English
Related papers

Related papers: Out-of-Vocabulary Sampling Boosts Speculative Deco…

200 papers

Speculative decoding speeds up autoregressive generation in Large Language Models (LLMs) through a two-step procedure, where a lightweight draft model proposes tokens which the target model then verifies in a single forward pass. Although…

Machine Learning · Computer Science 2026-05-12 Anton Plaksin , Sergei Krutikov , Sergei Skvortsov , Alexander Samarin

Multi-path speculative decoding accelerates lossless sampling from a target model by using a cheaper draft model to generate a draft tree of tokens, and then applies a verification algorithm that accepts a subset of these. While prior work…

Machine Learning · Computer Science 2026-02-20 Rahul Thomas , Teo Kitanovski , Micah Goldblum , Arka Pal

The emergence of long-context large language models (LLMs) offers a promising alternative to traditional retrieval-augmented generation (RAG) for processing extensive documents. However, the computational overhead of long-context inference…

Computation and Language · Computer Science 2025-06-24 Guanzheng Chen , Qilong Feng , Jinjie Ni , Xin Li , Michael Qizhe Shieh

The dominant approach to generating from language models subject to some constraint is locally constrained decoding (LCD), incrementally sampling tokens at each time step such that the constraint is never violated. Typically, this is…

Speculative decoding is a powerful technique that attempts to circumvent the autoregressive constraint of modern Large Language Models (LLMs). The aim of speculative decoding techniques is to improve the average inference time of a large,…

Computation and Language · Computer Science 2024-10-25 Sudhanshu Agrawal , Wonseok Jeon , Mingu Lee

Speculative Decoding (SD) is a technique to accelerate the inference of Large Language Models (LLMs) by using a lower complexity draft model to propose candidate tokens verified by a larger target model. To further improve efficiency,…

Computation and Language · Computer Science 2024-12-17 Xiaofan Lu , Yixiao Zeng , Feiyang Ma , Zixu Yu , Marco Levorato

Massive parameters of LLMs have made inference latency a fundamental bottleneck. Speculative decoding represents a lossless approach to accelerate inference through a guess-and-verify paradigm. Some methods rely on additional architectures…

Computation and Language · Computer Science 2025-05-27 Xianzhen Luo , Yixuan Wang , Qingfu Zhu , Zhiming Zhang , Xuanyu Zhang , Qing Yang , Dongliang Xu

We present Recurrent Drafter (ReDrafter), an advanced speculative decoding approach that achieves state-of-the-art speedup for large language models (LLMs) inference. The performance gains are driven by three key aspects: (1) leveraging a…

Computation and Language · Computer Science 2024-12-17 Yunfei Cheng , Aonan Zhang , Xuanyu Zhang , Chong Wang , Yi Wang

Scaling the size of language models to tens of billions of parameters has led to impressive performance on a wide range of tasks. At generation, these models are used auto-regressively, requiring a forward pass for each generated token, and…

Computation and Language · Computer Science 2023-11-23 Giovanni Monea , Armand Joulin , Edouard Grave

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 (SD) is a widely used approach to accelerate the inference of large language models (LLMs) without reducing generation quality. It operates by first using a compact model to draft multiple tokens efficiently, followed…

Computation and Language · Computer Science 2025-08-08 Hossein Entezari Zarch , Lei Gao , Chaoyi Jiang , Murali Annavaram

Speculative decoding accelerates large language model inference by proposing tokens with a lightweight draft model and selectively accepting them using a target model. This work introduces DropMatch, a novel approach that matches draft…

Computation and Language · Computer Science 2026-03-05 Jeongtae Lee , Minjung Jo , Hyunjoon Jeong , Gunho Park , Sunghyeon Woo , Joonghoon Kim , Se Jung Kwon , Dongsoo Lee

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

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 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

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 accelerates large language model (LLM) inference by using a small draft model to propose candidate tokens that a larger target model verifies. A critical hyperparameter in this process is the speculation length…

Machine Learning · Computer Science 2026-05-06 Shikhar Shukla

We consider multi-draft speculative sampling, where the proposal sequences are sampled independently from different draft models. At each step, a token-level draft selection scheme takes a list of valid tokens as input and produces an…

Computation and Language · Computer Science 2025-05-12 Ashish Khisti , M. Reza Ebrahimi , Hassan Dbouk , Arash Behboodi , Roland Memisevic , Christos Louizos

Speculative decoding has emerged as a promising technique to accelerate the inference of Large Language Models (LLMs) by employing a small language model to draft a hypothesis sequence, which is then validated by the LLM. The effectiveness…

Computation and Language · Computer Science 2024-07-24 Zhuocheng Gong , Jiahao Liu , Ziyue Wang , Pengfei Wu , Jingang Wang , Xunliang Cai , Dongyan Zhao , Rui Yan

Speculative decoding reduces the inference latency of a target large language model via utilizing a smaller and faster draft model. Its performance depends on a hyperparameter K -- the candidate length, i.e., the number of candidate tokens…

Computation and Language · Computer Science 2025-07-14 Kaixuan Huang , Xudong Guo , Mengdi Wang