Cover Image

LazyEviction: Lagged KV Eviction with Attention Pattern Observation for Efficient Long Reasoning

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Haoyue, Zhang, Hualei, Ma, Xiaosong, Zhang, Jie, Guo, Song
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

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

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

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

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

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

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

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

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

Alleviating Forgetfulness of Linear Attention by Hybrid Sparse Attention and Contextualized Learnable Token Eviction
by: He, Mutian, et al.
Published: (2025)

HashEvict: A Pre-Attention KV Cache Eviction Strategy using Locality-Sensitive Hashing
by: Liu, Minghui, et al.
Published: (2024)

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

ToFe: Lagged Token Freezing and Reusing for Efficient Vision Transformer Inference
by: Zhang, Haoyue, et al.
Published: (2025)

Hierarchical Adaptive Eviction for KV Cache Management in Multimodal Language Models
by: Ma, Xindian, et al.
Published: (2026)

Taming the Fragility of KV Cache Eviction in LLM Inference
by: Feng, Yuan, et al.
Published: (2025)

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

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

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

MomentKV: Closing the Directional Gap in KV Cache Eviction for Long-Context Inference
by: Li, Yu, et al.
Published: (2026)

LAVa: Layer-wise KV Cache Eviction with Dynamic Budget Allocation
by: Shen, Yiqun, et al.
Published: (2025)

EVICPRESS: Joint KV-Cache Compression and Eviction for Efficient LLM Serving
by: Feng, Shaoting, et al.
Published: (2025)

RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache
by: Zhang, Junkai, et al.
Published: (2026)

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

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

Protection Is (Nearly) All You Need: Structural Protection Dominates Scoring in Globally Capped KV Eviction
by: Garcia, Gabriel
Published: (2026)

CAKE: Cascading and Adaptive KV Cache Eviction with Layer Preferences
by: Qin, Ziran, 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)

AttentionPredictor: Temporal Patterns Matter for KV Cache Compression
by: Yang, Qingyue, et al.
Published: (2025)

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

CONF-KV: Confidence-Aware KV Cache Eviction with Mixed-Precision Storage for Long-Horizon LLM
by: Li, Yubo, et al.
Published: (2026)

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

Beyond Token Eviction: Mixed-Dimension Budget Allocation for Efficient KV Cache Compression
by: Miao, Ruijie, et al.
Published: (2026)

PagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
by: Chitty-Venkata, Krishna Teja, et al.
Published: (2025)

Make Each Token Count: Towards Improving Long-Context Performance with KV Cache Eviction
by: Bui, Ngoc, et al.
Published: (2026)

Active Geospatial Search for Efficient Tenant Eviction Outreach
by: Sarkar, Anindya, et al.
Published: (2024)

A Simple Plug-in for Improving Eviction-Based KV Cache Compression
by: Lin, Yuping, et al.
Published: (2026)

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

LookaheadKV: Fast and Accurate KV Cache Eviction by Glimpsing into the Future without Generation
by: Ahn, Jinwoo, et al.
Published: (2026)

Sparse Attention across Multiple-context KV Cache
by: Cao, Ziyi, et al.
Published: (2025)

Multipole Attention for Efficient Long Context Reasoning
by: Hooper, Coleman, et al.
Published: (2025)