Cover Image

Why Should the Server Do It All?: A Scalable, Versatile, and Model-Agnostic Framework for Server-Light DNN Inference over Massively Distributed Clients via Training-Free Intermediate Feature Compression

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sung, Mingyu, Im, Suhwan, Bang, Daeho, Kim, Il-Min, Yun, Sangseok, Kang, Jae-Mo
Format:	Preprint
Published:	2025
Subjects:	Distributed, Parallel, and Cluster Computing Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Range Asymmetric Numeral Systems-Based Lightweight Intermediate Feature Compression for Split Computing of Deep Neural Networks
by: Sung, Mingyu, et al.
Published: (2025)

Memory- and Latency-Constrained Inference of Large Language Models via Adaptive Split Computing
by: Sung, Mingyu, et al.
Published: (2025)

No Pose Estimation? No Problem: Pose-Agnostic and Instance-Aware Test-Time Adaptation for Monocular Depth Estimation
by: Sung, Mingyu, et al.
Published: (2025)

H2-Cache: A Novel Hierarchical Dual-Stage Cache for High-Performance Acceleration of Generative Diffusion Models
by: Sung, Mingyu, et al.
Published: (2025)

Beyond Inference: Performance Analysis of DNN Server Overheads for Computer Vision
by: AbouElhamayed, Ahmed F., et al.
Published: (2024)

NatServer: A Client-Server Architecture for building Parallel Corpora applications
by: Alberto Simões
Published: (2006)

Systems Librarians and the Client/Server Environment.
by: Ross, Mary, et al.
Published: (2000)

Verification of Unbounded Client-Server Systems with Distinguishable Clients
by: Phawade, Ramchandra, et al.
Published: (2026)

CycleSL: Server-Client Cyclical Update Driven Scalable Split Learning
by: Wang, Mengdi, et al.
Published: (2025)

GLYPH-SR: Can We Achieve Both High-Quality Image Super-Resolution and High-Fidelity Text Recovery via VLM-guided Latent Diffusion Model?
by: Sung, Mingyu, et al.
Published: (2025)

Robust Client-Server Watermarking for Split Federated Learning
by: Tang, Jiaxiong, et al.
Published: (2025)

Bounded Model Checking for Unbounded Client Server Systems
by: Phawade, Ramchandra, et al.
Published: (2022)

Design and Implementation of a Java-Based Client-Server Application
by: Patil, Omkar, et al.
Published: (2024)

Conflict-Aware Client Selection for Multi-Server Federated Learning
by: Hong, Mingwei, et al.
Published: (2026)

Asynchronous Multi-Server Federated Learning for Geo-Distributed Clients
by: Zuo, Yuncong, et al.
Published: (2024)

Ecomap: Sustainability-Driven Optimization of Multi-Tenant DNN Execution on Edge Servers
by: Paramanayakam, Varatheepan, et al.
Published: (2025)

Bandwidth-Efficient Two-Server ORAMs with O(1) Client Storage
by: Wang, Wei, et al.
Published: (2025)

Understanding Server-Assisted Federated Learning in the Presence of Incomplete Client Participation
by: Yang, Haibo, et al.
Published: (2024)

Crayon: Customized On-Device LLM via Instant Adapter Blending and Edge-Server Hybrid Inference
by: Bang, Jihwan, et al.
Published: (2024)

Gated Infinite Server Queues in Light Traffic
by: Pinotsi, Dimitra, et al.
Published: (2026)

DRAW Server
by: Chakraborty, Santam, et al.
Published: (2026)

Multi-Server FL with Overlapping Clients: A Latency-Aware Relay Framework
by: Ji, Yun, et al.
Published: (2025)

VDDP: Verifiable Distributed Differential Privacy under the Client-Server-Verifier Setup
by: Sun, Haochen, et al.
Published: (2025)

CoLM: Collaborative Large Models via A Client-Server Paradigm
by: Huang, Siqi, et al.
Published: (2025)

Collaborative Edge-to-Server Inference for Vision-Language Models
by: Song, Soochang, et al.
Published: (2025)

VLAgents: A Policy Server for Efficient VLA Inference
by: Jülg, Tobias, et al.
Published: (2026)

Scalable and Secure AI Inference in Healthcare: A Comparative Benchmarking of FastAPI and Triton Inference Server on Kubernetes
by: Ali, Ratul
Published: (2026)

Explicit Steady-State Approximations for Parallel Server Systems with Heterogeneous Servers
by: Xu, Yaosheng
Published: (2024)

Many-Server Queueing Systems with Heterogeneous Strategic Servers in Heavy Traffic
by: Büke, Burak, et al.
Published: (2022)

Communication Compression for Distributed Learning with Aggregate and Server-Guided Feedback
by: Ortega, Tomas, et al.
Published: (2025)

TailBench++: Flexible Multi-Client, Multi-Server Benchmarking for Latency-Critical Workloads
by: Li, Zhilin, et al.
Published: (2025)

FedOC: Multi-Server FL with Overlapping Client Relays in Wireless Edge Networks
by: Ji, Yun, et al.
Published: (2025)

DataFormatServer
by: Khokhriakov, Igor
Published: (2025)

Queues with Rechargeable Servers
by: Fuentes-Quezada, Eliezer, et al.
Published: (2026)

Energy Efficient Servers
by: Gough, Corey, et al.
Published: (2018)

IVE: An Accelerator for Single-Server Private Information Retrieval Using Versatile Processing Elements
by: Kim, Sangpyo, et al.
Published: (2025)

Taming Server Memory TCO with Multiple Software-Defined Compressed Tiers
by: Kumar, Sandeep, et al.
Published: (2024)

Federated Knowledge Transfer Fine-tuning Large Server Model with Resource-Constrained IoT Clients
by: Chen, Shaoyuan, et al.
Published: (2024)

FedSCAl: Leveraging Server and Client Alignment for Unsupervised Federated Source-Free Domain Adaptation
by: Yashwanth, M, et al.
Published: (2025)

Robust Server Defense Against Unreliable Clients in One-Shot Fair Collaborative Machine Learning
by: Wu, Chia-Yuan, et al.
Published: (2026)