Cover Image

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Ge, Suyu, Zhang, Yunan, Liu, Liyuan, Zhang, Minjia, Han, Jiawei, Gao, Jianfeng
Format:	Preprint
Published:	2023
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Model Tells You Where to Merge: Adaptive KV Cache Merging for LLMs on Long-Context Tasks
by: Wang, Zheng, et al.
Published: (2024)

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
by: Zhou, Xiabin, et al.
Published: (2024)

LoRC: Low-Rank Compression for LLMs KV Cache with a Progressive Compression Strategy
by: Zhang, Rongzhi, et al.
Published: (2024)

A Little Goes a Long Way: Efficient Long Context Training and Inference with Partial Contexts
by: Ge, Suyu, et al.
Published: (2024)

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
by: Zhang, Qingru, et al.
Published: (2023)

SABlock: Semantic-Aware KV Cache Eviction with Adaptive Compression Block Size
by: Chen, Jinhan, et al.
Published: (2025)

MiniKV: Pushing the Limits of LLM Inference via 2-Bit Layer-Discriminative KV Cache
by: Sharma, Akshat, et al.
Published: (2024)

KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
by: Chen, Jian, et al.
Published: (2026)

PyramidInfer: Pyramid KV Cache Compression for High-throughput LLM Inference
by: Yang, Dongjie, et al.
Published: (2024)

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
by: Cai, Zefan, et al.
Published: (2024)

NestedKV: Nested Memory Routing for Long-Context KV Cache Compression
by: Chen, Hong, et al.
Published: (2026)

ZigZagkv: Dynamic KV Cache Compression for Long-context Modeling based on Layer Uncertainty
by: Zhong, Meizhi, et al.
Published: (2024)

Lossless KV Cache Compression to 2%
by: Yang, Zhen, et al.
Published: (2024)

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
by: Cai, Zefan, et al.
Published: (2025)

LagKV: Lag-Relative Information of the KV Cache Tells Which Tokens Are Important
by: Liang, Manlai, et al.
Published: (2025)

CaliDrop: KV Cache Compression with Calibration
by: Su, Yi, et al.
Published: (2025)

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
by: Peng, Junjie, et al.
Published: (2026)

Attention Is All You Need for KV Cache in Diffusion LLMs
by: Nguyen-Tri, Quan, et al.
Published: (2025)

LongFlow: Efficient KV Cache Compression for Reasoning Models
by: Su, Yi, et al.
Published: (2026)

KV-Compress: Paged KV-Cache Compression with Variable Compression Rates per Attention Head
by: Rehg, Isaac
Published: (2024)

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
by: Ji, Shiyu, et al.
Published: (2026)

SurfaceLogicKV: Surface and Logic Attention Behaviors are All You Need for Robust KV Cache Compression
by: Li, Mengjie, et al.
Published: (2025)

ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs
by: Liu, Xin, et al.
Published: (2025)

MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
by: Liu, Akide, et al.
Published: (2024)

TaDA: Training-free recipe for Decoding with Adaptive KV Cache Compression and Mean-centering
by: Joshi, Vinay, et al.
Published: (2025)

DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity
by: Hao, Jitai, et al.
Published: (2026)

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
by: Liu, Xiang, et al.
Published: (2025)

Where Matters More Than What: Decoding-aligned KV Cache Compression via Position-aware Pseudo Queries
by: Tian, Zhenxu, et al.
Published: (2026)

WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference
by: Zuo, Youhui, et al.
Published: (2025)

EvolKV: Evolutionary KV Cache Compression for LLM Inference
by: Yu, Bohan, et al.
Published: (2025)

Hold Onto That Thought: Assessing KV Cache Compression On Reasoning
by: Liu, Minghui, et al.
Published: (2025)

Model Tells Itself Where to Attend: Faithfulness Meets Automatic Attention Steering
by: Zhang, Qingru, et al.
Published: (2024)

A Method for Building Large Language Models with Predefined KV Cache Capacity
by: Yi, Zhonghua, et al.
Published: (2024)

KVSculpt: KV Cache Compression as Distillation
by: Jiang, Bo, et al.
Published: (2026)

One Size Does Not Fit All: Token-Wise Adaptive Compression for KV Cache
by: Lu, Liming, et al.
Published: (2026)

Unlocking Data-free Low-bit Quantization with Matrix Decomposition for KV Cache Compression
by: Liu, Peiyu, et al.
Published: (2024)

Which Heads Matter for Reasoning? RL-Guided KV Cache Compression
by: Du, Wenjie, et al.
Published: (2025)

EFIM: Efficient Serving of LLMs for Infilling Tasks with Improved KV Cache Reuse
by: Guo, Tianyu, et al.
Published: (2025)

CommVQ: Commutative Vector Quantization for KV Cache Compression
by: Li, Junyan, et al.
Published: (2025)

Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques
by: Javidnia, Neusha, et al.
Published: (2025)