An animated book
Operationalizing Large Language Models · after the book by Roland Huß and Daniele Zonca (O’Reilly, early release)
For the Kubernetes and platform engineers who now have to run LLMs: how a model server is deployed, where the model data lives, what the inference metrics mean, how GPUs become schedulable, and what production asks for. Eight chapters, two hours, drawn and narrated.
Every work cited in the lessons.