vLLM x NVIDIA Dynamo Meetup

Join the vLLM community and the NVIDIA Dynamo team for an evening of tech talks and conversation during vLLM conference week.

We'll dig into what it takes to serve LLMs efficiently at scale—covering the latest work across vLLM and NVIDIA Dynamo, from inference optimization and distributed serving to the practical challenges of running these systems in production. After the talks, stick around to connect with engineers, researchers, and builders from across the inference community over food and drinks.

Whether you're deep in the internals of an inference engine or just getting started with LLM serving, come learn, ask questions, and meet the people pushing this work forward.

When: Monday, August 24 · 6-9pm PT

Schedule:

• 6:00pm: Doors open

• 6:30-6:45pm: vLLM tech talk

• 6:45-7pm: Dynamo tech talk

• 7-9pm: Socialize and mingle!

Space is limited and registration is subject to approval—reserve your spot early.