Image de couverture de livre

River-LLM: Large Language Model Seamless Exit Based on KV Share

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Shen, Yingtao, Zou, An
Format:	Preprint
Publié:	2026
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

NEAT: Neuron-Based Early Exit for Large Reasoning Models
par: Liu, Kang, et autres
Publié: (2026)

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference
par: Wu, You, et autres
Publié: (2024)

Effectively Compress KV Heads for LLM
par: Yu, Hao, et autres
Publié: (2024)

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference
par: Patel, Ishan, et autres
Publié: (2026)

Accelerating Large Language Model Inference with Self-Supervised Early Exits
par: Valade, Florian
Publié: (2024)

SpecExit: Accelerating Large Reasoning Model via Speculative Exit
par: Yang, Rubing, et autres
Publié: (2025)

DASH-KV: Accelerating Long-Context LLM Inference via Asymmetric KV Cache Hashing
par: Guo, Jinyu, et autres
Publié: (2026)

Layer-Condensed KV Cache for Efficient Inference of Large Language Models
par: Wu, Haoyi, et autres
Publié: (2024)

Path-Consistency with Prefix Enhancement for Efficient Inference in LLMs
par: Zhu, Jiace, et autres
Publié: (2024)

Mitigating KV Cache Competition to Enhance User Experience in LLM Inference
par: Shen, Haiying, et autres
Publié: (2025)

KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse
par: Yang, Jingbo, et autres
Publié: (2025)

A Method for Building Large Language Models with Predefined KV Cache Capacity
par: Yi, Zhonghua, et autres
Publié: (2024)

AhaKV: Adaptive Holistic Attention-Driven KV Cache Eviction for Efficient Inference of Large Language Models
par: Gu, Yifeng, et autres
Publié: (2025)

Self-supervised Quantized Representation for Seamlessly Integrating Knowledge Graphs with Large Language Models
par: Lin, Qika, et autres
Publié: (2025)

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction
par: Jiang, Tanqiu, et autres
Publié: (2024)

DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
par: Liu, Yuhan, et autres
Publié: (2024)

KV Shifting Attention Enhances Language Modeling
par: Xu, Mingyu, et autres
Publié: (2024)

Defending against Jailbreak through Early Exit Generation of Large Language Models
par: Zhao, Chongwen, et autres
Publié: (2024)

BriLLM: Brain-inspired Large Language Model
par: Zhao, Hai, et autres
Publié: (2025)

WeightedKV: Attention Scores Weighted Key-Value Cache Merging for Large Language Models
par: Yuan, Jian, et autres
Publié: (2025)

SimLens for Early Exit in Large Language Models: Eliciting Accurate Latent Predictions with One More Token
par: Ma, Ming, et autres
Publié: (2025)

EvolKV: Evolutionary KV Cache Compression for LLM Inference
par: Yu, Bohan, et autres
Publié: (2025)

dKV-Cache: The Cache for Diffusion Language Models
par: Ma, Xinyin, et autres
Publié: (2025)

Runaway is Ashamed, But Helpful: On the Early-Exit Behavior of Large Language Model-based Agents in Embodied Environments
par: Lu, Qingyu, et autres
Publié: (2025)

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference
par: Liu, Xiang, et autres
Publié: (2025)

HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving
par: Kumar, Avinash, et autres
Publié: (2025)

Seamless Deception: Larger Language Models Are Better Knowledge Concealers
par: Ashok, Dhananjay, et autres
Publié: (2026)

EMAFusion: A Self-Optimizing System for Seamless LLM Selection and Integration
par: Shah, Soham, et autres
Publié: (2025)

MinMo: A Multimodal Large Language Model for Seamless Voice Interaction
par: Chen, Qian, et autres
Publié: (2025)

INMS: Memory Sharing for Large Language Model based Agents
par: Gao, Hang, et autres
Publié: (2024)

WindowKV: Task-Adaptive Group-Wise KV Cache Window Selection for Efficient LLM Inference
par: Zuo, Youhui, et autres
Publié: (2025)

IntactKV: Improving Large Language Model Quantization by Keeping Pivot Tokens Intact
par: Liu, Ruikang, et autres
Publié: (2024)

AKVQ-VL: Attention-Aware KV Cache Adaptive 2-Bit Quantization for Vision-Language Models
par: Su, Zunhai, et autres
Publié: (2025)

EE-Tuning: An Economical yet Scalable Solution for Tuning Early-Exit Large Language Models
par: Pan, Xuchen, et autres
Publié: (2024)

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings
par: Wu, Qiong, et autres
Publié: (2024)

EchoKV: Efficient KV Cache Compression via Similarity-Based Reconstruction
par: Ji, Shiyu, et autres
Publié: (2026)

Early Exit Is a Natural Capability in Transformer-based Models: An Empirical Study on Early Exit without Joint Optimization
par: Shan, Weiqiao, et autres
Publié: (2024)

LLM as Dataset Analyst: Subpopulation Structure Discovery with Large Language Model
par: Luo, Yulin, et autres
Publié: (2024)

QAQ: Quality Adaptive Quantization for LLM KV Cache
par: Dong, Shichen, et autres
Publié: (2024)

Taming the Fragility of KV Cache Eviction in LLM Inference
par: Feng, Yuan, et autres
Publié: (2025)