Applied AI·Local and self-hosted inference

you put the loaded model behind an OpenAI-shaped HTTP API with queueing and health checks, and your client code stops caring which engine is underneath.

Model server / serving

Also calledserving

Draft summary, pending review

Exposing a loaded model over an API with batching, queueing and health checks; the OpenAI-compatible API shape has become the de facto local standard, so client code ports across engines. Everything you know about running services applies from here.