A serverless gateway for event-driven machine learning inference in multiple clouds

A serverless gateway for event-driven machine learning inference in multiple clouds

15 December 2021
The paper 'A serverless gateway for event-driven machine learning inference in multiple clouds' has been published by the Universitat Politècnica de València. The paper presents serverless web-based gateways in scalable applications in the cloud. The research has been conducted in cooperation with the AI-SPRINT project team.
TaScaaS: A Multi-Tenant Serverless Task Scheduler and Load Balancer as a Service

TaScaaS: A Multi-Tenant Serverless Task Scheduler and Load Balancer as a Service

03 September 2021

"TaScaaS: A Multi-Tenant Serverless Task Scheduler and Load Balancer as a Service" is a new scientific work published in cooperation with the AI-SPRINT project.

Network Function Decomposition and Offloading on Heterogeneous Networks With Programmable Data Planes

Network Function Decomposition and Offloading on Heterogeneous Networks With Programmable Data Planes

02 August 2021

The scientific publication "Network Function Decomposition and Offloading on Heterogeneous Networks With Programmable Data Planes" was supported by the work performed by

PERUN_AI-SPRINT

PERUN: Confidential Multi-stakeholder Machine Learning Framework with Hardware Acceleration Support

14 July 2021
IBM and Technische Universität Dresden have designed and implemented Perun, a framework for confidential multi-stakeholder machine learning that allows users to make a trade-off between security and performance. The new architecture executes ML training on hardware accelerators (e.g., GPU) while providing security guarantees using trusted computing technologies, such as trusted platform module and integrity measurement architecture. The research conducted has received funding from the European Union’s Horizon 2020 Research and Innovation program under the AI-SPRINT project.
Serverless Workflows for Containerised Applications in the Cloud Continuum

Serverless Workflows for Containerised Applications in the Cloud Continuum

13 July 2021
The paper introduces an open-source platform to support serverless computing for scientific data-processing workflow-based applications across the Cloud continuum, work conducted in cooperation with the AI-SPRINT project.