What is it about?
How can DNN inference be served for mobile applications and devices with the same level of system support as server-side serving systems? This paper identifies the key obstacles to serving latency-critical DNN inference over cellular networks and presents a coordinated solution across radio access networks and edge servers.
Featured Image
Photo by Immo Wegmann on Unsplash
Why is it important?
Our system enables DNN model serving for mobile applications over cellular networks under fluctuating wireless conditions and dynamic workloads. This is increasingly important as applications such as XR increasingly combine image processing, rendering, and language processing.
Read the Original
This page is a summary of: End-to-End Coordination of RAN and Edge Server for Latency-Critical Inference Serving over Cellular Networks, Proceedings of the ACM on Networking, November 2025, ACM (Association for Computing Machinery),
DOI: 10.1145/3768987.
You can read the full text:
Contributors
The following have contributed to this page
