English
Related papers

Related papers: Finch: Prompt-guided Key-Value Cache Compression

200 papers

Modern Large Language Models (LLMs) are increasingly trained to support very large context windows. We present Compactor, a training-free, query-agnostic KV compression strategy that uses approximate leverage scores to determine token…

Computation and Language · Computer Science 2025-12-10 Vivek Chari , Benjamin Van Durme

Providing extensive context via prompting is vital for leveraging the capabilities of Large Language Models (LLMs). However, lengthy contexts significantly increase inference latency, as the computational cost of self-attention grows…

Artificial Intelligence · Computer Science 2026-02-17 Guojie Liu , Yiqi Wang , Yanfeng Yang , Wenqi Fan , Songlei Jian , Jianfeng Zhang , Jie Yu

Large language models (LLMs) increasingly rely on long-context modeling for tasks such as document understanding, code analysis, and multi-step reasoning. However, scaling context windows to the million-token level brings prohibitive…

Computer Vision and Pattern Recognition · Computer Science 2025-10-22 Jiale Cheng , Yusen Liu , Xinyu Zhang , Yulin Fei , Wenyi Hong , Ruiliang Lyu , Weihan Wang , Zhe Su , Xiaotao Gu , Xiao Liu , Yushi Bai , Jie Tang , Hongning Wang , Minlie Huang

The transformer's context window is vital for tasks such as few-shot learning and conditional generation as it preserves previous tokens for active memory. However, as the context lengths increase, the computational costs grow…

Computation and Language · Computer Science 2025-04-01 Jeffrey Willette , Heejun Lee , Youngwan Lee , Myeongjae Jeon , Sung Ju Hwang

With context windows of millions of tokens, Long-Context Language Models (LCLMs) can encode entire document collections, offering a strong alternative to conventional retrieval-augmented generation (RAG). However, it remains unclear whether…

Computation and Language · Computer Science 2026-01-27 Francesco Maria Molfese , Momchil Hardalov , Rexhina Blloshmi , Bill Byrne , Adrià de Gispert

Large Language Models (LLMs) face significant computational challenges when processing long contexts due to the quadratic complexity of self-attention. While soft context compression methods, which map input text to smaller latent…

Computation and Language · Computer Science 2025-09-24 Gabriele Berton , Jayakrishnan Unnikrishnan , Son Tran , Mubarak Shah

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key…

Computation and Language · Computer Science 2025-03-28 Youhui Zuo , Sibo Wei , Chen Zhang , Zhuorui Liu , Wenpeng Lu , Dawei Song

We present Prompt Cache, an approach for accelerating inference for large language models (LLM) by reusing attention states across different LLM prompts. Many input prompts have overlapping text segments, such as system messages, prompt…

Computation and Language · Computer Science 2024-04-26 In Gim , Guojun Chen , Seung-seob Lee , Nikhil Sarda , Anurag Khandelwal , Lin Zhong

Large Language Models (LLMs) require significant GPU memory when processing long texts, with the key value (KV) cache consuming up to 70\% of total memory during inference. Although existing compression methods reduce memory by evaluating…

Computation and Language · Computer Science 2025-10-15 Xiang Liu , Zhenheng Tang , Peijie Dong , Zeyu Li , Yue Liu , Bo Li , Xuming Hu , Xiaowen Chu

Long-context language modeling is increasingly constrained by the Key-Value (KV) cache, whose memory and decode-time access costs scale linearly with the prefix length. This bottleneck has motivated a range of context-compression methods,…

Machine Learning · Computer Science 2026-05-13 Yoav Gelberg , Yam Eitan , Michael Bronstein , Yarin Gal , Haggai Maron

Large Language Models (LLMs) are increasingly expected to operate over long contexts, yet standard softmax attention incurs a KV cache that grows linearly with sequence length, quickly becoming the bottleneck for long context inference. A…

Computation and Language · Computer Science 2026-05-26 Xintong Yang , Hao Gu , Binxing Xu , Lujun Li , Bei Liu , Jiacheng Liu , Qiyuan Zhu , Sirui Han , Yike Guo

As the context length of current large language models (LLMs) rapidly increases, the memory demand for the Key-Value (KV) cache is becoming a bottleneck for LLM deployment and batch processing. Traditional KV cache compression methods…

Computation and Language · Computer Science 2025-12-23 Aomufei Yuan , Zhiming Wang , Ruijie Miao , Dayu Wang , Yuxuan Tian , Zihan Wang , Yebo Peng , Yuhan Wu , Bairen Yi , Xin Liu , Tong Yang

Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform compression across both prefill and decoding caches, but compressing the prefill cache…

Artificial Intelligence · Computer Science 2026-05-29 Soumyadeep Jana , Sagar Nishad , Sanasam Ranbir Singh

Large language models (LLMs) have triggered a new stream of research focusing on compressing the context length to reduce the computational cost while ensuring the retention of helpful information for LLMs to answer the given question.…

Computation and Language · Computer Science 2024-12-20 Barys Liskavets , Maxim Ushakov , Shuvendu Roy , Mark Klibanov , Ali Etemad , Shane Luke

Huge memory consumption has been a major bottleneck for deploying high-throughput large language models in real-world applications. In addition to the large number of parameters, the key-value (KV) cache for the attention mechanism in the…

Computation and Language · Computer Science 2024-06-05 Haoyi Wu , Kewei Tu

Efficiently handling long contexts in transformer-based language models with low perplexity is an active area of research. Numerous recent approaches like Linformer, Longformer, Performer, and Structured state space models (SSMs)., have not…

Machine Learning · Computer Science 2025-04-22 Sushant Singh , Ausif Mahmood

Repository-level code intelligence tasks require large language models (LLMs) to process long, multi-file contexts. Such inputs introduce three challenges: crucial context can be obscured by noise, truncated due to limited windows, and…

Software Engineering · Computer Science 2026-04-16 Jia Feng , Zhanyue Qin , Cuiyun Gao , Ruiqi Wang , Chaozheng Wang , Yingwei Ma , Xiaoyuan Xie

In-context learning (ICL) capabilities are foundational to the success of large language models (LLMs). Recently, context compression has attracted growing interest since it can largely reduce reasoning complexities and computation costs of…

Computation and Language · Computer Science 2024-08-02 Wenshan Wang , Yihang Wang , Yixing Fan , Huaming Liao , Jiafeng Guo

Large Language Models (LLMs), epitomized by ChatGPT's release in late 2022, have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture's…

Computation and Language · Computer Science 2024-11-21 Luohe Shi , Hongyi Zhang , Yao Yao , Zuchao Li , Hai Zhao

Large language models (LLMs) often incorporate multiple text chunks in their inputs to provide the necessary contexts. To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when…

Machine Learning · Computer Science 2025-04-07 Jiayi Yao , Hanchen Li , Yuhan Liu , Siddhant Ray , Yihua Cheng , Qizheng Zhang , Kuntai Du , Shan Lu , Junchen Jiang