English
Related papers

Related papers: Efficient Speculative Decoding for Llama at Scale:…

200 papers

Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of this technique hinges on the trade-off between the time…

Computation and Language · Computer Science 2026-03-03 Jiebin Zhang , Zhenghan Yu , Liang Wang , Nan Yang , Eugene J. Yu , Zheng Li , Yifan Song , Dawei Zhu , Xingxing Zhang , Furu Wei , Sujian Li

Large language models (LLM) have recently attracted surging interest due to their outstanding capabilities across various domains. However, enabling efficient LLM inference is challenging due to its autoregressive decoding that generates…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-10-31 Siqi Wang , Hailong Yang , Xuezhu Wang , Tongxuan Liu , Pengbo Wang , Xuning Liang , Kejie Ma , Tianyu Feng , Xin You , Yongjun Bao , Yi Liu , Zhongzhi Luan , Depei Qian

Large language models (LLMs) have demonstrated remarkable performance and tremendous potential across a wide range of tasks. However, deploying these models has been challenging due to the astronomical amount of model parameters, which…

Machine Learning · Computer Science 2023-12-08 Haihao Shen , Hanwen Chang , Bo Dong , Yu Luo , Hengyu Meng

Transformer-based Large Language Models (LLMs) have made a significant impact on various domains. However, LLMs' efficiency suffers from both heavy computation and memory overheads. Compression techniques like sparsification and…

LLM inference exhibits substantial variability across queries and execution phases, yet inference configurations are often applied uniformly. We present a measurement-driven characterization of workload heterogeneity and energy-performance…

Machine Learning · Computer Science 2026-02-25 Paul Joe Maliakel , Shashikant Ilager , Ivona Brandic

Speculative decoding is an emerging technique that accelerates large language model (LLM) inference by allowing a smaller draft model to predict multiple tokens in advance, which are then verified or corrected by a larger target model. In…

Signal Processing · Electrical Eng. & Systems 2025-11-10 Ce Zheng , Tingting Yang

We propose LLMA, an LLM accelerator to losslessly speed up Large Language Model (LLM) inference with references. LLMA is motivated by the observation that there are abundant identical text spans between the decoding result by an LLM and the…

Computation and Language · Computer Science 2023-04-11 Nan Yang , Tao Ge , Liang Wang , Binxing Jiao , Daxin Jiang , Linjun Yang , Rangan Majumder , Furu Wei

Large language models (LLMs) have shown exceptional performance and vast potential across diverse tasks. However, the deployment of LLMs with high performance in low-resource environments has garnered significant attention in the industry.…

Artificial Intelligence · Computer Science 2024-07-11 Pujiang He , Shan Zhou , Wenhuan Huang , Changqing Li , Duyi Wang , Bin Guo , Chen Meng , Sheng Gui , Weifei Yu , Yi Xie

Speculative decoding (SD) is a widely adopted approach for accelerating inference in large language models (LLMs), particularly when the draft and target models are well aligned. However, state-of-the-art SD methods typically rely on…

Computation and Language · Computer Science 2026-02-12 Wei Zhong , Manasa Bharadwaj , Yixiao Wang , Yipeng Ji , Chul Lee

Recent advances in inference-time compute have significantly improved performance on complex tasks by generating long chains of thought (CoTs) using Large Reasoning Models (LRMs). However, this improved accuracy comes at the cost of high…

Machine Learning · Computer Science 2025-05-20 Rui Pan , Yinwei Dai , Zhihao Zhang , Gabriele Oliaro , Zhihao Jia , Ravi Netravali

Speculative Decoding has emerged as a popular technique for accelerating inference in Large Language Models. However, most existing approaches yield only modest improvements in production serving systems. Methods that achieve substantial…

Computation and Language · Computer Science 2026-01-08 Michele Marzollo , Jiawei Zhuang , Niklas Roemer , Niklas Zwingenberger , Lorenz K. Müller , Lukas Cavigelli

We present Cacheback Decoding, a training-free and model-agnostic speculative decoding method that exploits the locality in language to accelerate Large Language Model (LLM) inference. Cacheback leverages only Least Recently Used (LRU)…

Computation and Language · Computer Science 2025-12-01 Zhiyao Ma , In Gim , Lin Zhong

Large language models (LLMs) have demonstrated remarkable capabilities across various tasks. However, their widespread application is hindered by the resource-intensive decoding process. To address this challenge, current approaches have…

Computation and Language · Computer Science 2024-04-19 Ziqian Zeng , Jiahong Yu , Qianshi Pang , Zihao Wang , Huiping Zhuang , Hongen Shao , Xiaofeng Zou

Speculative decoding improves LLM inference by generating and verifying multiple tokens in parallel, but existing systems suffer from suboptimal performance due to a mismatch between dynamic speculation and static runtime assumptions. We…

Machine Learning · Computer Science 2026-01-01 Yue Guan , Changming Yu , Shihan Fang , Weiming Hu , Zaifeng Pan , Zheng Wang , Zihan Liu , Yangjie Zhou , Yufei Ding , Minyi Guo , Jingwen Leng

Large Language Model (LLM) inference on large-scale systems is expected to dominate future cloud infrastructures. Efficient LLM inference in cloud environments with numerous AI accelerators is challenging, necessitating extensive…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-11-11 Ilias Bournias , Lukas Cavigelli , Georgios Zacharopoulos

The Mixture-of-Experts (MoE) architecture has emerged as a promising approach to mitigate the rising computational costs of large language models (LLMs) by selectively activating parameters. However, its high memory requirements and…

Artificial Intelligence · Computer Science 2026-04-14 Jehyeon Bang , Eunyeong Cho , Ranggi Hwang , Jinha Chung , Minsoo Rhu

Speculative decoding (SD) is a promising method for accelerating the decoding process of Large Language Models (LLMs). The efficiency of SD primarily hinges on the consistency between the draft model and the verify model. However, existing…

Computation and Language · Computer Science 2025-06-02 Longze Chen , Renke Shan , Huiming Wang , Lu Wang , Ziqiang Liu , Run Luo , Jiawei Wang , Hamid Alinejad-Rokny , Min Yang

Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor…

Machine Learning · Computer Science 2025-03-14 Shaobo Ma , Chao Fang , Haikuo Shao , Zhongfeng Wang

Vision-Language Models (VLMs) excel at visual reasoning but still struggle with integrating external knowledge. Retrieval-Augmented Generation (RAG) is a promising solution, but current methods remain inefficient and often fail to maintain…

Computer Vision and Pattern Recognition · Computer Science 2026-01-08 Gen Li , Peiyu Liu

We propose an acceleration scheme for large language models (LLMs) through Speculative Decoding with Semantic Adaptive Tokens (SDSAT). The primary objective of this design is to enhance the LLM model's ability to generate draft tokens more…

Computation and Language · Computer Science 2024-04-02 Chengbo Liu , Yong Zhu