English
Related papers

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

200 papers

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

Large Language Models (LLMs) face efficiency bottlenecks due to the quadratic complexity of the attention mechanism when processing long contexts. Sparse attention methods offer a promising solution, but existing approaches often suffer…

Computation and Language · Computer Science 2025-03-06 Lida Chen , Dong Xu , Chenxin An , Xintao Wang , Yikai Zhang , Jiangjie Chen , Zujie Liang , Feng Wei , Jiaqing Liang , Yanghua Xiao , Wei Wang

As large language models (LLMs) continue to support increasingly longer contexts, the memory demand for key-value (KV) caches during decoding grows rapidly, becoming a critical bottleneck in both GPU memory capacity and PCIe bandwidth.…

Machine Learning · Computer Science 2025-06-23 Feiyu Yao , Qian Wang

Speculative decoding has become a widely adopted as an effective technique for lossless inference acceleration when deploying large language models (LLMs). While on-the-fly self-speculative methods offer seamless integration and broad…

Machine Learning · Computer Science 2025-11-03 Zhiyuan Ning , Jiawei Shao , Ruge Xu , Xinfei Guo , Jun Zhang , 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

The context window of large language models (LLMs) is rapidly increasing, leading to a huge variance in resource usage between different requests as well as between different phases of the same request. Restricted by static parallelism…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-30 Bingyang Wu , Shengyu Liu , Yinmin Zhong , Peng Sun , Xuanzhe Liu , Xin Jin

Deploying long-context large language models (LLMs) is essential but poses significant computational and memory challenges. Caching all Key and Value (KV) states across all attention heads consumes substantial memory. Existing KV cache…

Computation and Language · Computer Science 2024-10-15 Guangxuan Xiao , Jiaming Tang , Jingwei Zuo , Junxian Guo , Shang Yang , Haotian Tang , Yao Fu , Song Han

Speculative decoding has emerged as a promising approach to accelerate autoregressive inference in large language models (LLMs). Self-draft methods, which leverage the base LLM itself for speculation, avoid the overhead of auxiliary draft…

Computation and Language · Computer Science 2026-04-15 Zhuofan Wen , Yang Feng

The performance of large language models (LLMs) is closely linked to their underlying size, leading to ever-growing networks and hence slower inference. Speculative decoding has been proposed as a technique to accelerate autoregressive…

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 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

Speculative decoding (SD), where a draft model provides multiple candidate tokens for the target model to verify in parallel, has demonstrated significant potential for accelerating LLM inference. Yet, existing SD approaches adhere to a…

Machine Learning · Computer Science 2025-09-22 Enyu Zhou , Kai Sheng , Hao Chen , Xin He

Large Language Model (LLM)-based generative recommendation has achieved notable success, yet its practical deployment is costly particularly due to excessive inference latency caused by autoregressive decoding. For lossless LLM decoding…

Information Retrieval · Computer Science 2025-02-27 Xinyu Lin , Chaoqun Yang , Wenjie Wang , Yongqi Li , Cunxiao Du , Fuli Feng , See-Kiong Ng , Tat-Seng Chua

The quadratic complexity of attention imposes severe memory and computational bottlenecks on Large Language Model (LLM) inference. This challenge is particularly acute for emerging agentic applications that require processing multi-million…

Machine Learning · Computer Science 2026-05-19 Ceyu Xu , Jiangnan Yu , Yongji Wu , Yuan Xie

Speculative decoding accelerates inference in large language models (LLMs) by generating draft tokens for target model verification. Current approaches for obtaining draft tokens rely on lightweight draft models or additional model…

Computation and Language · Computer Science 2025-03-06 Guofeng Quan , Wenfeng Feng , Chuzhan Hao , Guochao Jiang , Yuewei Zhang , Hao Wang

The limited context window of contemporary large language models (LLMs) remains a primary bottleneck for their broader application across diverse domains. Although continual pre-training on long-context data offers a straightforward…

Computation and Language · Computer Science 2026-04-10 Wei Han , Pan Zhou , Soujanya Poria , Shuicheng Yan

Recent advancements in Large Language Models (LLMs) have significantly enhanced their capacity to process long contexts. However, effectively utilizing this long context remains a challenge due to the issue of distraction, where irrelevant…

Computation and Language · Computer Science 2024-11-12 Zijun Wu , Bingyuan Liu , Ran Yan , Lei Chen , Thomas Delteil

LLM deployment on resource-constrained edge devices faces severe latency constraints, particularly in real-time applications where delayed responses can compromise safety or usability. Among many approaches to mitigate the inefficiencies of…

Speculative decoding is a powerful way to accelerate autoregressive large language models (LLMs), but directly porting it to vision-language models (VLMs) faces unique systems constraints: the prefill stage is dominated by visual tokens…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Haiduo Huang , Fuwei Yang , Zhenhua Liu , Xuanwu Yin , Dong Li , Pengju Ren , Emad Barsoum

Speculative decoding accelerates Large Language Model (LLM) inference by employing a small speculative model (SSM) to generate multiple candidate tokens and verify them using the LLM in parallel. This technique has been widely integrated…

Computation and Language · Computer Science 2025-05-26 Ruixiao Li , Fahao Chen , Peng Li