English
Related papers

Related papers: LongSpec: Long-Context Lossless Speculative Decodi…

200 papers

Speculative decoding is an inference-acceleration method for large language models (LLMs) where a small language model generates a draft-token sequence which is further verified by the target LLM in parallel. Recent works have advanced this…

Machine Learning · Computer Science 2024-03-06 Wonseok Jeon , Mukul Gagrani , Raghavv Goel , Junyoung Park , Mingu Lee , Christopher Lott

While long-context large language models (LLMs) exhibit remarkable document processing capabilities, their prohibitively high training costs often hinder customized applications. To mitigate this issue, we propose \textit{Sequential…

Machine Learning · Computer Science 2025-05-23 Wenhao Li , Yuxin Zhang , Gen Luo , Daohai Yu , Rongrong Ji

Speculative decoding (SD) accelerates large language model (LLM) reasoning by using a small draft model to generate candidate tokens, which the target LLM either accepts directly or regenerates upon rejection. However, excessive alignment…

Computation and Language · Computer Science 2026-01-01 Tiancheng Su , Meicong Zhang , Guoxiu He

Empowering LLMs with the ability to precisely understand long contexts is crucial for many downstream applications. However, handling long contexts with conventional transformer architecture requires substantial training and inference…

Computation and Language · Computer Science 2024-12-24 Zhenyu Li , Yike Zhang , Tengyu Pan , Yutao Sun , Zhichao Duan , Junjie Fang , Rong Han , Zixuan Wang , Jianyong Wang

With the increasingly giant scales of (causal) large language models (LLMs), the inference efficiency comes as one of the core concerns along the improved performance. In contrast to the memory footprint, the latency bottleneck seems to be…

Computation and Language · Computer Science 2024-04-24 Chen Zhang , Zhuorui Liu , Dawei Song

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

Large Language Models (LLMs) have demonstrated remarkable capabilities in code editing, substantially enhancing software development productivity. However, the inherent complexity of code editing tasks forces existing approaches to rely on…

Software Engineering · Computer Science 2025-10-01 Peiding Wang , Li Zhang , Fang Liu , Yinghao Zhu , Wang Xu , Lin Shi , Xiaoli Lian , Minxiao Li , Bo Shen , An Fu

Large language models (LLMs) have driven significant advancements across diverse NLP tasks, with long-context models gaining prominence for handling extended inputs. However, the expanding key-value (KV) cache size required by Transformer…

Machine Learning · Computer Science 2024-10-08 Lijie Yang , Zhihao Zhang , Zhuofu Chen , Zikun Li , Zhihao Jia

Speculative decoding (SD) has been shown to reduce the latency of autoregressive decoding (AD) by 2-3x for small batch sizes. However, increasing throughput and therefore reducing the cost per token requires decoding with large batch sizes.…

Machine Learning · Computer Science 2025-04-10 Sanjit Neelam , Daniel Heinlein , Vaclav Cvicek , Akshay Mishra , Reiner Pope

As the length of input text increases, the key-value (KV) cache in LLMs imposes prohibitive GPU memory costs and limits long-context inference on resource constrained devices. Existing approaches, such as KV quantization and pruning, reduce…

Machine Learning · Computer Science 2025-12-24 Tenghui Li , Guoxu Zhou , Xuyang Zhao , Yuning Qiu , Qibin Zhao

While many advanced LLMs are designed to handle long sequence data, we can still observe notable quality degradation even within the sequence limit. In this work, we introduce a novel approach called Scaling to Emphasize Attention for…

Computation and Language · Computer Science 2025-06-24 Changhun Lee , Minsang Seok , Jun-gyu Jin , Younghyun Cho , Eunhyeok Park

Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several…

Machine Learning · Computer Science 2025-06-04 Selin Yildirim , Deming Chen

Speculative Decoding (SD) has emerged as a premier technique for accelerating Large Language Model (LLM) inference by decoupling token generation into rapid drafting and parallel verification. While recent advancements in self-speculation…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-03-03 Guang Huang , Zeyi Wen

Efficient processing of long contexts has been a persistent pursuit in Natural Language Processing. With the growing number of long documents, dialogues, and other textual data, it is important to develop Long Context Language Models…

Large language models (LLMs) based on Transformer have been widely applied in the filed of natural language processing (NLP), demonstrating strong performance, particularly in handling short text tasks. However, when it comes to long…

Computation and Language · Computer Science 2025-07-09 Yijun Liu , Jinzheng Yu , Yang Xu , Zhongyang Li , Qingfu Zhu

Speculative decoding is a pivotal technique to accelerate the inference of large language models (LLMs) by employing a smaller draft model to predict the target model's outputs. However, its efficacy can be limited due to the low predictive…

Artificial Intelligence · Computer Science 2024-06-11 Xiaoxuan Liu , Lanxiang Hu , Peter Bailis , Alvin Cheung , Zhijie Deng , Ion Stoica , Hao Zhang

Speculative decoding accelerates autoregressive large language model (LLM) inference by using a lightweight draft model to propose candidate tokens that are then verified in parallel by the target model. The speedup is significantly…

Machine Learning · Computer Science 2026-03-02 Alexander Samarin , Sergei Krutikov , Anton Shevtsov , Sergei Skvortsov , Filipp Fisin , Alexander Golubev

Existing benchmarks for evaluating long-context language models (LCLMs) primarily focus on long-context recall, requiring models to produce short responses based on a few critical snippets while processing thousands of irrelevant tokens. We…

Computation and Language · Computer Science 2025-09-30 Xi Ye , Fangcong Yin , Yinghui He , Joie Zhang , Howard Yen , Tianyu Gao , Greg Durrett , Danqi Chen

Large Language Models (LLMs) have demonstrated remarkable capabilities across various applications, but their performance on long-context tasks is often limited by the computational complexity of attention mechanisms. We introduce a novel…

Machine Learning · Computer Science 2025-02-25 Bo Chen , Yingyu Liang , Zhizhou Sha , Zhenmei Shi , Zhao Song

Recently, large language models (LLMs) have shown remarkable capabilities including understanding context, engaging in logical reasoning, and generating responses. However, this is achieved at the expense of stringent computational and…

Computation and Language · Computer Science 2024-05-30 Xindi Wang , Mahsa Salmani , Parsa Omidi , Xiangyu Ren , Mehdi Rezagholizadeh , Armaghan Eshaghi