Vorträge und Posterpräsentationen (mit Tagungsband-Eintrag):
M. Reisinger, P. Frangoudis, S. Dustdar:
"System support and mechanisms for adaptive edge-to-cloud DNN model serving";
Poster: 9th IEEE International Conference on Cloud Engineering (IC2E 2021) - Online Conference,
San Francisco, CA, USA;
04.10.2021
- 08.10.2021; in: "Proceedings of the IEEE International Conference on Cloud Engineering (IC2E 2021)",
IEEE,
(2021),
ISBN: 978-1-6654-4971-7;
S. 278
- 279.
Kurzfassung englisch:
We present an orchestration scheme for Deep Neural Network (DNN) model serving, capable of computation distribution over the device-to-cloud continuum and low-latency inference. Our system allows automated layer-wise splitting of DNN structures and their adaptive distribution over compute hosts, providing an execution environment for collaborative inference. Model deployment and its self-adaptation at runtime are implemented by optimization algorithms supported in a plug-in manner. These follow service and infrastructure provider criteria and constraints, expressed via well-defined interfaces. Our framework can serve diverse neural architectures, including DNNs with early exits, with zero to minimal modifications.
"Offizielle" elektronische Version der Publikation (entsprechend ihrem Digital Object Identifier - DOI)
http://dx.doi.org/10.1109/IC2E52221.2021.00046
Erstellt aus der Publikationsdatenbank der Technischen Universität Wien.