Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Greece

Research and Innovation Action · Running

f-inference Efficient Foundation Model Inference Across the Computing Continuum

Coordinator
Erevnitiko Panepistimiako Institouto Systimaton Epikoinonion Kai Ypologiston, Greece
Runs
1 October 2026 to 30 September 2029
Status
Running
EU funding
€8.0m
Total cost
€8.0m
Partners
21 organisations in 12 countries
Type
Research and Innovation Action
Grant agreement
101298393

What the project is doing

In the project's own words, from its summary on CORDIS.

Foundation Models (FMs) represent a new class of AI paradigm that is trained on broad data and is adaptable to diverse downstream tasks across multiple modalities, including text, images, audio, video, and even time-series. They enable generative AI with zero-shot and few-shot capabilities, marking a paradigm shift from task-specific AI systems. This is why FMs are the go-to solution and are getting more and more attention over the last years.

However, their adoption faces critical challenges such as i) dependence on centralized cloud infrastructures and providers, which in turn threatens digital sovereignty and data security; ii) high energy demands of running large-scale FMs that conflict with sustainability goals; iii) prohibitive costs risk excluding small and medium enterprises (SMEs) from deploying and customizing FMs tailored to their needs; iv) and reliance on remote services introducing latency and single points of failure.

To address these challenges, the f-inference project envisions a Resource-driven Computing Continuum (RCC) that enables the hyper-distribution of FMs and their deployment across Cloud, Edge, and IoT tiers. In the proposed architecture, FM inference is pushed closer to where the data resides and end-users through optimization strategies, and adaptive and efficient inference methodologies, thus reducing latency, energy consumption, and operational costs of self-deploying FMs while preserving data sovereignty at the same time.

To further demonstrate and validate the proposed methodologies, the f-inference project has employed partners in diverse domains, including Situational Awareness, Resource Management, and Advanced Industrial Systems. By democratizing access to advanced GenAI and evaluating the applicability of the proposed solutions in diverse environments, the f-inference project empowers SMEs and resource-constrained communities, increasing competitiveness and paving the way for equitable digital transformation.

Topics

Who is involved

OrganisationCityCountryRole
Erevnitiko Panepistimiako Institouto Systimaton Epikoinonion Kai YpologistonAthinaGreeceCoordinator
Fachhochschule Zentralschweiz - Hochschule LuzernLuzernSwitzerlandParticipant
Framatome GmbHErlangenGermanyParticipant
Nec Laboratories Europe GmbHHeidelbergGermanyParticipant
Nxp Semiconductors Germany GmbHHamburgGermanyParticipant
Siemens AktiengesellschaftMunchenGermanyParticipant
Aarhus UniversitetAarhus CDenmarkParticipant
TurbeLytics OÜTallinnEstoniaParticipant
Panepistimio PatronRio PatrasGreeceParticipant
Zelus IkeAthinaGreeceParticipant
Telefonica Investigacion Y Desarrollo SAMadridSpainParticipant
Tampereen Korkeakoulusaatio SrTampereFinlandParticipant
Akkodis Digital SASVilleurbanneFranceThird party
Akkodis High Tech SASLyonFranceThird party
Akkodis I&s SASGuyancourtFranceParticipant
Consiglio Nazionale Delle RicercheRomaItalyParticipant
Universita Degli Studi Di Roma La SapienzaRomaItalyParticipant
Universita Di PisaPisaItalyParticipant
TUKOREA Industry-Academic Cooperation FoundationSiheung-siSouth KoreaParticipant
Technische Universiteit DelftDelftNetherlandsParticipant
Imperial College of Science Technology and MedicineLondonUnited KingdomParticipant

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI