English
Related papers

Related papers: Kangaroo: Lossless Self-Speculative Decoding via D…

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

We propose Speculative Decoding (SpecDec), for the first time ever, to formally study exploiting the idea of speculative execution to accelerate autoregressive (AR) decoding. Speculative Decoding has two innovations: Spec-Drafter -- an…

Computation and Language · Computer Science 2023-10-31 Heming Xia , Tao Ge , Peiyi Wang , Si-Qing Chen , Furu Wei , Zhifang Sui

Inference acceleration of large language models (LLMs) has been put forward in many application scenarios and speculative decoding has shown its advantage in addressing inference acceleration. Speculative decoding usually introduces a draft…

Machine Learning · Computer Science 2024-12-03 Zhuofan Wen , Shangtong Gui , Yang Feng

Speculative decoding accelerates autoregressive generation by letting a lightweight draft model propose future tokens that a larger target model then verifies in parallel. In practice, however, draft models are usually trained on broad…

Computation and Language · Computer Science 2026-03-31 Mohamad Zbib , Mohamad Bazzi , Ammar Mohanna , Hasan Abed Al Kader Hammoud , Bernard Ghanem

Long-context large language model (LLM) inference has become the norm for today's AI applications. However, it is severely bottlenecked by the increasing memory demands of its KV cache. Previous works have shown that self-speculative…

Machine Learning · Computer Science 2026-02-10 Yikang Yue , Yuqi Xue , Jian Huang

Speculative decoding accelerates LLMs by using a lightweight draft model to generate tokens autoregressively before verifying them in parallel with a larger target model. However, determining the optimal number of tokens to draft remains a…

Machine Learning · Computer Science 2025-11-05 Aditya Sridhar , Nish Sinnadurai , Sean Lie , Vithursan Thangarasa

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

Large language models achieve impressive performance across diverse tasks but exhibit high inference latency due to their large parameter sizes. While quantization reduces model size, it often leads to performance degradation compared to…

Hardware Architecture · Computer Science 2025-10-22 Yushu Zhao , Yubin Qin , Yang Wang , Xiaolong Yang , Huiming Han , Shaojun Wei , Yang Hu , Shouyi Yin

Speculative decoding accelerates LLM inference by drafting a tree of candidate continuations and verifying it in one target forward. Existing drafters fall into two camps with opposite weaknesses. Autoregressive drafters such as EAGLE-3…

Computation and Language · Computer Science 2026-05-22 Weijie Shi , Qiang Xu , Fan Deng , Yaguang Wu , Jiarun Liu , Yehong Xu , Hao Chen , Jia Zhu , Jiajie Xu , Xiangjun Huang , Jian Yang , Xiaofang Zhou

Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically…

Computation and Language · Computer Science 2026-05-19 Shuoyang Sun , Chang Dai , Hao Fang , Kuofeng Gao , Xinhao Zhong , Yi Sun , Fan Mo , Shu-Tao Xia , Bin Chen

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Computation and Language · Computer Science 2026-03-03 Jiebin Zhang , Zhenghan Yu , Liang Wang , Nan Yang , Eugene J. Yu , Zheng Li , Yifan Song , Dawei Zhu , Xingxing Zhang , Furu Wei , Sujian Li

Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\times$ slower than token generation when a…

Computation and Language · Computer Science 2026-05-27 Avinash Kumar , Sujay Sanghavi , Poulami Das

Transformer-based autoregressive sampling has been the major bottleneck for slowing down large language model inferences. One effective way to accelerate inference is \emph{Speculative Decoding}, which employs a small model to sample a…

Machine Learning · Computer Science 2024-11-05 Ming Yin , Minshuo Chen , Kaixuan Huang , Mengdi Wang

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

Speculative decoding accelerates inference in large language models (LLMs) by generating multiple draft tokens simultaneously. However, existing methods often struggle with token misalignment between the training and decoding phases,…

Computation and Language · Computer Science 2025-10-21 Shijing Hu , Jingyang Li , Xingyu Xie , Zhihui Lu , Kim-Chuan Toh , Pan Zhou

Accelerating the inference of large language models (LLMs) is a critical challenge in generative AI. Speculative decoding (SD) methods offer substantial efficiency gains by generating multiple tokens using a single target forward pass.…

Computation and Language · Computer Science 2025-06-12 Nadav Timor , Jonathan Mamou , Daniel Korat , Moshe Berchansky , Gaurav Jain , Oren Pereg , Moshe Wasserblat , David Harel

We present a simple on the fly method for faster inference of large language models. Unlike other (self-)speculative decoding techniques, our method does not require fine-tuning or black-box optimization to generate a fixed draft model,…

Computation and Language · Computer Science 2024-10-03 Michael R. Metel , Peng Lu , Boxing Chen , Mehdi Rezagholizadeh , Ivan Kobyzev

Speculative generation has emerged as a promising technique to accelerate inference in large language models (LLMs) by leveraging parallelism to verify multiple draft tokens simultaneously. However, the fundamental limits on the achievable…

Computation and Language · Computer Science 2025-12-15 Sergey Pankratov , Dan Alistarh

Large language models (LLMs) deliver impressive generation quality, but incur very high inference cost because each output token is generated auto-regressively through all model layers. Early-exit based self-speculative decoding (EESD) has…

Computation and Language · Computer Science 2025-09-25 Ruanjun Li , Ziheng Liu , Yuanming Shi , Jiawei Shao , Chi Zhang , Xuelong Li

Speculative decoding accelerates memory-bound LLM inference without quality degradation by using a fast drafter to propose multiple candidate tokens and the target model to verify them in parallel. However, conventional sequential…

Computation and Language · Computer Science 2026-05-20 Yaojie Zhang , Jianuo Huang , Junlong Ke , Yuhang Han , Yongji Long , Tianchen Zhao , Biqing Qi , Linfeng Zhang