Paris first inference & vLLM meet-up

​Join us for the first inference & vLLM community meet-up in Paris, bringing together AI practitioners, infrastructure experts, and companies using vLLM in production.

​Whether you're experimenting with vLLM or running large-scale inference workloads, this event is for you. Expect hands-on insights, real-world feedback, and open discussions with others working on optimizing inference at scale.

​📍 Location: Paris, France
🌎 Language: English
🕖 Time: 7:00PM – 10:00PM [Updated end time]
💬 Format: In-person

​Agenda:

• ​7:00 – 7:30 PM: Welcome

• ​7:30 – 8:30 PM: Talks

  • ​Exxa – Etienne Balit (CTO): Intro to vLLM

  • ​AMD – Félix Marty (ML/SW): Quantization on AMD Instinct

  • ​Scaleway – Grégoire de Turckheim (Engineering Manager): Deploying vLLM at scale (5,000+ GPUs)

• ​8:30 – 10 PM: Open networking & drinks + pizzas

​We’ll discuss performance optimizations, scaling strategies, hardware compatibility, and more.

​🎯 Who should come?
ML engineers, infra & DevOps teams, AI founders, and anyone using or evaluating vLLM in their stack.

​🎟️ Free registration – spots are limited (first edition)