English
Related papers

Related papers: Speculative Decoding via Early-exiting for Faster …

200 papers

Speculative decoding accelerates Large Language Model (LLM) inference by using a small draft model to predict multiple tokens, and a large target model to verify these tokens in parallel. Recent studies leverage the hidden state of the…

Computation and Language · Computer Science 2025-06-05 Langlin Huang , Chengsong Huang , Jixuan Leng , Di Huang , Jiaxin Huang

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

Diffusion large language models (dLLMs) are emerging as a promising alternative to autoregressive models (ARMs) due to their ability to capture bidirectional context and the potential for parallel generation. Despite the advantages, dLLM…

Machine Learning · Computer Science 2026-03-12 Zijian Zhu , Fei Ren , Zhanhong Tan , Kaisheng Ma

Speculative decoding is a widely used technique for accelerating inference in large language models (LLMs), but its performance degrades as input length grows, with significant drops even at moderate lengths. Yet, this early degradation has…

Computation and Language · Computer Science 2026-01-21 Jungyoub Cha , Hyunjong Kim , Sungzoon Cho

Early-Exit Large Language Models (EE-LLMs) enable high throughput inference by allowing tokens to exit early at intermediate layers. However, their throughput is limited by the computational and memory savings. Existing EE-LLM frameworks…

Computation and Language · Computer Science 2025-11-03 Avinash Kumar , Shashank Nag , Jason Clemons , Lizy John , Poulami Das

We present speculative sampling, an algorithm for accelerating transformer decoding by enabling the generation of multiple tokens from each transformer call. Our algorithm relies on the observation that the latency of parallel scoring of…

Computation and Language · Computer Science 2023-02-03 Charlie Chen , Sebastian Borgeaud , Geoffrey Irving , Jean-Baptiste Lespiau , Laurent Sifre , John Jumper

Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency between the draft model and the verify model. However, existing…

Computation and Language · Computer Science 2025-06-02 Longze Chen , Renke Shan , Huiming Wang , Lu Wang , Ziqiang Liu , Run Luo , Jiawei Wang , Hamid Alinejad-Rokny , Min Yang

Large Language Models (LLMs) have revolutionized natural language processing by understanding and generating human-like text. However, the increasing demand for more sophisticated LLMs presents significant computational challenges due to…

Computation and Language · Computer Science 2025-01-14 Ze Yang , Yihong Jin , Xinhe Xu

Diffusion Large Language Models (dLLMs) offer fast, parallel token generation, but their standalone use is plagued by an inherent efficiency-quality tradeoff. We show that, if carefully applied, the attributes of dLLMs can actually be a…

Machine Learning · Computer Science 2026-01-29 Rui Pan , Zhuofu Chen , Hongyi Liu , Arvind Krishnamurthy , Ravi Netravali

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 accelerates inference for Large Language Models by using a lightweight draft model to propose candidate tokens that are verified in parallel by a larger target model. Prior work shows that the draft model often…

Computation and Language · Computer Science 2026-03-06 Ofir Ben Shoham

Speculative decoding accelerates LLM inference by drafting multiple tokens and verifying them in parallel with the target model. However, its practical speedup is constrained by the trade-off between draft quality and drafting cost:…

Computation and Language · Computer Science 2026-05-29 Jianuo Huang , Yaojie Zhang , Qituan Zhang , Hao Lin , Hanlin Xu , Linfeng Zhang

Autoregressive decoding makes the inference of Large Language Models (LLMs) time-consuming. In this paper, we reconsider speculative sampling and derive two key observations. Firstly, autoregression at the feature (second-to-top-layer)…

Machine Learning · Computer Science 2025-03-05 Yuhui Li , Fangyun Wei , Chao Zhang , Hongyang Zhang

Diffusion large language models (dLLMs) offer a promising paradigm for parallel text generation, but in practice they face an accuracy-parallelism trade-off, where increasing tokens per forward (TPF) often degrades generation quality.…

Computation and Language · Computer Science 2026-05-12 Haoyang Zhou , Li Kong , Shijie Ren , Xiting Wang , Shuang Liang , Guowei Wang , Zhenxuan Pan

Speculative decoding has been shown as an effective way to accelerate Large Language Model (LLM) inference by using a Small Speculative Model (SSM) to generate candidate tokens in a so-called speculation phase, which are subsequently…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-03-21 Fahao Chen , Peng Li , Tom H. Luan , Zhou Su , Jing Deng

Speculative decoding is widely adopted to reduce latency in large language model (LLM) inference by leveraging smaller draft models capable of handling diverse user tasks. However, emerging AI applications, such as LLM-based agents, present…

Computation and Language · Computer Science 2025-10-09 Gabriele Oliaro , Zhihao Jia , Daniel Campos , Aurick Qiao

Extracting sentence embeddings from large language models (LLMs) is a promising direction, as LLMs have demonstrated stronger semantic understanding capabilities. Previous studies typically focus on prompt engineering to elicit sentence…

Computation and Language · Computer Science 2025-07-04 Yuchen Fu , Zifeng Cheng , Zhiwei Jiang , Zhonghui Wang , Yafeng Yin , Zhengliang Li , Qing Gu

Diffusion large language models (dLLMs) offer a promising alternative to autoregressive models, but their practical utility is severely hampered by slow, iterative sampling. We present SchED, a training-free, model-agnostic early-exit…

Computation and Language · Computer Science 2025-12-03 Amr Mohamed , Yang Zhang , Michalis Vazirgiannis , Guokan Shang

We propose a novel speculative decoding method tailored for multi-sample reasoning scenarios, such as self-consistency and Best-of-N sampling. Our method exploits the intrinsic consensus of parallel generation paths to synthesize…

Computation and Language · Computer Science 2025-03-10 Yiwei Li , Jiayi Shi , Shaoxiong Feng , Peiwen Yuan , Xinglin Wang , Yueqi Zhang , Ji Zhang , Chuyi Tan , Boyuan Pan , Yao Hu , Kan Li

To tackle the high inference latency exhibited by autoregressive language models, previous studies have proposed an early-exiting framework that allocates adaptive computation paths for each token based on the complexity of generating the…

Computation and Language · Computer Science 2023-10-10 Sangmin Bae , Jongwoo Ko , Hwanjun Song , Se-Young Yun
‹ Prev 1 8 9 10 Next ›