AI_dev: Open Source GenAI & ML Summit Europe 2025

In the rapidly evolving landscape of artificial intelligence, Vision-Language Models (VLMs) have emerged as powerful tools capable of understanding and interpreting both visual imagery and natural language. In this talk, we’ll dive into VLMs and how they work without getting bogged down in tech jargon. 

In October 2024 the Open Source Initiative (OSI) unveiled the Open Source AI Definition (OSAID) v.1, concluding a multi-year, world-wide community effort.

Recent research has raised concerns about LLM-generated code exhibiting significant similarity to their training data, raising potential legal issues with incompatible software licenses. While Xu et al. established a benchmark for evaluating this phenomenon through their LiCoEVAL benchmark, showing small but significant portions of LLM outputs containing "notably similar" code to existing open-source implementations, these findings were limited by the scope of their reference dataset.

Enabling LLMs to improve their outputs by using more test-time computation is a critical step towards building generally self-improving agents that can operate on open-ended natural language. The scaling of inference-time computation in LLMs, with a focus on answering the question: if an LLM is allowed to use a fixed but non-trivial amount of inference-time compute, how much can it improve its performance on a challenging prompt? Answering this question has implications not only on the achievable performance of LLMs, but also on the future of LLM pretraining and how one should tradeoff inference-time and pre-training compute. Despite its importance, little research attempted to understand the scaling behaviors of various test-time inference methods. 

In this 1-hour workshop, participants will have the opportunity to learn how to achieve robust observability for Large Language Models (LLMs) while safeguarding sensitive data. As LLMs become integral to production systems, monitoring their performance, usage, and costs is essential, and so is protecting user privacy! This session addresses these challenges using open-source tools such as OpenTelemetry + OpenLIT, and Prometheus + Grafana.

With the rise of on-device intelligence, the push to run LLMs on edge hardware — phones, Raspberry Pis, even microcontrollers — is accelerating. At the heart of this revolution is quantization: the art of shrinking models without shrinking their intelligence.

Unlock the insights hidden within unstructured PDF documents! Many PDFs contain multimodal elements like text, tables, and images, and relying solely on text-based processing risks overlooking critical information. This session explores two powerful approaches to address this challenge: building specialized pipelines that integrate OCR and ML models for handling diverse modalities, and leveraging cutting-edge Vision-Language Models like ColPali to represent multimodal data in a unified format. Join us to discover how both methods can be applied to build an intelligent conversational search application using open-source technology, OpenSearch by leveraging it's its powerful search and ingest pipelines. The session includes a live demonstration to showcase practical implementations, empowering you to choose the approach that best fits your needs!

In recent years, generative AI models have come to dominate the discourse around artificial intelligence and machine learning.

Running open models like LLaMA, Whisper, etc has traditionally required heavyweight runtimes, containerization, or cloud resources. However, as LLMs are increasingly deployed in edge environments, desktop apps, and dev boards, there's a growing need for lighter, more portable execution environments. 

It’s no secret that for a long time machine learning has been mostly a Python game, but the recent surge in popularity of Gen AI has brought many new developers into the field. With JavaScript being the most widely-used programming language, it’s no surprise that this has included many web developers.

OpenSearch has evolved from search to a powerful vector database solution. This talk will begin by explaining the transition from traditional lexical search to vector-based similarity search, and how OpenSearch combines both approaches in one complete package. 

Generative AI has made headlines with large models powering everything from chatbots to image synthesis—but these advancements usually rely on heavyweight cloud infrastructure. InfiniEdge AI is an open-source edge AI framework (under LF Edge) that enables those same powerful generative models to run on edge devices and distributed edge clouds. This talk will explore how InfiniEdge AI brings generative AI capabilities closer to users, enabling real-time responses, improved privacy (since data stays on device), and reduced latency even in offline or bandwidth-constrained environments. We’ll dive into the architecture of InfiniEdge AI and show how it optimizes large language models (LLMs) and other generative models through techniques like model compression and efficient inferencing on resource-constrained hardware. Attendees will see demos of edge-based AI (e.g., running a mini GPT-style assistant on a phone) and learn how open-source collaboration is accelerating GenAI innovation beyond the data center.

Okay, so Platform Engineering blew up around the same time AI did, right?