When is CoreWeave x NVIDIA Dynamo Meetup?

CoreWeave x NVIDIA Dynamo Meetup takes place on Friday, October 16, 2026 from 3:00 AM to 6:00 AM (America/Los_Angeles).

Where is CoreWeave x NVIDIA Dynamo Meetup held?

CoreWeave x NVIDIA Dynamo Meetup takes place at San Francisco, United States.

How much does CoreWeave x NVIDIA Dynamo Meetup cost?

CoreWeave x NVIDIA Dynamo Meetup is free to attend. Register on the event page to secure your spot.

Who is organising CoreWeave x NVIDIA Dynamo Meetup?

CoreWeave x NVIDIA Dynamo Meetup is organised by NVIDIA. You can find more of their events on Rifio.

How many people are attending CoreWeave x NVIDIA Dynamo Meetup?

88 people have registered so far out of 88 available spots.

How do I register for CoreWeave x NVIDIA Dynamo Meetup?

You can register for CoreWeave x NVIDIA Dynamo Meetup through the original event page on Luma. Click the "View on Luma" button above, or save it to your Rifio account to get reminders.

How long is CoreWeave x NVIDIA Dynamo Meetup?

CoreWeave x NVIDIA Dynamo Meetup runs for approximately 3 hours, from 3:00 AM to 6:00 AM (America/Los_Angeles).

CoreWeave x NVIDIA Dynamo Meetup

Name: CoreWeave x NVIDIA Dynamo Meetup
Start: 2026-10-16T01:00:00+00:00
End: 2026-10-16T04:00:00+00:00
Location: San Francisco

About this event

Overview

Join CoreWeave and NVIDIA Dynamo for an evening on the infrastructure behind production inference and reinforcement learning post-training.

In RL post-training, training and inference start to blend together. The policy generates rollouts, training produces new weights, and those weights need to be serving again before the next round can start. How fast that loop turns depends on how quickly your inference stack can pick up a new checkpoint.

We'll start with the recent CoreWeave Forge launch from Fully Connected 2026. One new piece is RL Rollouts on CoreWeave Dedicated Inference, built on NVIDIA Dynamo. It hot-loads updated checkpoints into a live deployment with minimal downtime, so each round of rollouts uses the latest policy. CoreWeave, NVIDIA and You.com used it to post-train NVIDIA Nemotron 3.5 Lightning with RL in NeMo Gym, using You.com's web search API. Model reload latency improved 15x over baseline.

This meetup is for developers and researchers building and scaling inference and post-training systems. Topics include high-throughput serving, disaggregated inference, efficient rollouts, weight hot-swapping, SFT and RL pipelines, and closing the loop from production signal to a better model. Expect technical talks, real lessons from teams running these systems, and plenty of time to connect.

Agenda:

6:00 pm: Doors open
6:30 pm: CoreWeave talk: CoreWeave Forge: from production inference to post-training
6:45 pm: NVIDIA Dynamo talk: Inference at scale and fast weight updates for RL rollouts
7:00–9:00 pm: Mingle with fellow developers!

Resources and Legal

NVIDIA Privacy Policy: https://www.nvidia.com/en-us/about-nvidia/privacy-policy/

Create a free account to see descriptions, save events, and more

About CoreWeave x NVIDIA Dynamo Meetup in San Francisco

CoreWeave x NVIDIA Dynamo Meetup is a free independent taking place on Friday, October 16, 2026 at San Francisco, United States. This independent is organised by NVIDIA. Attendance is free — register to secure your spot. Currently 88 people have registered out of 88 spots. The event runs for approximately 3 hours.