2 papers
cs.DC2025
Cicada: A Pipeline-Efficient Approach to Serverless Inference with Decoupled Management
Z. Wu, Y. Deng, J. Hu +4
Serverless computing has emerged as a pivotal paradigm for deploying Deep Learning (DL) models, offering automatic scaling and cost efficiency. However, the inherent cold start pro…
cs.NI2025
Quark: Implementing Convolutional Neural Networks Entirely on Programmable Data Plane
Mai Zhang, Lin Cui, Xiaoquan Zhang +4
The rapid development of programmable network devices and the widespread use of machine learning (ML) in networking have facilitated efficient research into intelligent data plane…