LLM-D a Cloud Native Kubernetes based high-performance distributed LLM inference framework. Its architecture focuses on a well-lit path for serving llms at scale, with competitive performance for most models across a wide set of accelerators.

The audience will learn the safety precautions you have to take when running models that generate code or use a browser (Computer use models) and how to run them safely

Learn how KRO allows platform teams to tame Kubernetes complexity using a simple tool. KRO alleviates the pain of managing CRDs while providing teams with ready-to-use recipes for apps and dependencies.