English
Related papers

Related papers: Prefixing Attention Sinks can Mitigate Activation …

200 papers

Large language models (LLMs) have demonstrated state-of-the-art performance across various tasks. However, the latency of inference and the large GPU memory consumption of LLMs restrict their deployment performance. Recently, there have…

Machine Learning · Computer Science 2024-02-29 Yi Zhang , Fei Yang , Shuang Peng , Fangyu Wang , Aimin Pan

As large language models (LLMs) improve their capabilities in handling complex tasks, the issues of computational cost and efficiency due to long prompts are becoming increasingly prominent. To accelerate model inference and reduce costs,…

Computation and Language · Computer Science 2024-09-04 Xuechen Liang , Meiling Tao , Yinghui Xia , Tianyu Shi , Jun Wang , JingSong Yang

Large language models (LLMs) have recently attracted considerable interest for their ability to perform complex reasoning tasks, such as chain-of-thought (CoT) reasoning. However, most of the existing approaches to enhance this ability rely…

Computation and Language · Computer Science 2024-08-08 Xinyi Wang , Lucas Caccia , Oleksiy Ostapenko , Xingdi Yuan , William Yang Wang , Alessandro Sordoni

With the expanding application of Large Language Models (LLMs) in various domains, it becomes imperative to comprehensively investigate their unforeseen behaviors and consequent outcomes. In this study, we introduce and systematically…

Computation and Language · Computer Science 2024-04-22 Yuxi Li , Yi Liu , Gelei Deng , Ying Zhang , Wenjia Song , Ling Shi , Kailong Wang , Yuekang Li , Yang Liu , Haoyu Wang

We investigate the origins of massive activations in large language models (LLMs) and identify a specific layer named the \textbf{Massive Emergence Layer (ME Layer)}, that is consistently observed across model families, where massive…

Computation and Language · Computer Science 2026-05-14 Zeru Shi , Zhenting Wang , Fan Yang , Qifan Wang , Ruixiang Tang

The inference of transformer-based large language models consists of two sequential stages: 1) a prefilling stage to compute the KV cache of prompts and generate the first token, and 2) a decoding stage to generate subsequent tokens. For…

Computation and Language · Computer Science 2024-07-22 Qichen Fu , Minsik Cho , Thomas Merth , Sachin Mehta , Mohammad Rastegari , Mahyar Najibi

Large language models (LLMs) have recently advanced auditory speech recognition (ASR), visual speech recognition (VSR), and audio-visual speech recognition (AVSR). However, understanding of their internal dynamics under fine-tuning remains…

Audio and Speech Processing · Electrical Eng. & Systems 2026-01-28 Anand , Umberto Cappellazzo , Stavros Petridis , Maja Pantic

Quantization is a proven effective method for compressing large language models. Although popular techniques like W8A8 and W4A16 effectively maintain model performance, they often fail to concurrently speed up the prefill and decoding…

Machine Learning · Computer Science 2024-08-01 Ying Zhang , Peng Zhang , Mincong Huang , Jingyang Xiang , Yujie Wang , Chao Wang , Yineng Zhang , Lei Yu , Chuan Liu , Wei Lin

Layer-wise quantization is a key technique for efficiently compressing large models without expensive retraining. Previous methods typically quantize the weights of each layer by "uniformly" optimizing the layer reconstruction loss across…

Machine Learning · Computer Science 2025-03-04 Yi-Lin Sung , Prateek Yadav , Jialu Li , Jaehong Yoon , Mohit Bansal

State-of-the-art language models (LMs) represented by long-short term memory recurrent neural networks (LSTM-RNNs) and Transformers are becoming increasingly complex and expensive for practical applications. Low-bit neural network…

Computation and Language · Computer Science 2021-12-22 Junhao Xu , Jianwei Yu , Shoukang Hu , Xunying Liu , Helen Meng

Large language models (LLMs) rely on key-value cache (KV cache) to accelerate decoding by reducing redundant computations. However, the KV cache memory usage grows substantially with longer text sequences, posing challenges for efficient…

Computation and Language · Computer Science 2025-11-18 Yixuan Wang , Shiyu Ji , Yijun Liu , Yuzhuang Xu , Yang Xu , Qingfu Zhu , Wanxiang Che

Large language models (LLMs) have shown remarkable performance in complex reasoning tasks, but their efficiency is hindered by the substantial memory and computational costs associated with generating lengthy tokens. In this paper, we…

Computation and Language · Computer Science 2025-09-24 Jintian Zhang , Yuqi Zhu , Mengshu Sun , Yujie Luo , Shuofei Qiao , Lun Du , Da Zheng , Huajun Chen , Ningyu Zhang

Large Language Models (LLMs) have made significant strides in natural language processing and generation, yet their ability to handle long-context input remains constrained by the quadratic complexity of attention computation and…

Computation and Language · Computer Science 2025-06-16 Manlai Liang , Wanyi Huang , Mandi Liu , Huaijun Li , Jinlong Li

Large Language Models (LLMs) rely on optimizations like Automatic Prefix Caching (APC) to accelerate inference. APC works by reusing previously computed states for the beginning part of a request (prefix), when another request starts with…

Cryptography and Security · Computer Science 2026-05-21 Panagiotis Georgios Pennas , Konstantinos Papaioannou , Marco Guarnieri , Thaleia Dimitra Doudali

The increasing size and complexity of large language models (LLMs) have raised significant challenges in deployment efficiency, particularly under resource constraints. Post-training quantization (PTQ) has emerged as a practical solution by…

Computation and Language · Computer Science 2026-04-07 Han Liu , Haotian Gao , Changya Li , Feng Zhang , Xiaotong Zhang , Wei Wang , Hong Yu

Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…

Computation and Language · Computer Science 2025-03-04 Jian Yuan , Ziwei He , Haoli Bai , Jingwen Leng , Bo Jiang

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token…

Software Engineering · Computer Science 2026-02-10 Viacheslav Siniaev , Iaroslav Chelombitko , Aleksey Komissarov

Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly…

Machine Learning · Computer Science 2025-05-23 Zhihang Cai , Xingjun Zhang , Zhendong Tan , Zheng Wei

The memory and computational demands of Key-Value (KV) cache present significant challenges for deploying long-context language models. Previous approaches attempt to mitigate this issue by selectively dropping tokens, which irreversibly…

Machine Learning · Computer Science 2024-07-24 Hanlin Tang , Yang Lin , Jing Lin , Qingsen Han , Shikuan Hong , Yiwu Yao , Gongyi Wang

Retrieval-Augmented Generation enhances Large Language Models by integrating external knowledge, which reduces hallucinations but increases prompt length. This increase leads to higher computational costs and longer Time to First Token…