English
Related papers

Related papers: Multi-Draft Speculative Sampling: Canonical Decomp…

200 papers

Inference latency stands as a critical bottleneck in the large-scale deployment of Large Language Models (LLMs). Speculative decoding methods have recently shown promise in accelerating inference without compromising the output…

Machine Learning · Computer Science 2025-10-31 Ruilin Wang , Huixia Li , Yuexiao Ma , Xiawu Zheng , Fei Chao , Xuefeng Xiao , Rongrong Ji

Statistical signal processing applications usually require the estimation of some parameters of interest given a set of observed data. These estimates are typically obtained either by solving a multi-variate optimization problem, as in the…

Computation · Statistics 2021-07-27 D. Luengo , L. Martino , M. Bugallo , V. Elvira , S. Särkkä

We propose Composition Sampling, a simple but effective method to generate diverse outputs for conditional generation of higher quality compared to previous stochastic decoding strategies. It builds on recently proposed plan-based neural…

Computation and Language · Computer Science 2022-03-30 Shashi Narayan , Gonçalo Simões , Yao Zhao , Joshua Maynez , Dipanjan Das , Michael Collins , Mirella Lapata

We aim to efficiently allocate a fixed simulation budget to identify the top-mc designs for each context among a finite number of contexts. The performance of each design under a context is measured by an identifiable statistical…

Methodology · Statistics 2023-07-03 Xinbo Shi , Yijie Peng , Gongbo Zhang

Speculative decoding is an emerging technique that accelerates large language model (LLM) inference by allowing a smaller draft model to predict multiple tokens in advance, which are then verified or corrected by a larger target model. In…

Signal Processing · Electrical Eng. & Systems 2025-11-10 Ce Zheng , Tingting Yang

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

We propose a randomized method for solving linear programs with a large number of columns but a relatively small number of constraints. Since enumerating all the columns is usually unrealistic, such linear programs are commonly solved by…

Optimization and Control · Mathematics 2023-11-29 Yi-Chun Akchen , Velibor V. Mišić

Large language models (LLMs) exhibit exceptional performance across a wide range of tasks; however, their token-by-token autoregressive generation process significantly hinders inference speed. Speculative decoding presents a promising…

Computation and Language · Computer Science 2025-03-04 Kai Lv , Honglin Guo , Qipeng Guo , Xipeng Qiu

Top-$k$ decoding is a widely used method for sampling from LLMs: at each token, only the largest $k$ next-token-probabilities are kept, and the next token is sampled after re-normalizing them to sum to unity. Top-$k$ and other sampling…

Artificial Intelligence · Computer Science 2026-02-24 Georgy Noarov , Soham Mallick , Tao Wang , Sunay Joshi , Yan Sun , Yangxinyu Xie , Mengxin Yu , Edgar Dobriban

Recent advances in Markov chain Monte Carlo (MCMC) extend the scope of Bayesian inference to models for which the likelihood function is intractable. Although these developments allow us to estimate model parameters, other basic problems…

Computation · Statistics 2019-12-12 Minh-Ngoc Tran , Marcel Scharth , David Gunawan , Robert Kohn , Scott D. Brown , Guy E. Hawkins

Duplicate removal is a critical step to accomplish a reasonable amount of predictions in prevalent proposal-based object detection frameworks. Albeit simple and effective, most previous algorithms utilize a greedy process without making…

Computer Vision and Pattern Recognition · Computer Science 2018-10-23 Lu Qi , Shu Liu , Jianping Shi , Jiaya Jia

Large language models (LLMs) suffer from high inference latency due to the auto-regressive decoding process. Speculative decoding accelerates inference by generating multiple draft tokens using a lightweight model and verifying them in…

Machine Learning · Computer Science 2025-05-27 Yixuan Wang , Yijun Liu , Shiyu ji , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

Speculative decoding (SD) accelerates large language model (LLM) inference by using a smaller model to draft future tokens, which are then verified by the target LLM. This preserves generation quality by accepting only aligned tokens.…

Computation and Language · Computer Science 2026-04-08 Taehyeon Kim , Hojung Jung , Se-Young Yun

Speculative sampling (SpS) has been successful in accelerating the decoding throughput of auto-regressive large language models by leveraging smaller draft models. SpS strictly enforces the generated distribution to match that of the…

Machine Learning · Computer Science 2026-04-08 Yongchang Hao , Lili Mou

As large language models (LLMs) scale up, accuracy improves, but the autoregressive (AR) nature of decoding increases latency since each token requires a serial forward pass. Speculative decoding addresses this by employing a fast drafter…

Computation and Language · Computer Science 2025-10-06 Guanghao Li , Zhihui Fu , Min Fang , Qibin Zhao , Ming Tang , Chun Yuan , Jun Wang

Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficiency, multi-sample speculative decoding has been overlooked…

Computation and Language · Computer Science 2024-10-15 Yunsheng Ni , Chuanjian Liu , Yehui Tang , Kai Han , Yunhe Wang

Despite their growing capabilities, language models still frequently reproduce content from their training data, generate repetitive text, and favor common grammatical patterns and vocabulary. A possible cause is the decoding strategy: the…

Computation and Language · Computer Science 2026-01-15 Giorgio Franceschelli , Mirco Musolesi

Bayesian inference for doubly-intractable pairwise exponential graphical models typically involves variations of the exchange algorithm or approximate Markov chain Monte Carlo (MCMC) samplers. However, existing methods for both classes of…

Computation · Statistics 2026-03-30 Yujie Chen , Antik Chakraborty , Anindya Bhadra

Speculative decoding has rapidly emerged as a leading approach for accelerating language model (LM) inference, as it offers substantial speedups while yielding identical outputs. This relies upon a small draft model, tasked with predicting…

Computation and Language · Computer Science 2026-02-17 Miles Williams , Young D. Kwon , Rui Li , Alexandros Kouris , Stylianos I. Venieris

Speculative decoding (SD), where a draft model provides multiple candidate tokens for the target model to verify in parallel, has demonstrated significant potential for accelerating LLM inference. Yet, existing SD approaches adhere to a…

Machine Learning · Computer Science 2025-09-22 Enyu Zhou , Kai Sheng , Hao Chen , Xin He