merge(happy_hour) -> open_inference

Luma Event Link Keep the conversation going after Ray Summit and the vLLM Conference. A year ago, open weights were a cost play: worse performance, cheaper price. Intelligence is the product now, and companies want to own it and compound it inside their own walls. This is a night for that shift: owning your intelligence, staying open across hardware and models, and valuemaxxing every dollar and hour of infra. Join a select group of founders, engineers, and operators, and builders for demos worth watching, good conversation, and cold drinks in a room full of people who take tokens seriously. Speakers • Balaji Varadarajan, Staff Engineer of Inference Services, DigitalOcean — "Maximize intelligence/dollar w/Inference Router" • Wenwen Gao, Sr. Product Manager, NVIDIA — "Day 0 Post-Training on Open Models" • Zachary Xi, Founding Product Manager, Inferact — "vLLM roadmap" • More co-hosts and speakers to come!* Agenda • 6:00 PM — Doors, drinks, bites • 6:30 PM — Lightning talks + live demos • 7:30 PM — Open bar, more bites & conversation • 8:30 PM — Doors close Hosted by DigitalOcean, NVIDIA, Inferact, and Nous Research More co-hosts and speakers to come. RSVP now and we'll keep you posted. Registration This one's for the AI-native builders. Space is limited. Request to join below. Note Alcohol will be served at this event. Attendees must be 21 or older and will be asked to present valid government-issued photo ID at check-in. Non-alcoholic options will be available. DigitalOcean is the organizer of this event and will use the information you provide to register you, communicate with you about the event, and manage on-site logistics. See the DigitalOcean Privacy Policy for how we handle your information and your privacy rights. location provided by event source: "Yerba Buena" ―――――――――― SF Stuff To Do