Madrid vLLM & llm-d AI Inference Meetup
vLLM & llm-d Meetup Madrid with Red Hat and NVIDIA
Join us for the vLLM & llm-d meetup in Madrid, hosted by Red Hat and NVIDIA. It's an evening for AI engineers, researchers, and infrastructure builders working on open source inference.
vLLM is the leading open source engine for fast, efficient LLM serving, and llm-d brings vLLM to Kubernetes for distributed inference at scale. Together they form an open stack for running models in production, from a single GPU to a full cluster.
You'll connect with Red Hat and NVIDIA engineers and leave with:
A practical grounding in vLLM, including model compression with LLM Compressor and speculative decoding with Speculators
A look at serving text, image, audio, and video models with vLLM-omni
Patterns for building agentic systems on open source technology
A clear picture of how vLLM and llm-d scale inference on Kubernetes
We'll close with an open Q&A, then finish the evening with networking, food, and drinks.
Agenda (Subject to More Awesomeness)
18:00 - Doors open and check-in
18:30 - Intro to vLLM: Fast and Efficient Open Source Inference
Nelson Paez, AI Specialist Solution Architect, Red Hat
19:00 - Easy, Fast, and Cheap Omni-Modality Model Serving with vLLM-omni
Ricardo Noriega, Initiative Tech Lead, Office of the CTO, Red Hat
19:30 - Building Safe Agentic Systems with Open Source Technology
Tobias Fischer, AI Developer Technology Engineer, NVIDIA
20:00 - Distributed Inference at Scale on Kubernetes with llm-d
Roberto Carratalá, Principal AI Platform Architect, Red Hat
20:30 - Q&A and open discussion
21:00 - Networking, food, and drinks
22:00 - Close
Important information
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 Madrid
If you are building, deploying, or scaling inference, this is the room to be in.
See you soon!