Cover Image for Paris vLLM Meetup
Cover Image for Paris vLLM Meetup
Avatar for vLLM Meetups and Events
Join the vLLM community to discuss optimizing LLM inference!
30 Going
Registration
Approval Required
Your registration is subject to approval by the host.
Welcome! To join the event, please register below.
About Event

Join Us for the vLLM Inference Meetup in Paris!

Hosted by Red Hat, AMD, and Hugging Face, this event takes place on 19 November 2025 in Paris and brings together vLLM users, developers, and AI engineers to explore the latest in GenAI inference.

​Learn from the vLLM Team

​Hear directly from leading vLLM committers and users shaping the project’s roadmap and building its most advanced features. Expect deep technical talks, live demos, and plenty of time to connect with the community.

[Optional] Developing Multi-Model Multi-Agent Systems

Our official vLLM meetup begins at 17:00 (see agenda below). Before the main session, join Red Hat and AMD at 16:00 for a beginner to intermediate level, instructor-led, hands-on GPU workshop where you will learn how to set up an OpenAI compatible endpoint to serve multiple models concurrently using vLLM and build multi-agent applications to deliver real-world applications. The workshop culminates with a short application development challenge. Doors open at 15:30 for the workshop. Space is limited — indicate your interest by selecting the workshop option during registration.

vLLM Meetup Agenda (Subject to Change & More Awesomeness)

17:00 – 17:30 — Doors Open, Snacks & Drinks

17:30 – 17:40 — Welcome & Opening Remarks

Erwan Gallen, Technical Product Manager, Red Hat AI

17:40 – 18:00Introduction to vLLM & llm-d

Christopher Nuland, Principal TMM, Red Hat AI

18:00 – 18:20 — vLLM inference optimization on AMD GPUs

Learn how vLLM can be optimized on a variety of AMD GPUs

18:20 – 18:40Hugging Face & vLLM

Hugging Face to be announced soon

18:40 – 19:00 — Break

19:00 – 19:30Scaling LLM Inference on Kubernetes: Fast, Cost-Efficient, Production-Ready with vLLM

Roberto Carratalá, Principal AI Platform Architect, Red Hat AI

19:30 – 19:50Disaggregated Serving for Large-Scale MoE Models

Nicolo Lucchesi, vLLM Core Committer & Sr. Software Engineer, Red Hat AI

19:50 – 20:00 — Group Q&A / Lightning Panel

20:00 – 21:00 — Networking, Food & Drinks

​Important Information

Registration Deadline: Registration closes 24 hours prior to the event. We will be unable to admit any attendees who are not registered.

Check-In: Please bring a photo ID to verify your registration upon arrival.

​We look forward to seeing you there!

Location
LANDSCAPE
6 Pl. des Degrés, 92800 Puteaux, France
Avatar for vLLM Meetups and Events
Join the vLLM community to discuss optimizing LLM inference!
30 Going