English
Related papers

Related papers: Prefixing Attention Sinks can Mitigate Activation …

200 papers

Sparse attention mechanisms aim to reduce computational overhead with minimal accuracy loss by selectively processing salient tokens. Despite their effectiveness, most methods merely exploit a model's inherent sparsity and thus plateau at…

Machine Learning · Computer Science 2026-03-02 Feng Chen , Yefei He , Lequan Lin , Chenhui Gou , Jing Liu , Bohan Zhuang , Qi Wu

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across a wide array of text-centric tasks. However, their `large' scale introduces significant computational and storage challenges, particularly in…

Computation and Language · Computer Science 2024-07-03 Chaoran Zhang , Lixin Zou , Dan Luo , Min Tang , Xiangyang Luo , Zihao Li , Chenliang Li

Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and activations to minimize quantization error with equally…

Computation and Language · Computer Science 2025-08-12 Yuxuan Sun , Ruikang Liu , Haoli Bai , Han Bao , Kang Zhao , Yuening Li , Jiaxin Hu , Xianzhi Yu , Lu Hou , Chun Yuan , Xin Jiang , Wulong Liu , Jun Yao

Large language models (LLMs) face significant challenges in processing long contexts due to the linear growth of the key-value (KV) cache and quadratic complexity of self-attention. Existing approaches address these bottlenecks separately:…

Computation and Language · Computer Science 2026-04-17 Zeng You , Yaofo Chen , Qiuwu Chen , Ying Sun , Shuhai Zhang , Yingjian Li , Yaowei Wang , Mingkui Tan

Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV…

Operating Systems · Computer Science 2026-01-21 Jing Zou , Shangyu Wu , Hancong Duan , Qiao Li , Chun Jason Xue

Large Language Models (LLMs) excel across a variety of language tasks yet are constrained by limited input lengths and high computational costs. Existing approaches\textemdash such as relative positional encodings (e.g., RoPE, ALiBi) and…

Computation and Language · Computer Science 2025-02-18 Kun-Hui Lee , Eunhwan Park , Donghoon Han , Seung-Hoon Na

Integrating large language models (LLMs) as priors in reinforcement learning (RL) offers significant advantages but comes with substantial computational costs. We present a principled cache-efficient framework for posterior sampling with…

Machine Learning · Computer Science 2025-09-30 Ibne Farabi Shihab , Sanjeda Akter , Anuj Sharma

With the growing size of large language models, the role of quantization becomes increasingly significant. However, outliers present in weights or activations notably influence the performance of quantized models. Recently,…

Computation and Language · Computer Science 2024-02-20 Baohao Liao , Christof Monz

Quantization stands as a pivotal technique for large language model (LLM) serving, yet it poses significant challenges particularly in achieving effective low-bit quantization. The limited numerical mapping makes the quantized model produce…

Machine Learning · Computer Science 2024-12-13 Weibo Zhao , Yubin Shi , Xinyu Lyu , Wanchen Sui , Shen Li , Yong Li

Efficient deployment of Large Language Models (LLMs) requires batching multiple requests together to improve throughput. As the batch size, context length, or model size increases, the size of the key and value (KV) cache can quickly become…

Machine Learning · Computer Science 2024-05-08 Tianyi Zhang , Jonah Yi , Zhaozhuo Xu , Anshumali Shrivastava

Diffusion transformers have gained substantial interest in diffusion generative modeling due to their outstanding performance. However, their computational demands, particularly the quadratic complexity of attention mechanisms and…

Machine Learning · Computer Science 2026-01-28 Jinming Lou , Wenyang Luo , Yufan Liu , Bing Li , Xinmiao Ding , Weiming Hu , Yuming Li , Chenguang Ma

Large Language Models (LLMs) are transforming recommendation from ranking into a generative task, but industrial deployment remains limited by the high latency of processing long, personalized prompts. Standard prefix caching provides…

Distributed, Parallel, and Cluster Computing · Computer Science 2026-05-11 Zhan Zhao , Yuxin Wang , Amelie Chi Zhou

Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among numerous works that have been proposed in recent years, layer-wise token pruning approaches,…

Computation and Language · Computer Science 2026-04-17 Rei Taniguchi , Yuyang Dong , Makoto Onizuka , Chuan Xiao

Quantizing large language models (LLMs) to 1-bit precision significantly reduces computational costs, but existing quantization techniques suffer from noticeable performance degradation when using weight and activation precisions below 4…

Machine Learning · Computer Science 2025-07-01 Siqing Song , Chuang Wang , Ruiqi Wang , Yi Yang , Xu-Yao Zhang

Quantization is pivotal for mitigating the significant memory and computational overhead of Large Language Models (LLMs). While emerging transformation-based methods have successfully enhanced quantization by projecting feature spaces onto…

Computation and Language · Computer Science 2026-03-06 Xiaohao Liu , Xiaobo Xia , Manyi Zhang , Ji-Fu Li , Xianzhi Yu , Fei Shen , Xiu Su , See-Kiong Ng , Tat-Seng Chua

The quadratic complexity of attention remains the central bottleneck in long-context inference for large language models. Prior acceleration methods either sparsify the attention map with structured patterns or permanently evict tokens at…

Computation and Language · Computer Science 2026-05-04 Dongwon Jo , Beomseok Kang , Jiwon Song , Jae-Joon Kim

Inference on large language models (LLMs) can be expensive in terms of the compute and memory costs involved, especially when long sequence lengths are used. In particular, the self-attention mechanism used in LLM inference contributes…

Machine Learning · Computer Science 2024-11-11 Prajwal Singhania , Siddharth Singh , Shwai He , Soheil Feizi , Abhinav Bhatele

Large Language Models struggle with memory demands from the growing Key-Value (KV) cache as context lengths increase. Existing compression methods homogenize head dimensions or rely on attention-guided token pruning, often sacrificing…

Computation and Language · Computer Science 2025-06-16 Xiaoran Liu , Siyang He , Qiqi Wang , Ruixiao Li , Yuerong Song , Zhigeng Liu , Linlin Li , Qun Liu , Zengfeng Huang , Qipeng Guo , Ziwei He , Xipeng Qiu

Recently, large language models (LLM) based on transformers are facing memory bottleneck issues due to KV cache, especially in long sequence handling. Previous researches proposed KV cache compression techniques that identify insignificant…

Computation and Language · Computer Science 2024-08-01 Hyun-rae Jo , Dongkun Shin

Large Language Models (LLMs) have demonstrated remarkable capabilities. However, their massive parameter scale leads to significant resource consumption and latency during inference. Post-training weight-only quantization offers a promising…

Machine Learning · Computer Science 2026-05-12 Zhikai Li , Zhen Dong , Xuewen Liu , Jing Zhang , Qingyi Gu