English
Related papers

Related papers: Towards Optimal Multi-draft Speculative Decoding

200 papers

Self-speculative decoding (SSD) accelerates LLM inference by skipping layers to create an efficient draft model, yet existing methods often rely on static heuristics that ignore the dynamic computational overhead of attention in…

Machine Learning · Computer Science 2026-02-25 Seongjin Cha , Gyuwan Kim , Dongsu Han , Tao Yang , Insu Han

Decoding from large language models (LLMs) typically relies on fixed sampling hyperparameters (e.g., temperature, top-p), despite substantial variation in task difficulty and uncertainty across prompts and individual decoding steps. We…

Machine Learning · Computer Science 2026-03-17 Chloe H. Su , Zhe Ye , Samuel Tenka , Aidan Yang , Soonho Kong , Udaya Ghai

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

Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing…

Machine Learning · Computer Science 2025-05-13 Hang Wu , Jianian Zhu , Yinghui Li , Haojie Wang , Biao Hou , Jidong Zhai

Speculative decoding accelerates autoregressive language model inference by verifying multiple draft tokens in parallel. However, the verification stage often becomes the dominant computational bottleneck, especially for long-context inputs…

Computation and Language · Computer Science 2025-12-29 Jikai Wang , Jianchao Tan , Yuxuan Hu , Jiayu Qin , Yerui Sun , Yuchen Xie , Xunliang Cai , Juntao Li , Min Zhang

Lossless speculative decoding accelerates target large language model (LLM) inference by employing a lightweight draft model for generating tree-structured candidates, which are subsequently verified in parallel by the target LLM.…

Computation and Language · Computer Science 2024-08-29 Lujun Gui , Bin Xiao , Lei Su , Weipeng Chen

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

Speculative decoding is a prominent technique to speed up the inference of a large target language model based on predictions of an auxiliary draft model. While effective, in application-specific settings, it often involves fine-tuning both…

Computation and Language · Computer Science 2024-02-20 Nikhil Bhendawade , Irina Belousova , Qichen Fu , Henry Mason , Mohammad Rastegari , Mahyar Najibi

Speculative decoding relies on fast and accurate drafters. Recent state-of-the-art language models employ larger and larger vocabularies, which significantly slows down drafters. One promising approach to boost the efficiency of speculative…

Machine Learning · Computer Science 2025-06-05 Nadav Timor , Jonathan Mamou , Oren Pereg , Hongyang Zhang , David Harel

Accelerating inference in Large Language Models (LLMs) is critical for real-time interactions, as they have been widely incorporated into real-world services. Speculative decoding, a fully algorithmic solution, has gained attention for…

Computation and Language · Computer Science 2025-02-11 Sukmin Cho , Sangjin Choi , Taeho Hwang , Jeongyeon Seo , Soyeong Jeong , Huije Lee , Hoyun Song , Jong C. Park , Youngjin Kwon

Existing Large Language Models (LLMs) generate text through unidirectional autoregressive decoding methods to respond to various user queries. These methods tend to consider token selection in a simple sequential manner, making it easy to…

Computation and Language · Computer Science 2024-05-28 Ziqin Luo , Haixia Han , Haokun Zhao , Guochao Jiang , Chengyu Du , Tingyun Li , Jiaqing Liang , Deqing Yang , Yanghua Xiao

Inference with modern Large Language Models (LLMs) is expensive and slow, and speculative sampling has emerged as an effective solution to this problem, however, the number of the calls to the draft model for generating candidate tokens in…

Artificial Intelligence · Computer Science 2025-12-17 Junjie Ma , Jinlong Li

In spite of the great potential of large language models (LLMs) across various tasks, their deployment on resource-constrained devices remains challenging due to their excessive computational and memory demands. Quantization has emerged as…

Machine Learning · Computer Science 2025-02-28 Hao Mark Chen , Fuwen Tan , Alexandros Kouris , Royson Lee , Hongxiang Fan , Stylianos I. Venieris

The growing gap between the increasing complexity of large language models (LLMs) and the limited computational budgets of edge devices poses a key challenge for efficient on-device inference, despite gradual improvements in hardware…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-06 Xiangchen Li , Dimitrios Spatharakis , Saeid Ghafouri , Jiakun Fan , Hans Vandierendonck , Deepu John , Bo Ji , Dimitrios Nikolopoulos

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

The acceleration of Large Language Models (LLMs) with speculative decoding provides a significant runtime improvement without any loss of accuracy. Currently, EAGLE-2 is the state-of-the-art speculative decoding method, improving on EAGLE…

Computation and Language · Computer Science 2024-09-04 Oscar Brown , Zhengjie Wang , Andrea Do , Nikhil Mathew , Cheng Yu

Constrained decoding enables Language Models (LMs) to produce samples that provably satisfy hard constraints. However, existing constrained-decoding approaches often distort the underlying model distribution, a limitation that is especially…

Artificial Intelligence · Computer Science 2025-06-09 Emmanuel Anaya Gonzalez , Sairam Vaidya , Kanghee Park , Ruyi Ji , Taylor Berg-Kirkpatrick , Loris D'Antoni

While Large Language Models (LLMs) have shown remarkable abilities, they are hindered by significant resource consumption and considerable latency due to autoregressive processing. In this study, we introduce Adaptive N-gram Parallel…

Computation and Language · Computer Science 2024-07-11 Jie Ou , Yueming Chen , Wenhong Tian

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

Large language models (LLMs) underpin interactive multimedia applications such as captioning, retrieval, recommendation, and creative content generation, yet their autoregressive decoding incurs substantial latency. Speculative decoding…

Artificial Intelligence · Computer Science 2026-02-06 Hanyu Wei , Zunhai Su , Peng Lu , Chao Li , Spandan Tiwari , Ashish Sirasao , Yuhan Dong