vLLM & NVIDIA Triton User Meetup

​We are excited to invite you to the next vLLM meetup hosted by NVIDIA at Gallery 308 of the Fort Mason Center For Arts & Culture.

​​What to Expect:

• ​​Inspiring Talks: hear from vLLM and NVIDIA Triton Inference Server experts as they present recent updates and innovative advancements in the field.

• ​​Expert Insights: dive into the latest developments in vLLM. Learn about the latest Triton Inference Server features including vLLM support, Kubernetes multi-node scaling, Python in-process API, OpenAI compatible API, and performance benchmarking.

• ​​Networking Opportunities: connect with fellow AI builders, researchers, and enthusiasts to share ideas and best practices.

​Agenda: 

​4:00 - 5:30 pm: Doors open and social hour 

​5:30 - 6:30 pm: vLLM presentation

​6:30 - 7:30 pm: NVIDIA Triton Inference Server presentation

​7:30 - 9:00 pm: Networking and light refreshments

​​To get there:

​Public parking is available at the venue. Parking fee is $3/hr and $15 for the entire day. The parking fee can be paid at the kiosk. Please find your way to Gallery 308 after parking.

​​All attendees will be required to show a photo ID at the reception.