Cover Image

KVSink: Understanding and Enhancing the Preservation of Attention Sinks in KV Cache Quantization for LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Su, Zunhai, Yuan, Kehong
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

AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models
by: Su, Zunhai, et al.
Published: (2025)

RotateKV: Accurate and Robust 2-Bit KV Cache Quantization for LLMs via Outlier-Aware Adaptive Rotations
by: Su, Zunhai, et al.
Published: (2025)

Accurate KV Cache Quantization with Outlier Tokens Tracing
by: Su, Yi, et al.
Published: (2025)

Beyond KV Caching: Shared Attention for Efficient LLMs
by: Liao, Bingli, et al.
Published: (2024)

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

PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs
by: Liu, Tengxuan, et al.
Published: (2025)

QAQ: Quality Adaptive Quantization for LLM KV Cache
by: Dong, Shichen, et al.
Published: (2024)

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

Beyond Homogeneous Attention: Memory-Efficient LLMs via Fourier-Approximated KV Cache
by: Liu, Xiaoran, et al.
Published: (2025)

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
by: Chen, Han, et al.
Published: (2025)

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

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

SQuat: Subspace-orthogonal KV Cache Quantization
by: Wang, Hao, et al.
Published: (2025)

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

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

Quantization Dominates Rank Reduction for KV-Cache Compression
by: Salfati, Samuel
Published: (2026)

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

KV Cache Steering for Controlling Frozen LLMs
by: Belitsky, Max, et al.
Published: (2025)

HCAttention: Extreme KV Cache Compression via Heterogeneous Attention Computing for LLMs
by: Yang, Dongquan, et al.
Published: (2025)

Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
by: Lin, Hongzhan, et al.
Published: (2025)

Task-KV: Task-aware KV Cache Optimization via Semantic Differentiation of Attention Heads
by: He, Xingyang, et al.
Published: (2025)

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

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
by: Liu, Zirui, et al.
Published: (2024)

Unveiling Super Experts in Mixture-of-Experts Large Language Models
by: Su, Zunhai, et al.
Published: (2025)

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

Compressing KV Cache for Long-Context LLM Inference with Inter-Layer Attention Similarity
by: Ma, Da, et al.
Published: (2024)

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

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

WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language Models
by: Yuan, Jian, et al.
Published: (2025)

XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression
by: Yang, Haoqi, et al.
Published: (2025)

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

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

CTkvr: KV Cache Retrieval for Long-Context LLMs via Centroid then Token Indexing
by: Lu, Kuan, et al.
Published: (2025)

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

Eigen Attention: Attention in Low-Rank Space for KV Cache Compression
by: Saxena, Utkarsh, et al.
Published: (2024)

ParisKV: Fast and Drift-Robust KV-Cache Retrieval for Long-Context LLMs
by: Qi, Yanlin, et al.
Published: (2026)

QJL: 1-Bit Quantized JL Transform for KV Cache Quantization with Zero Overhead
by: Zandieh, Amir, et al.
Published: (2024)

Understanding the Physics of Key-Value Cache Compression for LLMs through Attention Dynamics
by: Ananthanarayanan, Samhruth, et al.
Published: (2026)

dKV-Cache: The Cache for Diffusion Language Models
by: Ma, Xinyin, et al.
Published: (2025)

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