Copertina

Krul: Efficient State Restoration for Multi-turn Conversations with Dynamic Cross-layer KV Sharing

Fuente: arXiv

Salvato in:

Dettagli Bibliografici
Autori principali:	Wen, Junyi, Liang, Junyuan, Hong, Zicong, Chen, Wuhui, Cai, Ting, Zheng, Zibin
Natura:	Preprint
Pubblicazione:	2025
Soggetti:	Computation and Language Artificial Intelligence
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

Klotski: Efficient Mixture-of-Expert Inference via Expert-Aware Multi-Batch Pipeline
di: Fang, Zhiyuan, et al.
Pubblicazione: (2025)

Fate: Fast Edge Inference of Mixture-of-Experts Models via Cross-Layer Gate
di: Fang, Zhiyuan, et al.
Pubblicazione: (2025)

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

A Systematic Study of Cross-Layer KV Sharing for Efficient LLM Inference
di: Wu, You, et al.
Pubblicazione: (2024)

Reconstructing KV Caches with Cross-layer Fusion For Enhanced Transformers
di: Lin, Hongzhan, et al.
Pubblicazione: (2025)

KVDrive: A Holistic Multi-Tier KV Cache Management System for Long-Context LLM Inference
di: Lin, Jian, et al.
Pubblicazione: (2026)

Broaden your SCOPE! Efficient Multi-turn Conversation Planning for LLMs with Semantic Space
di: Chen, Zhiliang, et al.
Pubblicazione: (2025)

SpindleKV: A Novel KV Cache Reduction Method Balancing Both Shallow and Deep Layers
di: Tang, Zicong, et al.
Pubblicazione: (2025)

CORAL: Benchmarking Multi-turn Conversational Retrieval-Augmentation Generation
di: Cheng, Yiruo, et al.
Pubblicazione: (2024)

Pixel-Level Reasoning Segmentation via Multi-turn Conversations
di: Cai, Dexian, et al.
Pubblicazione: (2025)

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

AM$^3$Safety: Towards Data Efficient Alignment of Multi-modal Multi-turn Safety for MLLMs
di: Zhu, Han, et al.
Pubblicazione: (2026)

Cost-Efficient Large Language Model Serving for Multi-turn Conversations with CachedAttention
di: Gao, Bin, et al.
Pubblicazione: (2024)

FairMT-Bench: Benchmarking Fairness for Multi-turn Dialogue in Conversational LLMs
di: Fan, Zhiting, et al.
Pubblicazione: (2024)

On the Multi-turn Instruction Following for Conversational Web Agents
di: Deng, Yang, et al.
Pubblicazione: (2024)

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

DroidSpeak: KV Cache Sharing for Cross-LLM Communication and Multi-LLM Serving
di: Liu, Yuhan, et al.
Pubblicazione: (2024)

GriDB: Scaling Blockchain Database via Sharding and Off-Chain Cross-Shard Mechanism
di: Hong, Zicong, et al.
Pubblicazione: (2024)

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

Learning Multi-Indicator Weights for Data Selection: A Joint Task-Model Adaptation Framework with Efficient Proxies
di: Song, Jingze, et al.
Pubblicazione: (2026)

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

DyMoE: Dynamic Expert Orchestration with Mixed-Precision Quantization for Efficient MoE Inference on Edge
di: Huang, Yuegui, et al.
Pubblicazione: (2026)

Rethinking Text-to-SQL: Dynamic Multi-turn SQL Interaction for Real-world Database Exploration
di: Sun, Linzhuang, et al.
Pubblicazione: (2025)

A State-Update Prompting Strategy for Efficient and Robust Multi-turn Dialogue
di: Liu, Ziyi
Pubblicazione: (2025)

Training and Serving System of Foundation Models: A Comprehensive Survey
di: Zhou, Jiahang, et al.
Pubblicazione: (2024)

NaturalConv: A Chinese Dialogue Dataset Towards Multi-turn Topic-driven Conversation
di: Wang, Xiaoyang, et al.
Pubblicazione: (2021)

Multimodal Multi-turn Conversation Stance Detection: A Challenge Dataset and Effective Model
di: Niu, Fuqiang, et al.
Pubblicazione: (2024)

LogQuant: Log-Distributed 2-Bit Quantization of KV Cache with Superior Accuracy Preservation
di: Chen, Han, et al.
Pubblicazione: (2025)

Learning to Clarify: Multi-turn Conversations with Action-Based Contrastive Self-Training
di: Chen, Maximillian, et al.
Pubblicazione: (2024)

Token Statistics Reveal Conversational Drift in Multi-turn LLM Interaction
di: Hafez, Wael, et al.
Pubblicazione: (2026)

SemShareKV: Efficient KVCache Sharing for Semantically Similar Prompts via Token-Level LSH Matching
di: Zhao, Xinye, et al.
Pubblicazione: (2025)

ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
di: Dong, Zican, et al.
Pubblicazione: (2026)

MAC: A Multi-Agent Framework for Interactive User Clarification in Multi-turn Conversations
di: Acikgoz, Emre Can, et al.
Pubblicazione: (2025)

SafeMT: Multi-turn Safety for Multimodal Language Models
di: Zhu, Han, et al.
Pubblicazione: (2025)

Source-primed Multi-turn Conversation Helps Large Language Models Translate Documents
di: Hu, Hanxu, et al.
Pubblicazione: (2025)

PolyKV: A Shared Asymmetrically-Compressed KV Cache Pool for Multi-Agent LLM Inference
di: Patel, Ishan, et al.
Pubblicazione: (2026)

DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs
di: Zhou, Xiabin, et al.
Pubblicazione: (2024)

Securing Multi-turn Conversational Language Models From Distributed Backdoor Triggers
di: Tong, Terry, et al.
Pubblicazione: (2024)

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

LabelCoRank: Revolutionizing Long Tail Multi-Label Classification with Co-Occurrence Reranking
di: Yan, Yan, et al.
Pubblicazione: (2025)