THE PROBLEM/CHALLENGE
The development of advanced AI models for video processing and visual analytics requires enormous computing power and the ability to handle complex data in real time. Standard server infrastructure was not sufficient to enable scaling the models to the level needed for testing, optimization, and the development of new functionalities. The key challenge was how to secure resources that would allow training models on thousands of GPU cores while maintaining stability, speed, and accuracy of results. In addition to technical barriers, there was also the challenge of positioning a local project within the European context, where some of the most advanced research and industrial teams compete for resources.
SOLUTION
Through access to EuroHPC resources on the Leonardo Booster, Wasco AI first implemented the Benchmark Access phase, where the system’s performance and scalability were tested. This phase allowed the team to examine how algorithms behave in an environment with a high number of parallel processes and to identify optimization opportunities. After successfully completing the benchmarking, the project received Development Access, paving the way for the development of an advanced version of the Wasco AI system. In this phase, HPC resources are used to improve the accuracy of analysis, enable more efficient processing of large amounts of video material, and develop new algorithmic solutions. A special added value of the project is that, through the EuroHPC network, a foundation for international cooperation was created – the experiences of the Wasco AI team are now recognized by partners from other European countries, opening the door to joint projects and knowledge exchange. In addition to the computing resources, the team also benefited from the expertise of the EuroHPC support team, which greatly facilitated algorithm optimization and enabled more efficient use of the supercomputing environment.
BENEFITS
- Using EuroHPC resources enabled the Wasco AI team to overcome the limitations of local infrastructure and accelerate the development of a system with applications across different industries – from security and transportation to creative industries.
- The project has demonstrated that companies from Montenegro’s private IT sector can successfully leverage Europe’s most advanced supercomputing capacities. This represents an important milestone as it opens the door for other domestic research and industrial teams to access HPC resources, strengthens regional visibility, and encourages broader use of supercomputing in the field of artificial intelligence.
- Furthermore, the international dimension of the project positions Montenegro on the map of countries actively contributing to the development of the European AI ecosystem, while for foreign partners, Wasco AI serves as an example of an innovative and scalable solution developed in a smaller country but with the ambition to compete on the global market.