Image de couverture de livre

Cloud Is Closer Than It Appears: Revisiting the Tradeoffs of Distributed Real-Time Inference

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Sharma, Pragya, Qiu, Hang, Srivastava, Mani
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning Artificial Intelligence Distributed, Parallel, and Cluster Computing Networking and Internet Architecture
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Smaller, Smarter, Closer: The Edge of Collaborative Generative AI
par: Morabito, Roberto, et autres
Publié: (2025)

Edge-First Language Model Inference: Models, Metrics, and Tradeoffs
par: Jang, SiYoung, et autres
Publié: (2025)

Trust-Aware Routing for Distributed Generative AI Inference at the Edge
par: Nguyen, Chanh, et autres
Publié: (2026)

Early-Exit meets Model-Distributed Inference at Edge Networks
par: Colocrese, Marco, et autres
Publié: (2024)

HALO: Semantic-Aware Distributed LLM Inference in Lossy Edge Network
par: Zheng, Peirong, et autres
Publié: (2026)

Optimizing Resource Allocation for Geographically-Distributed Inference by Large Language Models
par: Sun, Tingyang, et autres
Publié: (2025)

SpaceMoE: Realizing Distributed Mixture-of-Experts Inference over Space Networks
par: Wang, Zhanwei, et autres
Publié: (2026)

NebulaFL: Effective Asynchronous Federated Learning for JointCloud Computing
par: Gao, Fei, et autres
Publié: (2024)

An Open API Architecture to Discover the Trustworthy Explanation of Cloud AI Services
par: Wang, Zerui, et autres
Publié: (2024)

$Λ$-Split: A Privacy-Preserving Split Computing Framework for Cloud-Powered Generative AI
par: Ohta, Shoki, et autres
Publié: (2023)

AI Greenferencing: Routing AI Inferencing to Green Modular Data Centers with Heron
par: Reddy, Tella Rajashekhar, et autres
Publié: (2025)

Jupiter: Fast and Resource-Efficient Collaborative Inference of Generative LLMs on Edge Devices
par: Ye, Shengyuan, et autres
Publié: (2025)

Cluster Topology-Driven Placement of Experts Reduces Network Traffic in MoE Inference
par: Sivtsov, Danil, et autres
Publié: (2025)

Galaxy: A Resource-Efficient Collaborative Edge AI System for In-situ Transformer Inference
par: Ye, Shengyuan, et autres
Publié: (2024)

XWind: A Cross-site Router for Large Language Model Inference Serving at Renewable Energy Farms
par: Reddy, Tella Rajashekhar, et autres
Publié: (2026)

Design and Optimization of Hierarchical Gradient Coding for Distributed Learning at Edge Devices
par: Tang, Weiheng, et autres
Publié: (2024)

Rina: Enhancing Ring-AllReduce with In-network Aggregation in Distributed Model Training
par: Chen, Zixuan, et autres
Publié: (2024)

Dynamic and Distributed Routing in IoT Networks based on Multi-Objective Q-Learning
par: Vaishnav, Shubham, et autres
Publié: (2025)

Enabling Intelligent Vehicular Networks Through Distributed Learning in the Non-Terrestrial Networks 6G Vision
par: Naseh, David, et autres
Publié: (2023)

Resilient by Design -- Active Inference for Distributed Continuum Intelligence
par: Donta, Praveen Kumar, et autres
Publié: (2025)

Adaptive DNN Partitioning and Offloading in Heterogeneous Edge-Cloud Continuum
par: Deng, Akuen Akoi, et autres
Publié: (2026)

FogROS2-FT: Fault Tolerant Cloud Robotics
par: Chen, Kaiyuan, et autres
Publié: (2024)

Causal Inference for Quantifying Noisy Neighbor Effects in Multi-Tenant Cloud Environments
par: Schiavo, Philipe S., et autres
Publié: (2026)

PerLLM: Personalized Inference Scheduling with Edge-Cloud Collaboration for Diverse LLM Services
par: Yang, Zheming, et autres
Publié: (2024)

SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference
par: Chen, Qian, et autres
Publié: (2025)

Real-time and Downtime-tolerant Fault Diagnosis for Railway Turnout Machines (RTMs) Empowered with Cloud-Edge Pipeline Parallelism
par: Wu, Fan, et autres
Publié: (2024)

OptiReduce: Resilient and Tail-Optimal AllReduce for Distributed Deep Learning in the Cloud
par: Warraich, Ertza, et autres
Publié: (2023)

Benchmarking Dynamic SLO Compliance in Distributed Computing Continuum Systems
par: Lapkovskis, Alfreds, et autres
Publié: (2025)

Revisiting Cache Freshness for Emerging Real-Time Applications
par: Mao, Ziming, et autres
Publié: (2024)

Collective Communication Profiling of Modern-day Machine Learning Workloads
par: Gupta, Jit, et autres
Publié: (2025)

Digital Twinning of a Pressurized Water Reactor Startup Operation and Partial Computational Offloading in In-network Computing-Assisted Multiaccess Edge Computing
par: Aliyu, Ibrahim, et autres
Publié: (2024)

Context-Aware Orchestration of Energy-Efficient Gossip Learning Schemes
par: Dinani, Mina Aghaei, et autres
Publié: (2024)

Towards Net-Zero Carbon Emissions in Network AI for 6G and Beyond
par: Zhang, Peng, et autres
Publié: (2023)

Optimizing Split Learning Latency in TinyML-Based IoT Systems
par: Jenhani, Zied, et autres
Publié: (2025)

Agentic Performance at the Edge: Insights from Benchmarking
par: Wang, Shiqiang, et autres
Publié: (2026)

KVServe: Service-Aware KV Cache Compression for Communication-Efficient Disaggregated LLM Serving
par: Liu, Zedong, et autres
Publié: (2026)

When IoT Meet LLMs: Applications and Challenges
par: Kok, Ibrahim, et autres
Publié: (2024)

When Digital Twin Meets 6G: Concepts, Obstacles, and Research Prospects
par: Liu, Wenshuai, et autres
Publié: (2024)

High-speed Networking for Giga-Scale AI Factories
par: Khashab, Sajy, et autres
Publié: (2026)

ScaleAcross Explorer: Exploring Communication Optimization for Scale-Across AI Model Training
par: Li, Minghao, et autres
Publié: (2026)