AI_dev: Open Source GenAI & ML Summit Europe 2025

This issue has plagued Kubernetes for nearly 8 years: K8s issue #52757. The challenge of flexibly sharing GPUs across multiple containers is particularly prominent in AI scenarios, where inference tasks are typically short-lived. As a result, resource utilization becomes a critical concern.

Red Hat integrates and supports both kServe and vLLM in its MLOps Platform, OpenShift AI. In addition, Red Hat's engineers actively contribute on kServe and vLLM upstream projects everyday.

AI is evolving beyond the cloud—and into the browser. This talk explores how recent advances in Web AI are making it possible to run powerful machine learning models for language, vision, and personalization directly on the client side. Leveraging technologies like WebGPU and WebAssembly, frameworks such as ONNX.js and WebLLM are enabling real-time, private, and serverless inference right where users are. We'll demonstrate how this shift improves latency, enhances user privacy, and removes infrastructure barriers—bringing scalable, intelligent experiences to the open web. This talk will promotes open-source, privacy-first AI that reduces cloud dependency, lowers entry barriers, and encourages ethical, accessible AI development across devices.

In my session, I will discuss the topic of emotion estimation from facial expressions using AI and computer vision.

Generative AI applications present unique challenges, from unpredictability in responses to ensuring reliability in production.

What happens when you combine real radar images of Venus, a bunch of volcanoes, and deep learning? In this talk, I’ll walk you through a fully open-source machine learning pipeline that turns extraterrestrial data into structured scientific insights. Our goal is to automatically recognize geological formations like craters, ridges, or volcanoes on radar imagery — a bit like Google Maps, but for another planet.

Sentiment analysis is easy—until sarcasm enters the chat. Traditional natural language processing models often stumble when trying to decode sarcastic nuances, missing crucial contextual cues and delivering misleading results. To tackle this, we will explore a multi-modal approach that integrates facial expression analysis with textual inputs, dramatically improving accuracy in sentiment detection, particularly for sarcasm. By combining transformer-based NLP models and facial landmark detection, we create a richer, context-aware understanding of sentiment.

In today's increasingly complex and dynamic network environments, traditional monitoring and management approaches often fall short. Artificial intelligence offers immense potential to revolutionize network operations, security, and optimization. This session will introduce Essedum, an open-source framework designed specifically to empower developers and network engineers to build intelligent AI applications for network analysis, automation, and prediction.