Avatar for vLLM Meetups and Events
Join the vLLM community to discuss optimizing LLM inference!
172 Went
Registration
Past Event
Please click on the button below to join the waitlist. You will be notified if additional spots become available.
About Event

​vLLM Inference Meetup in Vienna

​Hosted by Red Hat AI, NVIDIA, NTS, and Canva, this event takes place on 12 March 2026 in Vienna, Austria.

​Huge thank you to NTS Netzwerk Telekom Service AG for providing the venue for this meetup. Join their NTS Data Day before the meetup; learn more here.

​What to Expect

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

  • ​Live demos focused on real workflows

  • ​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 – 17:00 — Hands-On Workshop: Latest GenAI Compressing Techniques in Practice

​Meetup Program (Subject to More Awesomeness)

​17:00 – 17:30 — Doors Open, Check-In

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

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

​17:40 – 18:00 — Intro to vLLM and Project Update

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

​18:00 – 18:20 — Transforming LLM Quantization

​Dan Alistarh, Professor at ISTA & Researcher, Red Hat AI

​18:20 – 18:40 — A Brief Tutorial on Speculative Decoding

​​Eldar Kurtić, Principal Research Scientist, Red Hat AI & ISTA

​18:40 – 19:10 — Tackling Inference at Scale with vLLM, NVIDIA Dynamo, and llm-d

​AI Engineers from Red Hat AI and NVIDIA

​19:10 – 19:20 — Coffee & Tea Break

​19:20 – 19:40 — Communications in MoE architectures

​Dan Blanaru, AI DevTech Engineer, NVIDIA

​19:40 – 20:00 — Real-World vLLM Case Study from Canva: Wins and Challenges in Hosting LLMs for 260 Million Monthly Users

​Georg Narodoslawsky, MLOps Engineer, Canva

​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 Vienna

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

​See you soon!

Location
NTS NETZWERK TELEKOM SERVICE AG
Trabrennstraße 2b, 1020 Wien, Austria
Exact meetup address: NTS Office Vienna 7th floor Trabrennstraße 2b 1020 Vienna
Avatar for vLLM Meetups and Events
Join the vLLM community to discuss optimizing LLM inference!
172 Went