Kubernetes has become the operating system for AI. 82% of container users run it in production, and 66% of organizations hosting generative AI models use it for inference. But the hard problem isn't training models, it's…
Kubernetes has become the operating system for AI. 82% of container users run it in production, and 66% of organizations hosting generative AI models use it for inference. But the hard problem isn't training models, it's serving them to users reliably and affordably on scarce, expensive GPUs. This session explains, without deep technical detail, the open source building blocks the CNCF community offers to solve that, from smart request routing to GPU sharing with HAMi, and how teams mix and match them. We'll look at why this matters for Argentina and Latin America, and four concrete ways you can start contributing this week. Sobre Daniel Krook: Daniel Krook is the Senior Director of Developer Experience at the Cloud Native Computing Foundation (a part of the Linux Foundation). He is focused on better serving the maintainers, contributors, and users in the community of 200+ open source projects hosted by the CNCF.
Watch talk