ito-inference

Reports that Itô inference serving is unavailable and provides a documentation handoff without authenticating or invoking commands.

When to use it

Use after ito-compute has booked GPU nodes when the user requests an OpenAI-compatible endpoint, ito-serve, hosted Kimi, or self-hosted open-weights inference.

Ask for inference serving on booked Itô compute; it reports the missing capability and returns a documentation handoff rather than launching a workload.