How many compagnies can manage a mostly stateless workload at "whatever-the-scale-because-it-does-not-matter-because-stateless" ? Lots of people can do that. Massive amount of people can do that.
I think you mean mostly-stateless-but-with-prompt-caching-and-batching, ie not really
The workload is anything besides stateless
I think you mean mostly-stateless-but-with-prompt-caching-and-batching, ie not really