Imagen de Portada

SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Jie, Shibo, Tang, Yehui, Han, Kai, Deng, Zhi-Hong, Han, Jing
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Memory-Space Visual Prompting for Efficient Vision-Language Fine-Tuning
por: Jie, Shibo, et al.
Publicado: (2024)

Mixture of Lookup Experts
por: Jie, Shibo, et al.
Publicado: (2025)

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models
por: Ni, Yunsheng, et al.
Publicado: (2024)

SpeCa: Accelerating Diffusion Transformers with Speculative Feature Caching
por: Liu, Jiacheng, et al.
Publicado: (2025)

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

CacheFocus: Dynamic Cache Re-Positioning for Efficient Retrieval-Augmented Generation
por: Lee, Kun-Hui, et al.
Publicado: (2025)

SCOPE: Optimizing Key-Value Cache Compression in Long-context Generation
por: Wu, Jialong, et al.
Publicado: (2024)

FlowKV: Enhancing Multi-Turn Conversational Coherence in LLMs via Isolated Key-Value Cache Management
por: Liu, Xiang, et al.
Publicado: (2025)

RazorAttention: Efficient KV Cache Compression Through Retrieval Heads
por: Tang, Hanlin, et al.
Publicado: (2024)

Learning to Evict from Key-Value Cache
por: Moschella, Luca, et al.
Publicado: (2026)

SONIC: Segmented Optimized Nexus for Information Compression in Key-Value Caching
por: Chen, Hong, et al.
Publicado: (2026)

Cacheback: Speculative Decoding With Nothing But Cache
por: Ma, Zhiyao, et al.
Publicado: (2025)

TableCache: Primary Foreign Key Guided KV Cache Precomputation for Low Latency Text-to-SQL
por: Su, Jinbo, et al.
Publicado: (2026)

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting
por: Liu, Fangcheng, et al.
Publicado: (2024)

TreeKV: Smooth Key-Value Cache Compression with Tree Structures
por: He, Ziwei, et al.
Publicado: (2025)

Parallel Key-Value Cache Fusion for Position Invariant RAG
por: Oh, Philhoon, et al.
Publicado: (2025)

Homogeneous Keys, Heterogeneous Values: Exploiting Local KV Cache Asymmetry for Long-Context LLMs
por: Cui, Wanyun, et al.
Publicado: (2025)

Key, Value, Compress: A Systematic Exploration of KV Cache Compression Techniques
por: Javidnia, Neusha, et al.
Publicado: (2025)

CSR:Achieving 1 Bit Key-Value Cache via Sparse Representation
por: Zhang, Hongxuan, et al.
Publicado: (2024)

Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
por: Brandon, William, et al.
Publicado: (2024)

When Do LLMs Reason? A Dynamical Systems View via Entropy Phase Transitions
por: Xia, Wei, et al.
Publicado: (2026)

SemantiCache: Efficient KV Cache Compression via Semantic Chunking and Clustered Merging
por: Wu, Shunlong, et al.
Publicado: (2026)

KV-Runahead: Scalable Causal LLM Inference by Parallel Key-Value Cache Generation
por: Cho, Minsik, et al.
Publicado: (2024)

From Prefix Cache to Fusion RAG Cache: Accelerating LLM Inference in Retrieval-Augmented Generation
por: Wang, Jiahao, et al.
Publicado: (2026)

PocketLLM: Ultimate Compression of Large Language Models via Meta Networks
por: Tian, Ye, et al.
Publicado: (2025)

SKVQ: Sliding-window Key and Value Cache Quantization for Large Language Models
por: Duanmu, Haojie, et al.
Publicado: (2024)

EpiCache: Episodic KV Cache Management for Long-Term Conversation on Resource-Constrained Environments
por: Kim, Minsoo, et al.
Publicado: (2025)

d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
por: Jiang, Yuchu, et al.
Publicado: (2025)

InstCache: A Predictive Cache for LLM Serving
por: Zou, Longwei, et al.
Publicado: (2024)

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
por: Ge, Suyu, et al.
Publicado: (2023)

Token Compensator: Altering Inference Cost of Vision Transformer without Re-Tuning
por: Jie, Shibo, et al.
Publicado: (2024)

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

ZSMerge: Zero-Shot KV Cache Compression for Memory-Efficient Long-Context LLMs
por: Liu, Xin, et al.
Publicado: (2025)

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

Cache-Craft: Managing Chunk-Caches for Efficient Retrieval-Augmented Generation
por: Agarwal, Shubham, et al.
Publicado: (2025)

ThinK: Thinner Key Cache by Query-Driven Pruning
por: Xu, Yuhui, et al.
Publicado: (2024)

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

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

XC-Cache: Cross-Attending to Cached Context for Efficient LLM Inference
por: Monteiro, João, et al.
Publicado: (2024)

GRKV: Global Regression for Training-Free KV Cache Compression in Long-Context LLMs
por: Peng, Junjie, et al.
Publicado: (2026)