Nvidia and Red Hat Partner on AI Container Platform

Editor’s Note: Some bigger Red Hat news broke over the weekend that we’ll be covering in detail.

Artificial Intelligence in the enterprise is at an interesting point. It essentially doesn’t really exist, but every vendor and manufacturer wants to be ready when it gets there.

That’s the kind of mentality that Nvidia and Red Hat are taking with their recently announced partnership. Essentially they are working to create an OpenShift-based container platform to run on massive server jobs using Nvidia’s GPUs.

Nvidia will start this partnership by getting RHEL running on Nvidia’s DGX-1, their rack-mounted server crammed with 8 high-end cards connected over NVLink. Down the road Nvidia will bring their GPU cloud officially to OpenShift.

Of course, all of this is laying the groundwork for when AI becomes a reality in the enterprise. Once that happens, this kind of partnership will make training advanced AI models much faster and more efficient. Given how AI-forward Nvidia has been with their new product releases, getting the OS platform lined up is the next logical step.

Source: Container Journal

About the author

Rich Stroffolino

Rich has been a tech enthusiast since he first used the speech simulator on a Magnavox Odyssey². Current areas of interest include ZFS, the false hopes of memristors, and the oral history of Transmeta.

Leave a Comment