Operations | Monitoring | ITSM | DevOps | Cloud

Running a startup means every resource counts, especially when it comes to expensive GPUs. In this video, we break down proven GPU hacks to help you get maximum AI performance at minimum cost. Learn how to choose the right hardware, use pre-trained models, leverage quantization, adopt CPU-efficient frameworks, and make the most of affordable GPU providers. Whether you’re prototyping, training, or deploying AI models, these strategies will help you deliver big results without a big budget.

Looking to kickstart your journey? Hear from Gunasekhar Matamalam, Senior Engineering Manager at @SUSE about how you can simplify your local development with the extension on Rancher Desktop.

This Product Klip covers Komodor's cost optimization features, highlighting how the platform helps users reduce Kubernetes spending while maintaining operational stability. Key features discussed include: Before activation, Komodor provides simulations of potential savings, and for activated clusters, it shows CPU and memory usage before and after Komodor's bin packing and the resulting dollar savings. Komodor enhances existing autoscalers rather than replacing them, unlocking up to 40% in additional savings.

Meet Dustin Kirkland, VP of Engineering at Chainguard. Dustin shares his fascinating 26-year journey in the tech industry, from IBM and two stints at Canonical to roles at Google (working on GKE), Apex, and Goldman Sachs, eventually leading him back to engineering at Chainguard.

Learn more about the core components of the OPEA project under @LinuxfoundationOrg with Katherine Druckman.

In this video we’ll demonstrate how to use Splunk’s AlwaysOn Profiler to identify and fix a performance bug in a Java web application running on Kubernetes.