Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on
Long-Context Tasks

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks

11 July 2024

Papers citing "Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks"

12 / 12 papers shown

Title
Sparse Attention Remapping with Clustering for Efficient LLM Decoding on PIM Zehao Fan Garrett Gagnon Zhenyu Liu Liu Liu 29 0 0 09 May 2025
FreqKV: Frequency Domain Key-Value Compression for Efficient Context Window Extension Jushi Kai Boyi Zeng Yue Wang Haoli Bai Bo Jiang Bo Jiang Zhouhan Lin 42 0 0 01 May 2025
Cognitive Memory in Large Language Models Lianlei Shan Shixian Luo Zezhou Zhu Yu Yuan Yong Wu LLMAG KELM 163 1 0 03 Apr 2025
X-EcoMLA: Upcycling Pre-Trained Attention into MLA for Efficient and Extreme KV Compression Guihong Li Mehdi Rezagholizadeh Mingyu Yang Vikram Appia Emad Barsoum VLM 60 0 0 14 Mar 2025
TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection Wei Yu Wu Zhuoshi Pan Chao Wang L. Chen Y. Bai Kun Fu Zehua Wang Hui Xiong Hui Xiong LLMAG 36 5 0 05 Nov 2024
MatryoshkaKV: Adaptive KV Compression via Trainable Orthogonal Projection Bokai Lin Zihao Zeng Zipeng Xiao Siqi Kou Tianqi Hou Xiaofeng Gao Hao Zhang Zhijie Deng 16 2 0 16 Oct 2024
TurboRAG: Accelerating Retrieval-Augmented Generation with Precomputed KV Caches for Chunked Text Songshuo Lu Hua Wang Yutian Rong Zhi Chen Yaohua Tang VLM 31 14 0 10 Oct 2024
House of Cards: Massive Weights in LLMs Jaehoon Oh Seungjun Shin Dokwan Oh 37 1 0 02 Oct 2024
Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibration Zhongzhi Yu Zheng Wang Yonggan Fu Huihong Shi Khalid Shaikh Yingyan Celine Lin 49 20 0 22 Jun 2024
D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models Zhongwei Wan Xinjian Wu Yu Zhang Yi Xin Chaofan Tao ... Xin Wang Siqi Luo Jing Xiong Mi Zhang Mi Zhang 29 0 0 18 Jun 2024
No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization J. Yang Byeongwook Kim Jeongin Bae Beomseok Kwon Gunho Park Eunho Yang S. Kwon Dongsoo Lee MQ 39 45 0 28 Feb 2024
FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU Ying Sheng Lianmin Zheng Binhang Yuan Zhuohan Li Max Ryabinin ... Joseph E. Gonzalez Percy Liang Christopher Ré Ion Stoica Ce Zhang 149 369 0 13 Mar 2023