Imagen de Portada

Towards Threshold-Free KV Cache Pruning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Ni, Xuanfan, Xu, Liyan, Lyu, Chenyang, Wang, Longyue, Yu, Mo, Liu, Lemao, Meng, Fandong, Zhou, Jie, Li, Piji
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

A Systematic Evaluation of Large Language Models for Natural Language Generation Tasks
por: Ni, Xuanfan, et al.
Publicado: (2024)

Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models
por: Yin, Huifeng, et al.
Publicado: (2025)

DepthKV: Layer-Dependent KV Cache Pruning for Long-Context LLM Inference
por: Dehghanighobadi, Zahra, et al.
Publicado: (2026)

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

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

SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
por: Liao, Huanxuan, et al.
Publicado: (2025)

CSCD-NS: a Chinese Spelling Check Dataset for Native Speakers
por: Hu, Yong, et al.
Publicado: (2022)

DeepTrans: Deep Reasoning Translation via Reinforcement Learning
por: Wang, Jiaan, et al.
Publicado: (2025)

ExTrans: Multilingual Deep Reasoning Translation via Exemplar-Enhanced Reinforcement Learning
por: Wang, Jiaan, et al.
Publicado: (2025)

OBCache: Optimal Brain KV Cache Pruning for Efficient Long-Context LLM Inference
por: Gu, Yuzhe, et al.
Publicado: (2025)

EAG: Extract and Generate Multi-way Aligned Corpus for Complete Multi-lingual Neural Machine Translation
por: Xu, Yulin, et al.
Publicado: (2022)

On the token distance modeling ability of higher RoPE attention dimension
por: Hong, Xiangyu, et al.
Publicado: (2024)

Lookahead Q-Cache: Achieving More Consistent KV Cache Eviction via Pseudo Query
por: Wang, Yixuan, et al.
Publicado: (2025)

R-KV: Redundancy-aware KV Cache Compression for Reasoning Models
por: Cai, Zefan, et al.
Publicado: (2025)

Beyond Next Token Prediction: Patch-Level Training for Large Language Models
por: Shao, Chenze, et al.
Publicado: (2024)

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

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

PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling
por: Cai, Zefan, et al.
Publicado: (2024)

HGMEM: Hypergraph-based Working Memory to Improve Multi-step RAG for Long-Context Complex Relational Modeling
por: Zhou, Chulun, et al.
Publicado: (2025)

Unsupervised Information Refinement Training of Large Language Models for Retrieval-Augmented Generation
por: Xu, Shicheng, et al.
Publicado: (2024)

DeltaKV: Residual-Based KV Cache Compression via Long-Range Similarity
por: Hao, Jitai, et al.
Publicado: (2026)

Retrieval-Augmented Machine Translation with Unstructured Knowledge
por: Wang, Jiaan, et al.
Publicado: (2024)

TEAL: Tokenize and Embed ALL for Multi-modal Large Language Models
por: Yang, Zhen, et al.
Publicado: (2023)

DRT: Deep Reasoning Translation via Long Chain-of-Thought
por: Wang, Jiaan, et al.
Publicado: (2024)

Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference
por: Feng, Yuan, et al.
Publicado: (2024)

Lossless KV Cache Compression to 2%
por: Yang, Zhen, et al.
Publicado: (2024)

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

LCS: A Language Converter Strategy for Zero-Shot Neural Machine Translation
por: Sun, Zengkui, et al.
Publicado: (2024)

Judge Q: Trainable Queries for Optimized Information Retention in KV Cache Eviction
por: Liu, Yijun, et al.
Publicado: (2025)

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

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

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

TextBind: Multi-turn Interleaved Multimodal Instruction-following in the Wild
por: Li, Huayang, et al.
Publicado: (2023)

DivLogicEval: A Framework for Benchmarking Logical Reasoning Evaluation in Large Language Models
por: Chung, Tsz Ting, et al.
Publicado: (2025)

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

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

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

Continuous Autoregressive Language Models
por: Shao, Chenze, et al.
Publicado: (2025)

General learned delegation by clones
por: Li, Darren, et al.
Publicado: (2026)

Q-Filters: Leveraging QK Geometry for Efficient KV Cache Compression
por: Godey, Nathan, et al.
Publicado: (2025)