paper-with-me

Papers

SpecEdge: Scalable Edge-Assisted Serving Framework for Interactive LLMs

2025-05-16 · Jinwoo Park, Seunggeun Cho, Dongsu Han

Large language models (LLMs) power many modern applications, but serving them at scale remains costly and resource-intensive. Current server-centric systems overlook consumer-grade GPUs at the edge. We introduce SpecEdge, an edge-assisted inference framework that splits LLM workloads between edge and server GPUs using a speculative decoding scheme, exchanging only token outputs over the network. SpecEdge employs proactive edge drafting to overlap edge token creation with server verification and pipeline-aware scheduling that interleaves multiple user requests to increase server-side throughput. Experiments show SpecEdge enhances overall cost efficiency by 1.91x through achieving 2.22x server throughput, and reduces inter token latency by 11.24% compared to a server-only baseline, introducing a scalable, cost-effective paradigm for LLM serving.

📄 PDF Abstract BibTeX arXiv:2505.17052

Code (0)

등록된 구현이 없습니다.

Tasks

Scheduling

Similar Papers 제목 키워드 기반

ZK-HybridFL: Zero-Knowledge Proof-Enhanced Hybrid Ledger for Federated Learning

2026-01-29 · Amirhossein Taherpour, Xiaodong Wang arxiv

Federated learning (FL) enables collaborative model training while preserving data privacy, yet both centralized and decentralized approaches face challenges in scalability, security, and update validation. We propose ZK…

Image ClassificationFederated Learning

Secure and Parallel Determinant Computation for Large-Scale Matrices in Edge Environments

2026-05-21 · Prajwal Panth arxiv

The advent of edge computing has enabled resource-constrained clients to delegate intensive computational tasks to distributed edge servers, especially within Internet of Things (IoT) environments. Among such tasks, Matr…

Scalable Wi-Fi RSS-Based Indoor Localization via Automatic Vision-Assisted Calibration

2025-09-26 · Abdulkadir Bilge, Erdem Ergen, Burak Soner, Sinem Coleri arxiv

Wi-Fi-based positioning promises a scalable and privacy-preserving solution for location-based services in indoor environments such as malls, airports, and campuses. RSS-based methods are widely deployable as RSS data is…

SCAR: State-Space Compression for Scalable AI-Based Network Management of Vehicular Services

2025-08-08 · Ioan-Sorin Comsa, Purav Shah, Karthik Vaidhyanathan, Deepak Gangadharan 외 arxiv

The increasing demand for connected vehicular services poses significant challenges for AI-based network and service management due to the high volume and rapid variability of network state information. Traditional manag…

Reinforcement Learning

Edge Assisted Multi-Camera Vehicle Tracking Framework for Real-Time and Scalable Deployment

2025-11-17 · Yuqiang Lin, Sam Lockyer, Shucheng Zhang, Florian Stanek 외 arxiv

Cameras are a core sensing modality in modern intelligent transportation systems (ITS), providing rich visual information on road-user activities. Multi-Camera Vehicle Tracking (MCVT) uses this data to reconstruct vehicl…

Object Detection