English
Related papers

Related papers: Faster Cascades via Speculative Decoding

200 papers

Introduced to enhance the efficiency of large language model (LLM) inference, speculative decoding operates by having a smaller model generate a draft. A larger target model then reviews this draft to align with its output, and any…

Machine Learning · Computer Science 2025-07-15 Ziyi Chen , Xiaocong Yang , Jiacheng Lin , Chenkai Sun , Kevin Chen-Chuan Chang , Jie Huang

The practice of speculative decoding, whereby inference is probabilistically supported by a smaller, cheaper, ``drafter'' model, has become a standard technique for systematically reducing the decoding time of large language models. This…

Computation and Language · Computer Science 2025-10-03 Jameson Sandler , Ahmet Üstün , Marco Romanelli , Sara Hooker , Ferdinando Fioretto

Cascades are a classical strategy to enable inference cost to vary adaptively across samples, wherein a sequence of classifiers are invoked in turn. A deferral rule determines whether to invoke the next classifier in the sequence, or to…

Recent advances in language models (LMs) have led to significant improvements in quality on complex NLP tasks, but at the expense of increased inference costs. Cascading offers a simple strategy to achieve more favorable cost-quality…

Computation and Language · Computer Science 2024-04-17 Neha Gupta , Harikrishna Narasimhan , Wittawat Jitkrittum , Ankit Singh Rawat , Aditya Krishna Menon , Sanjiv Kumar

Speculative decoding has emerged as a widely adopted method to accelerate large language model inference without sacrificing the quality of the model outputs. While this technique has facilitated notable speed improvements by enabling…

Computation and Language · Computer Science 2025-02-12 Jacob K Christopher , Brian R Bartoldson , Tal Ben-Nun , Michael Cardei , Bhavya Kailkhura , Ferdinando Fioretto

Speculative Decoding is a widely used technique to speed up inference for Large Language Models (LLMs) without sacrificing quality. When performing inference, speculative decoding uses a smaller draft model to generate speculative tokens…

Machine Learning · Computer Science 2025-02-06 Minghao Yan , Saurabh Agarwal , Shivaram Venkataraman

Efficient inference in large language models (LLMs) has become a critical focus as their scale and complexity grow. Traditional autoregressive decoding, while effective, suffers from computational inefficiencies due to its sequential token…

Computation and Language · Computer Science 2024-11-28 Hyun Ryu , Eric Kim

Speculative decoding is a technique that uses multiple language models to accelerate infer- ence. Previous works have used an experi- mental approach to optimize the throughput of the inference pipeline, which involves LLM training and can…

Computation and Language · Computer Science 2026-03-13 Amirhossein Bozorgkhoo , Igor Molybog

To mitigate the high inference latency stemming from autoregressive decoding in Large Language Models (LLMs), Speculative Decoding has emerged as a novel decoding paradigm for LLM inference. In each decoding step, this method first drafts…

Computation and Language · Computer Science 2024-06-05 Heming Xia , Zhe Yang , Qingxiu Dong , Peiyi Wang , Yongqi Li , Tao Ge , Tianyu Liu , Wenjie Li , Zhifang Sui

Larger models often outperform smaller ones but come with high computational costs. Cascading offers a potential solution. By default, it uses smaller models and defers only some instances to larger, more powerful models. However, designing…

Computation and Language · Computer Science 2025-02-19 António Farinhas , Nuno M. Guerreiro , Sweta Agrawal , Ricardo Rei , André F. T. Martins

Speculative decoding has emerged as an effective approach for accelerating autoregressive inference by parallelizing token generation through a draft-then-verify paradigm. However, existing methods rely on static drafting lengths and rigid…

Computation and Language · Computer Science 2026-05-29 Jaydip Sen , Subhasis Dasgupta , Hetvi Waghela

Model Cascading, recently applied successfully to LLMs, is a simple but powerful technique that improves the efficiency of inference by selectively applying models of varying sizes. Models are used in sequence from smallest to largest, only…

Machine Learning · Computer Science 2025-08-21 David Warren , Mark Dras

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

Large language models~(LLMs) exhibit exceptional performance in language tasks, yet their auto-regressive inference is limited due to high computational requirements and is sub-optimal due to the exposure bias. Inspired by speculative…

Computation and Language · Computer Science 2024-03-14 Hongyi Yuan , Keming Lu , Fei Huang , Zheng Yuan , Chang Zhou

Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering challenges, including efficiently implementing different…

Generative Large Language Models (LLMs) based on the Transformer architecture have recently emerged as a dominant foundation model for a wide range of Natural Language Processing tasks. Nevertheless, their application in real-time scenarios…

Computation and Language · Computer Science 2024-01-04 Coleman Hooper , Sehoon Kim , Hiva Mohammadzadeh , Hasan Genc , Kurt Keutzer , Amir Gholami , Sophia Shao

Transformer language models generate text autoregressively, making inference latency proportional to the number of tokens generated. Speculative decoding reduces this latency without sacrificing output quality, by leveraging a small draft…

Machine Learning · Computer Science 2025-10-24 Clara Mohri , Haim Kaplan , Tal Schuster , Yishay Mansour , Amir Globerson

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

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 accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While effective in centralized systems, its behavior in…

Distributed, Parallel, and Cluster Computing · Computer Science 2025-11-18 Jingwei Song , Wanyi Chen , Xinyuan Song , Max , Chris Tong , Gufeng Chen , Tianyi Zhao , Eric Yang , Bill Shi , Lynn Ai
‹ Prev 1 2 3 10 Next ›