Imagen de Portada

Dialogue Without Limits: Constant-Sized KV Caches for Extended Responses in LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ghadia, Ravi, Kumar, Avinash, Jain, Gaurav, Nair, Prashant, Das, Poulami
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

HiSpec: Hierarchical Speculative Decoding for LLMs
por: Kumar, Avinash, et al.
Publicado: (2025)

Keyformer: KV Cache Reduction through Key Tokens Selection for Efficient Generative Inference
por: Adnan, Muhammad, et al.
Publicado: (2024)

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

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

Crystal-KV: Efficient KV Cache Management for Chain-of-Thought LLMs via Answer-First Principle
por: Wang, Zihan, et al.
Publicado: (2026)

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

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

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

KV Cache Recycling to Expand Usable Context Capacity in Low Parameter LLMs
por: Pandey, Prashant
Publicado: (2025)

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

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

Stateful KV Cache Management for LLMs: Balancing Space, Time, Accuracy, and Positional Fidelity
por: Poudel, Pratik
Publicado: (2025)

OjaKV: Context-Aware Online Low-Rank KV Cache Compression
por: Zhu, Yuxuan, et al.
Publicado: (2025)

KV Cache Offloading for Context-Intensive Tasks
por: Bocharnikov, Andrey, et al.
Publicado: (2026)

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

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

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

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

ManifoldKV: Training-Free KV Cache Compression via Euclidean Outlier Detection
por: Datta, Debajyoti, et al.
Publicado: (2026)

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

KVzap: Fast, Adaptive, and Faithful KV Cache Pruning
por: Jegou, Simon, et al.
Publicado: (2026)

Beyond Speedup -- Utilizing KV Cache for Sampling and Reasoning
por: Xing, Zeyu, et al.
Publicado: (2026)

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

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

KV Cache Transform Coding for Compact Storage in LLM Inference
por: Staniszewski, Konrad, et al.
Publicado: (2025)

Latent Phase-Shift Rollback: Inference-Time Error Correction via Residual Stream Monitoring and KV-Cache Steering
por: Gupta, Manan, et al.
Publicado: (2026)

LaCache: Ladder-Shaped KV Caching for Efficient Long-Context Modeling of Large Language Models
por: Shi, Dachuan, et al.
Publicado: (2025)

Training-Free Exponential Context Extension via Cascading KV Cache
por: Willette, Jeffrey, et al.
Publicado: (2024)

TTKV: Temporal-Tiered KV Cache for Long-Context LLM Inference
por: Dzikanyanga, Gradwell, et al.
Publicado: (2026)

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

AMUSED: A Multi-Stream Vector Representation Method for Use in Natural Dialogue
por: Kumar, Gaurav, et al.
Publicado: (2019)

EliteKV: Scalable KV Cache Compression via RoPE Frequency Selection and Joint Low-Rank Projection
por: Zhou, Yuhao, et al.
Publicado: (2025)

TokenSelect: Efficient Long-Context Inference and Length Extrapolation for LLMs via Dynamic Token-Level KV Cache Selection
por: Wu, Wei, et al.
Publicado: (2024)

KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs
por: Chen, Chuangtao, et al.
Publicado: (2026)

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

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

NQKV: A KV Cache Quantization Scheme Based on Normal Distribution Characteristics
por: Cai, Zhihang, et al.
Publicado: (2025)

CSKV: Training-Efficient Channel Shrinking for KV Cache in Long-Context Scenarios
por: Wang, Luning, et al.
Publicado: (2024)

KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing
por: Yang, Yifei, et al.
Publicado: (2024)

Test-Time Speculation
por: Kumar, Avinash, et al.
Publicado: (2026)