As our valued NVIDIA DGX customer, we’re giving you direct access to our best practices and AI expertise through a series of live technical sessions. Get answers to your questions about DGX systems, with topics ranging from planning to deployment to ongoing optimization. The sessions are led by NVIDIA DGXperts — AI-fluent professionals who have deployed thousands of DGX systems like yours. These sessions are exclusive to DGX users, and registration links to upcoming sessions will be posted here.
Make sure you get communications on future sessions by signing up for an account on our enterprise support portal. Your NVIDIA enterprise account manager can easily add you to our portal or you can contact us dgx_info@nvidia.com
Due to overwhelming interest in the new Multi-Instance GPU (MIG) feature of DGX A100, we had three sessions that explored it in more detail. DGX A100 with MIG enables your team to support more AI workloads, right-size resources for every job, and increase overall system utilization. Check out the replay here:
Join us for our next live technical session is Friday, Feb 21 at 8am PT. Register here . Note: Registration is required and will only be approved for customers that have an active support contract.
** Why DGX for LLM Inference?**
As a result of lots of clever engineering in the AI community, it is possible to prototype LLM applications with extremely modest hardware — perhaps you’ve even chatted with an LLM on your laptop! However, production inference is far more demanding than merely generating text for a single user. In this session, you’ll learn about the demands of generative AI systems, the challenges of production inference at scale, and why the increased memory, communication, and compute capabilities of DGX systems are essential to help your LLM applications deliver the quality of service that your users demand.
If you are a DGX customer and not receiving the invitations, email dgx_info@nvidia.com.