Cover Image

Taming the Fragility of KV Cache Eviction in LLM Inference

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Feng, Yuan, Guo, Haoyu, Lv, JunLin, Zhou, S. Kevin, Xie, Xike
Format:	Preprint
Published:	2025
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

CriticalKV: Optimizing KV Cache Eviction from an Output Perturbation Perspective
by: Feng, Yuan, et al.
Published: (2025)

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
by: Feng, Yuan, et al.
Published: (2024)

Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
by: Mai, Tho, et al.
Published: (2026)

IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference
by: Yang, Xintong, et al.
Published: (2026)

MadaKV: Adaptive Modality-Perception KV Cache Eviction for Efficient Multimodal Long-Context Inference
by: Li, Kunxi, et al.
Published: (2025)

CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences
by: Qin, Ziran, et al.
Published: (2025)

G-KV: Decoding-Time KV Cache Eviction with Global Attention
by: Liao, Mengqi, et al.
Published: (2025)

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models
by: Gu, Yifeng, et al.
Published: (2025)

NACL: A General and Effective KV Cache Eviction Framework for LLMs at Inference Time
by: Chen, Yilong, et al.
Published: (2024)

In-context KV-Cache Eviction for LLMs via Attention-Gate
by: Zeng, Zihao, et al.
Published: (2024)

LKV: End-to-End Learning of Head-wise Budgets and Token Selection for LLM KV Cache Eviction
by: Zhou, Enshuai, et al.
Published: (2026)

GraphKV: Breaking the Static Selection Paradigm with Graph-Based KV Cache Eviction
by: Li, Xuelin, et al.
Published: (2025)

Fast KVzip: Efficient and Accurate LLM Inference with Gated KV Eviction
by: Kim, Jang-Hyun, et al.
Published: (2026)

FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
by: Liu, Guangda, et al.
Published: (2025)

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

DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
by: Guo, Jinyu, et al.
Published: (2026)

ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
by: Dong, Zican, et al.
Published: (2026)

RetentiveKV: State-Space Memory for Uncertainty-Aware Multimodal KV Cache Eviction
by: Liu, Sihao, et al.
Published: (2026)

Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query
by: Wang, Yixuan, et al.
Published: (2025)

ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing
by: An, Yongqi, et al.
Published: (2026)

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

Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction
by: Liu, Yijun, et al.
Published: (2025)

Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
by: Huang, Jianuo, et al.
Published: (2025)

SkewRoute: Training-Free LLM Routing for Knowledge Graph Retrieval-Augmented Generation via Score Skewness of Retrieved Context
by: Wang, Hairu, et al.
Published: (2025)

Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation
by: Wang, Hairu, et al.
Published: (2025)

Efficient Long-Context LLM Inference via KV Cache Clustering
by: Hu, Jie, et al.
Published: (2025)

Sparse-dLLM: Accelerating Diffusion LLMs with Dynamic Cache Eviction
by: Song, Yuerong, et al.
Published: (2025)

LLMs Know What to Drop: Self-Attention Guided KV Cache Eviction for Efficient Long-Context Inference
by: Wang, Guangtao, et al.
Published: (2025)

LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning
by: Zhang, Haoyue, et al.
Published: (2025)

KeepKV: Achieving Periodic Lossless KV Cache Compression for Efficient LLM Inference
by: Tian, Yuxuan, et al.
Published: (2025)

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

CAOTE: KV Cache Selection for LLMs via Attention Output Error-Based Token Eviction
by: Goel, Raghavv, et al.
Published: (2025)

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference
by: Lin, Jian, et al.
Published: (2026)

Mitigating KV Cache Competition to Enhance User Experience in LLM Inference
by: Shen, Haiying, et al.
Published: (2025)

ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference
by: Sun, Hanshi, et al.
Published: (2024)

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference
by: Dehghanighobadi, Zahra, et al.
Published: (2026)

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

HeteroCache: A Dynamic Retrieval Approach to Heterogeneous KV Cache Compression for Long-Context LLM Inference
by: Shi, Zhiyuan, et al.
Published: (2026)

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

SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching
by: Zhu, Yuxuan, et al.
Published: (2025)