Cover Image

More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Zhang, Jiebin, Zhu, Dawei, Song, Yifan, Wu, Wenhao, Kuang, Chuqiao, Li, Xiaoguang, Shang, Lifeng, Liu, Qun, Li, Sujian
Format:	Preprint
Published:	2024
Subjects:	Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

No Token Left Behind: Reliable KV Cache Compression via Importance-Aware Mixed Precision Quantization
by: Yang, June Yong, et al.
Published: (2024)

Hierarchical Memory Organization for Wikipedia Generation
by: Yu, Eugene J., et al.
Published: (2025)

Time and Memory Trade-off of KV-Cache Compression in Tensor Transformer Decoding
by: Chen, Yifang, et al.
Published: (2025)

KVCompose: Efficient Structured KV Cache Compression with Composite Tokens
by: Akulov, Dmitry, et al.
Published: (2025)

LightVLM: Acceleraing Large Multimodal Models with Pyramid Token Merging and KV Cache Compression
by: Hu, Lianyu, et al.
Published: (2025)

UIS-Digger: Towards Comprehensive Research Agent Systems for Real-world Unindexed Information Seeking
by: Liu, Chang, et al.
Published: (2026)

AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization
by: Tan, Yifan, et al.
Published: (2024)

KVReviver: Reversible KV Cache Compression with Sketch-Based Token Reconstruction
by: Yuan, Aomufei, et al.
Published: (2025)

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

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

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

CoUDA: Coherence Evaluation via Unified Data Augmentation
by: Zhu, Dawei, et al.
Published: (2024)

WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario
by: Zhang, Jiebin, et al.
Published: (2024)

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

Meta-Soft: Leveraging Composable Meta-Tokens for Context-Preserving KV Cache Compression
by: Luo, Wei, et al.
Published: (2026)

DocPuzzle: A Process-Aware Benchmark for Evaluating Realistic Long-Context Reasoning Capabilities
by: Zhuang, Tianyi, et al.
Published: (2025)

KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache
by: Li, Fei, et al.
Published: (2025)

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

TriAxialKV: Toward Extreme Low-Precision KV-Cache Quantization for Agentic Inference Tasks
by: Shen, Hanzhang, et al.
Published: (2026)

ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
by: He, Yefei, et al.
Published: (2024)

Cache What Lasts: Token Retention for Memory-Bounded KV Cache in LLMs
by: Bui, Ngoc, et al.
Published: (2025)

CommonKV: Compressing KV Cache with Cross-layer Parameter Sharing
by: Wang, Yixuan, et al.
Published: (2025)

Tokenization Is More Than Compression
by: Schmidt, Craig W., et al.
Published: (2024)

AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories
by: Song, Yifan, et al.
Published: (2024)

LongEmbed: Extending Embedding Models for Long Context Retrieval
by: Zhu, Dawei, et al.
Published: (2024)

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
by: Zhu, Dawei, et al.
Published: (2023)

EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
by: Cheong, Minsoo, et al.
Published: (2026)

RateQuant: Optimal Mixed-Precision KV Cache Quantization via Rate-Distortion Theory
by: Zuo, Fei, et al.
Published: (2026)

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

LongAttn: Selecting Long-context Training Data via Token-level Attention
by: Wu, Longyun, et al.
Published: (2025)

Lost in Tokenization: Fundamental Trade-offs in Graph Tokenization for Transformers
by: Bechler-Speicher, Maya, et al.
Published: (2026)

HySparse: A Hybrid Sparse Attention Architecture with Oracle Token Selection and KV Cache Sharing
by: Gao, Yizhao, et al.
Published: (2026)

PreciseCache: Precise Feature Caching for Efficient and High-fidelity Video Generation
by: Wang, Jiangshan, et al.
Published: (2026)

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

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

CaliDrop: KV Cache Compression with Calibration
by: Su, Yi, 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)

Knowledge Packs: Zero-Token Knowledge Delivery via KV Cache Injection
by: Pustovit, Andrey
Published: (2026)

CompressKV: Semantic Retrieval Heads Know What Tokens are Not Important Before Generation
by: Lin, Xiaolin, et al.
Published: (2025)

The Pitfalls of KV Cache Compression
by: Chen, Alex, et al.
Published: (2025)