AI Developer Meetup @Station F

​​Join us for an AI Developers in Paris meetup, an evening of talks and demos for developers eager to explore AI.

​​This event is an opportunity to showcase projects, learn from experts, and partake in insightful discussions.

​Agenda

• ​18:30 - Doors Open 👋

• ​19:00 - Meeting kick-off 💫

• ​🎤 🧑‍💻 Amine Saboni - MLOps Engineer @Pruna AI
  Why quantization works? We'll see in this talk what is the impact of quantization on model weights, how they are loaded in the GPU RAM memory and how GPU kernel tricks effectively reduce computations at inference time, to speed up tokens generation.

• ​ 🎤 🧑‍💻 Yann Leger - Co-founder @Koyeb
  Optimizing AI inference for Production

• ​🎤 🧑‍💻 Sören Dréano - ML Engineer @Numind AI
  Inference Performance Benchmarks: Discover how NuMind is providing efficient API access to NuExtract 2.0 72B - their most recent LLM specialized in extracting structured information from documents.

• ​🎤 🧑‍💻 Samir Akarioh - DevRel @Gatling
  Inference efficiency: Load testing LLM APIs
  

​​See you at this great meetup in Paris, where you can connect with the AI community and hear about the latest developments from leaders in the space!