English
Related papers

Related papers: PaSS: Parallel Speculative Sampling

200 papers

Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The issue is exacerbated in Large Reasoning Models (LRMs), which generate lengthy chains of…

Computation and Language · Computer Science 2026-02-05 Ximing Dong , Shaowei Wang , Dayi Lin , Boyuan Chen , Ahmed E. Hassan

Speculative decoding is an inference-acceleration method for large language models (LLMs) where a small language model generates a draft-token sequence which is further verified by the target LLM in parallel. Recent works have advanced this…

Machine Learning · Computer Science 2024-03-06 Wonseok Jeon , Mukul Gagrani , Raghavv Goel , Junyoung Park , Mingu Lee , Christopher Lott

Speculative decoding (SPD) accelerates large language model (LLM) inference by letting a smaller draft model propose multiple future tokens that are verified in parallel by a larger target model. The dominant SPD paradigm treats the target…

Computation and Language · Computer Science 2026-05-26 Jinze Li , Yixing Xu , Guanchen Li , Jinfeng Xu , Shuo Yang , Yang Zhang , Xuanwu Yin , Dong Li , Edith C. H. Ngai , Emad Barsoum

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

Temporal point processes are powerful generative models for event sequences that capture complex dependencies in time-series data. They are commonly specified using autoregressive models that learn the distribution of the next event from…

Machine Learning · Computer Science 2025-10-24 Marin Biloš , Anderson Schneider , Yuriy Nevmyvaka

Reasoning models excel by generating long chain-of-thoughts, but decoding the resulting thousands of tokens is slow. Token-level speculative decoding (SD) helps, but its benefit is capped, because the chance that an entire $\gamma$-token…

Machine Learning · Computer Science 2025-06-25 Yichao Fu , Rui Ge , Zelei Shao , Zhijie Deng , Hao Zhang

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model…

Computation and Language · Computer Science 2025-03-06 Guofeng Quan , Wenfeng Feng , Chuzhan Hao , Guochao Jiang , Yuewei Zhang , Hao Wang

Despite the remarkable strides made by autoregressive language models, their potential is often hampered by the slow inference speeds inherent in sequential token generation. Blockwise parallel decoding (BPD) was proposed by Stern et al. as…

Computation and Language · Computer Science 2024-06-06 Taehyeon Kim , Ananda Theertha Suresh , Kishore Papineni , Michael Riley , Sanjiv Kumar , Adrian Benton

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

We present parallel algorithms to accelerate sampling via counting in two settings: any-order autoregressive models and denoising diffusion models. An any-order autoregressive model accesses a target distribution $\mu$ on $[q]^n$ through an…

Data Structures and Algorithms · Computer Science 2025-11-12 Nima Anari , Carlo Baronio , CJ Chen , Alireza Haqi , Frederic Koehler , Anqi Li , Thuy-Duong Vuong

We propose TPP-SD, a novel approach that accelerates Transformer temporal point process (TPP) sampling by adapting speculative decoding (SD) techniques from language models. By identifying the structural similarities between thinning…

Machine Learning · Computer Science 2025-10-22 Shukai Gong , Yiyang Fu , Fengyuan Ran , Quyu Kong , Feng Zhou

Large language models (LLMs) have achieved remarkable performance across a wide range of tasks, but their increasing parameter sizes significantly slow down inference. Speculative decoding mitigates this issue by leveraging a smaller draft…

Computation and Language · Computer Science 2026-05-27 Kuan-Wei Lu , Ding-Yong Hong , Pangfeng Liu , Jan-Jan Wu

Existing speculative decoding methods typically require additional model structure and training processes to assist the model for draft token generation. This makes the migration of acceleration methods to the new model more costly and more…

Computation and Language · Computer Science 2024-10-08 Yixuan Wang , Xianzhen Luo , Fuxuan Wei , Yijun Liu , Qingfu Zhu , Xuanyu Zhang , Qing Yang , Dongliang Xu , Wanxiang Che

Parallel test-time scaling (TTS) is a pivotal approach for enhancing large language models (LLMs), typically by sampling multiple token-based chains-of-thought in parallel and aggregating outcomes through voting or search. Recent advances…

Computation and Language · Computer Science 2026-04-21 Runyang You , Yongqi Li , Meng Liu , Wenjie Wang , Liqiang Nie , Wenjie Li

Diffusion large language models (dLLMs) have recently drawn considerable attention within the research community as a promising alternative to autoregressive generation, offering parallel token prediction and lower inference latency. Yet,…

Computation and Language · Computer Science 2025-10-01 Zigeng Chen , Gongfan Fang , Xinyin Ma , Ruonan Yu , Xinchao Wang

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

As text generation has become a core capability of modern Large Language Models (LLMs), it underpins a wide range of downstream applications. However, most existing LLMs rely on autoregressive (AR) generation, producing one token at a time…

Computation and Language · Computer Science 2026-02-11 Lingzhe Zhang , Liancheng Fang , Chiming Duan , Minghua He , Leyi Pan , Pei Xiao , Shiyu Huang , Yunpeng Zhai , Xuming Hu , Philip S. Yu , Aiwei Liu

Decoding methods for large language models often trade-off between diversity of outputs and parallelism of computation. Methods such as beam search and Gumbel top-k sampling can guarantee a different output for each element of the beam, but…

Computation and Language · Computer Science 2023-06-02 Luke Vilnis , Yury Zemlyanskiy , Patrick Murray , Alexandre Passos , Sumit Sanghai

Test-time scaling has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs) by allocating additional computational resources during inference. However, this paradigm is inherently…

Computation and Language · Computer Science 2025-09-08 Shengyin Sun , Yiming Li , Xing Li , Yingzhao Lian , Weizhe Lin , Hui-Ling Zhen , Zhiyuan Yang , Chen Chen , Xianzhi Yu , Mingxuan Yuan , Chen Ma

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