorithm to sample from autoregressive models faster without any…

Machine Learning · Computer Science 2023-05-22 Yaniv Leviathan , Matan Kalman , Yossi Matias

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…

Systems and Control · Electrical Eng. & Systems 2026-01-30 Junhao He , Feiran You , Hongyang Du

Scaling test-time compute has driven the recent advances in the reasoning capabilities of large language models (LLMs), typically by allocating additional computation for more thorough exploration. However, increased compute often comes at…

Artificial Intelligence · Computer Science 2026-02-20 Mert Cemri , Nived Rajaraman , Rishabh Tiwari , Xiaoxuan Liu , Kurt Keutzer , Ion Stoica , Kannan Ramchandran , Ahmad Beirami , Ziteng Sun

Speculative decoding accelerates LLM inference by drafting future tokens with a small model, but drafter models degrade sharply under template perturbation and long-context inputs. We identify a previously-unreported phenomenon we call…

Machine Learning · Computer Science 2026-05-12 Doğaç Eldenk , Payal Mohapatra , Yigitcan Comlek , Kaan Oktay , Hongyang Zhang , Stephen Xia

Federated inference enhances LLM performance in edge computing through weighted averaging of distributed model predictions. However, autoregressive LLM inference requires frequent full-model forward passes across workers, severely limiting…

Signal Processing · Electrical Eng. & Systems 2026-04-29 Ce Zheng , Xinghan Wang , Jiahong Ning , Yuxuan Shi , Ning Huang , Tingting Yang

Speculative Decoding (SD) ensures that the output matches the target model's distribution exactly. However, we argue that this distribution matching requirement is too stringent and results in unnecessarily low acceptance rates, limiting…

In edge-cloud speculative decoding (SD), edge devices equipped with small language models (SLMs) generate draft tokens that are verified by large language models (LLMs) in the cloud. A key bottleneck in such systems is the limited…

Signal Processing · Electrical Eng. & Systems 2026-01-13 Guangyi Zhang , Yunlong Cai , Guanding Yu , Petar Popovski , Osvaldo Simeone

Large Language Models (LLMs) have achieved remarkable success across many applications, with Mixture of Experts (MoE) models demonstrating great potential. Compared to traditional dense models, MoEs achieve better performance with less…

Machine Learning · Computer Science 2026-02-17 Zongle Huang , Lei Zhu , Zongyuan Zhan , Ting Hu , Weikai Mao , Xianzhi Yu , Yongpan Liu , Tianyu Zhang

Speculative decoding aims to speed up autoregressive generation of a language model by verifying in parallel the tokens generated by a smaller draft model.In this work, we explore the effectiveness of learning-free, negligible-cost draft…

Machine Learning · Computer Science 2024-11-07 Lawrence Stewart , Matthew Trager , Sujan Kumar Gonugondla , Stefano Soatto

Speculative inference is a promising paradigm employing small speculative models (SSMs) as drafters to generate draft tokens, which are subsequently verified in parallel by the target large language model (LLM). This approach enhances the…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-05-16 Luyao Gao , Jianchun Liu , Hongli Xu , Xichong Zhang , Yunming Liao , Liusheng Huang

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-06 Xiangchen Li , Dimitrios Spatharakis , Saeid Ghafouri , Jiakun Fan , Hans Vandierendonck , Deepu John , Bo Ji , Dimitrios Nikolopoulos

Speculative decoding can substantially accelerate LLM inference, but realizing its benefits in practice is challenging due to evolving workloads and system-level constraints. We present TIDE (Temporal Incremental Draft Engine), a…

Machine Learning · Computer Science 2026-02-06 Jiyoung Park , Hankyu Jang , Changseok Song , Wookeun Jung

Speculative decoding is a widely adopted technique for accelerating inference in large language models (LLMs), yet its application to vision-language models (VLMs) remains underexplored, with existing methods achieving only modest speedups…

Computer Vision and Pattern Recognition · Computer Science 2025-10-24 Jialiang Kang , Han Shu , Wenshuo Li , Yingjie Zhai , Xinghao Chen

The immense model sizes of large language models (LLMs) challenge deployment on memory-limited consumer GPUs. Although model compression and parameter offloading are common strategies to address memory limitations, compression can degrade…

Computation and Language · Computer Science 2025-10-10 Pei-Shuo Wang , Jian-Jia Chen , Chun-Che Yang , Chi-Chih Chang , Ning-Chi Huang , Mohamed S. Abdelfattah , Kai-Chiang Wu

The acceleration of Large Language Models (LLMs) with speculative decoding provides a significant runtime improvement without any loss of accuracy. Currently, EAGLE-2 is the state-of-the-art speculative decoding method, improving on EAGLE…

Computation and Language · Computer Science 2024-09-04 Oscar Brown , Zhengjie Wang , Andrea Do , Nikhil Mathew , Cheng Yu

LLM serving platforms are increasingly deployed as multi-model cloud systems, where user demand is often long-tailed: a few popular large models receive most requests, while many smaller tail models remain underutilized. We propose…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-13 Jincheng Xie , Yawen Ling , Qi Xiao , Feiyu Zhang , Zhongyi Huang , Wen Hu , Yu Zheng