Copertina

Subkv: Quantizing Long Context KV Cache for Sub‐Billion Parameter Language Models on Edge Devices

Fuente: Wiley Open Access

Salvato in:

Dettagli Bibliografici
Autori principali:	Ziqian Zeng, Tao Zhang, Zhengdong Lu, Wenjun Li, Huiping Zhuang, Hongen Shao, Sin G. Teo, Xiaofeng Zou
Natura:	Artículo Open Access
Pubblicazione:	Wiley 2025
Soggetti:	Software: Practice and Experience
Accesso online:	Acceder al recurso
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!

Documenti analoghi

BanaServe: Unified KV Cache and Dynamic Module Migration for Balancing Disaggregated LLM Serving in AI Infrastructure
di: Yiyuan He, et al.
Pubblicazione: (2026)

Migration Using Context Cache for Multicore RISC‐V Processor
di: Akira Yamazawa, et al.
Pubblicazione: (2025)

Dataset and Approach for Helmet‐Wearing Detection With Edge Devices at Construction Sites
di: Longlong Liao, et al.
Pubblicazione: (2026)

Secuyolo: Secure Object Detection Framework With Darknet‐53 and CBAM in Edge Devices
di: P. Lakshmiramana, et al.
Pubblicazione: (2025)

SIB: Sorted‐Integers‐Based Index for Compact and Fast Caching in Top‐Down Logic Rule Mining Targeting KB Compression
di: Ruoyu Wang, et al.
Pubblicazione: (2025)

On‐Demand Deployment of Edge Cloud Infrastructures for Federated Learning
di: Eduardo Huedo, et al.
Pubblicazione: (2025)

Continuous QoS‐compliant orchestration in the Cloud‐Edge continuum
di: Giuseppe Bisicchia, et al.
Pubblicazione: (2024)

Ranking‐based architecture generation for surrogate‐assisted neural architecture search
di: Songyi Xiao, et al.
Pubblicazione: (2024)

A Cache Friendly LSM Tree Based on Extendible Hash
di: Tao Cai, et al.
Pubblicazione: (2025)

Ensemble Instance Selection for Medical Datasets: Single‐Stage Parallel and Two‐Stage Serial Ensemble Approaches
di: Min‐Wei Huang, et al.
Pubblicazione: (2025)

Prototype‐Based Collaborative Learning in UAV‐Assisted Edge Computing Networks
di: Enze Yu, et al.
Pubblicazione: (2024)

Confidential Computing Across Edge‐To‐Cloud for Machine Learning: A Survey Study
di: Sm Zobaed, et al.
Pubblicazione: (2025)

Quality of Experience Based Dynamic Path Serverless Data Pipelines in Edge/Fog Computing
di: Sreenivasu Mirampalli, et al.
Pubblicazione: (2025)

The Cache Oracle: Preemptive Request Dispatching for I/O‐Asymmetric Serverless Databases
di: Seyed Hossein Ahmadpanah, et al.
Pubblicazione: (2025)

A Context‐Aware Decision Support Framework for Scientific Experiment Configuration
di: Pouriya Miri, et al.
Pubblicazione: (2026)

Improving Energy Efficiency in Iot Edge Computing Through Dynamic Deep Q‐Network Based Resource Management
di: Aditya Bhushan, et al.
Pubblicazione: (2025)

Special Issue on Edge Intelligence Software Systems for Internet of Autonomous Unmanned Vehicles Journal of Software: Practice and Experience (Wiley Press)
di: Kaijian Xia, et al.
Pubblicazione: (2025)

HealthEdgeAI: GAI and XAI Based Healthcare System for Sustainable Edge AI and Cloud Computing Environments
di: Han Wang, et al.
Pubblicazione: (2025)

Multi‐Objective Dynamic Registry Provisioning in Edge Computing Infrastructures
di: Lucas Roges, et al.
Pubblicazione: (2025)

Fine‐grained forest net primary productivity monitoring: Software system integrating multisource data and smart optimization
di: Weitao Zou, et al.
Pubblicazione: (2024)

Enhancing Edge Environment Scalability: Leveraging Kubernetes for Container Orchestration and Optimization
di: K. Aruna, et al.
Pubblicazione: (2024)

Request Deadline Split and Interference‐Aware Request Migration in Edge Cloud
di: Jie Wang, et al.
Pubblicazione: (2024)

EAF‐DETR: An Edge‐Aware Fusion Transformer for UAV Object Detection
di: Lianke Shi, et al.
Pubblicazione: (2026)

Application of an Improved Differential Evolution Algorithm in Practical Engineering
di: Yangyang Shen, et al.
Pubblicazione: (2025)

FEMBNet: Toward Robust and Lightweight Federated Learning for Heterogeneous IoT Devices
di: Jiao Tian, et al.
Pubblicazione: (2026)

Edge computing collaborative offloading strategy for space‐air‐ground integrated networks
di: Biqun Xiang, et al.
Pubblicazione: (2024)

Energy‐Latency Tradeoffs for Service Placement Based on Reinforcement Learning in Edge Computing
di: Bing Tang, et al.
Pubblicazione: (2025)

Dynamic Probabilistic Scheduling for Efficient Edge Resource Orchestration in Tier‐Agnostic Architecture
di: Jingjing Zhu, et al.
Pubblicazione: (2025)

An Efficient Load Distribution Approach for Optimizing Resources in SDN‐Based Edge Computing Environment
di: Ajay Nain, et al.
Pubblicazione: (2025)

New Continual Federated Learning System for Intrusion Detection in SDN‐Based Edge Computing
di: Ameni Chetouane, et al.
Pubblicazione: (2024)

SDT‐MCS: Topology‐Aware Microservice Orchestration With Adaptive Learning in Cloud‐Edge Environments
di: Jianyong Zhu, et al.
Pubblicazione: (2025)

Adaptive Hierarchical Offloading for Mobile Edge Computing in High‐Mobility SWIPT‐Enabled Networks
di: Zewei Zhang, et al.
Pubblicazione: (2025)

A Real‐Time Automated Library Inventory System Based on Edge‐Cloud Collaboration
di: Lu Zhu, et al.
Pubblicazione: (2026)

Parameter instance learning with enhanced vision transformers for aerial person re‐identification
di: Houfu Peng, et al.
Pubblicazione: (2024)

MBN ‐ YOLOv8 : Patch‐Aware Attention and Cross‐Scale Feature Fusion Network for Large Coal Detection in Fully Mechanized Mining Face
di: Zhi Wang, et al.
Pubblicazione: (2025)

EE ‐ YOLO11n : Improved Detection of Rice Leaf Diseases via Edge Enhancement
di: Di Zhang, et al.
Pubblicazione: (2026)

Mixed‐Criticality Scheduling Toward Real‐Time Applications in a Vehicular Edge Computing System
di: Biao Hu, et al.
Pubblicazione: (2025)

Novel Edge Computing Offloading Method Based on Cooperative Optimization Learning Strategy of Whale Group
di: De‐Gan Zhang, et al.
Pubblicazione: (2025)

PLRAC : A PUF Characteristic Based Lightweight Remote Attestation for Container
di: XinFeng He, et al.
Pubblicazione: (2026)

Energy‐Efficient Blockchain‐Based Secure Model to Share Medical Data Using Mobile Edge Computing
di: Sagnik Datta, et al.
Pubblicazione: (2025)