Skip to content
NetworkingIn personPast event

vLLM x NVIDIA Dynamo Meetup

Event artwork for vLLM x NVIDIA Dynamo Meetup

This event has ended

This listing is kept as an archive. Explore upcoming events to find your next one.

See upcoming events in San Francisco

Supporting this event

Sponsors

NVIDIA Dynamo
About this event

What to expect

Explore efficient, production-scale LLM inference with the vLLM community and NVIDIA Dynamo team in San Francisco on 24 August 2026.

Taking place during vLLM conference week, this evening meetup focuses on the systems, techniques and practical decisions involved in serving large language models efficiently at scale. Attendees will hear focused technical talks covering the latest work across vLLM and NVIDIA Dynamo, then have time to discuss ideas and connect with others working across the inference community.

What to expect

The programme will examine key areas of modern LLM infrastructure, including:

  • LLM inference optimisation and the work required to improve serving efficiency
  • Distributed serving with vLLM and NVIDIA Dynamo
  • The practical challenges of operating inference systems in production
  • Perspectives from the engineers, researchers and builders pushing scalable inference forward

The event is designed to be useful at different levels of experience. It welcomes people already deep in inference-engine internals as well as those beginning to explore LLM serving. The talks offer a compact technical introduction to current work, while the conversational format creates space to ask questions and compare approaches with practitioners.

Evening schedule

  • 6:00pm: Doors open
  • 6:30–6:45pm: vLLM technical talk
  • 6:45–7:00pm: NVIDIA Dynamo technical talk
  • 7:00–9:00pm: Networking, food and drinks

After the presentations, the event shifts into an informal social session. This is an opportunity to meet members of the vLLM and NVIDIA Dynamo communities, continue conversations prompted by the talks, and make connections with engineers, researchers and builders interested in LLM inference.

The meetup is presented by vLLM Meetups and Events and hosted by Joe Cotant, Yasong Wang, Amr Elmeleegy, Harry Kim, Tina Wisdom and Simon Mo.

Venue and registration

The meetup runs from 6:00pm to 9:00pm PDT on Monday, 24 August 2026 at Convene 100 Stockton, 40 O'Farrell Street, San Francisco. Space is limited, and every registration is subject to host approval, so requesting a place early is recommended.

Request to attend the vLLM x NVIDIA Dynamo Meetup

Running an AI event in San Francisco?

List it here, free.

Meetups, workshops and conferences go in front of thousands of builders after a quick review.

List your event