xinference.client.Client.list_cached_models

Client.list_cached_models(model_name: str | None = None, worker_ip: str | None = None) → List[Dict[Any, Any]]

Get a list of cached models. :param model_name: The name of model. :type model_name: Optional[str] :param worker_ip: Specify the worker ip where the model is located in a distributed scenario. :type worker_ip: Optional[str]

Devuelve:

The collection of cached models on the server.

Tipo del valor devuelto:

List[Dict[Any, Any]]

Muestra:

RuntimeError – Raised when the request fails, including the reason for the failure.