Avatar for vLLM Meetups and Events
Join the vLLM community to discuss optimizing LLM inference!
193 Went
Registration
Past Event
Welcome! To join the event, please register below.
About Event

​vLLM Inference Meetup in Warsaw

​Organized and sponsored by JetBrains AI in collaboration with Red Hat AI and NVIDIA, this event takes place on 10 March 2026 in Warsaw, Poland.

​What to Expect

  • ​Deep technical sessions from vLLM maintainers, committers, and teams using vLLM at scale

  • ​Live demos focused on real workflows (local, cloud, IDE integrations, omni-modality, Kubernetes)

  • ​Hands-on workshop option earlier in the day

  • ​Great networking with food and drinks

​Who Should Attend

  • ​vLLM users and contributors

  • ​ML and infra engineers working on inference and serving

  • ​Platform teams running GenAI in production

  • ​Anyone curious about efficient inference across local, cloud, and Kubernetes

​Agenda

​Optional Workshop

​15:30 — Doors Open (Workshop Attendees)

16:00 – 17:15 — Hands-On Workshop: Latest GenAI Compressing Techniques in Practice

​Meetup Program

​17:15 – 17:45 — Doors Open, Check-In

17:45 – 17:55 — Welcome and Opening Remarks

​Saša Zelenović, Sr. Manager of Developer Marketing & Advocacy, Red Hat AI

​Damian Bogunowicz, Sr. ML Engineer, JetBrains AI

​17:55 – 18:15 — Intro to vLLM and Project Update

​Michael Goin, vLLM Core Committer and Principal Engineer, Red Hat AI

​18:15 – 18:35 — Powering JetBrains IDE Features with AI

​JetBrains AI Team

​18:35 – 18:55 — Demo: Next Edit Suggestion (NES), Using vLLM to Enable Local and Cloud-Based Edits

​JetBrains AI Team

​18:55 – 19:15 — CPU Weights Offloading in vLLM with FlexTensor

​Blazej Kubiak, Sr. Deep Learning Software Engineer, NVIDIA

​19:15 – 19:25 — Coffee Break

​19:25 – 19:45 — Intro to vLLM-Omni: Easy, Fast, and Cheap Omni-Modality Model Serving

​Nicolò Lucchesi, vLLM Core Committer and Sr. Software Engineer, Red Hat AI

​19:45 – 20:00 — Scaling LLM Inference on Kubernetes with llm-d: Fast, Cost-Efficient, Production-Ready with vLLM

​Michael Goin, vLLM Maintainer and Principal Engineer, Red Hat AI

​20:00 – 21:00 — Networking, Food and Drinks

​Important information

​Agenda is subject to change. We may add extra demos or lightning updates.

​Registration closes 24 hours before the event. We cannot admit unregistered attendees.

​Please bring a photo ID to verify your registration on arrival.

​See you in Warsaw

​If you are building, deploying, or scaling inference, this is the room to be in. See you soon!

Location
Crowne Plaza Warsaw - the Hub by IHG
rondo Ignacego Daszyńskiego 2, 02-843 Warszawa, Poland
Avatar for vLLM Meetups and Events
Join the vLLM community to discuss optimizing LLM inference!
193 Went