Cover Image for vLLM x Google Cloud Meetup
Cover Image for vLLM x Google Cloud Meetup
Avatar for vLLM Meetups and Events
Join the vLLM community to discuss optimizing LLM inference!
278 Going
Registration Closed
This event is not currently taking registrations. You may contact the host or subscribe to receive updates.
About Event

We are absolutely thrilled to invite you to the first vLLM meetup of 2025 in collaboration with Google Cloud. This is the first in-person vLLM event of the year!

We are excited to invite you to the vLLM meetup hosted by Google Cloud on January 22 at Google SF Office. This event is for the growing community of vLLM users and developers to connect, share, and learn together. Both vLLM maintainers and Google Cloud engineers will present technical talks with a deep dive into our journey in optimizing LLM inference.

Refreshments: Light refreshments will be available to keep you energized throughout the event, as well as light snacks/pizza at Doors open. 

Agenda:

• 5:00 - 6:00 pm: Doors open and social hour

• 6:00 - 6:45 pm: Google Cloud's innovation around vLLM

  • Envoy innovations for GenAI Inference – Andres Guedez  

  • vLLM optimizations on Vertex AI – Ying Wang, Guangxiang Du

  • Productionizing vLLM inference service on Cloud Run – Oded Shahar

  • vLLM:TPU ongoing work and roadmap  – Brittany Rockwell

  • vLLM in Streaming framework - Challenges & Choices - Chamikara Jayalath

• 6:45 - 7:15 pm: vLLM's V1 architecture and Q1 roadmap - Woosuk Kwon, Simon Mo

• 7:00 - 7:15 pm: Q&A

• 7:15 - 8:30 pm: Social hour. This is your chance to mingle, share your experiences, ask questions, and get to know the vLLM community on a personal level.

We look forward to seeing you there!

This event will not be recorded. Slides will be shared afterward on our GitHub page.

Location
Google San Francisco - One Market Plaza
The Landmark Building, 1 Market St, San Francisco, CA 94105, USA
Avatar for vLLM Meetups and Events
Join the vLLM community to discuss optimizing LLM inference!
278 Going