xinference.client.Client

class xinference.client.Client(base_url, api_key: str | None = None)

__init__(base_url, api_key: str | None = None)

Methods

__init__(base_url[, api_key])
abort_cluster()
abort_request(model_uid, request_id)	Abort a request.
confirm_and_remove_model(model_version[, ...])	Remove the cached models with the model name cached on the server.
describe_model(model_uid)	Get model information via RESTful APIs.
get_model(model_uid)	Launch the model based on the parameters on the server via RESTful APIs.
get_model_registration(model_type, model_name)	Get the model with the model type and model name registered on the server.
get_supervisor_info()
get_workers_info()
launch_model(model_name[, model_type, ...])	Launch the model based on the parameters on the server via RESTful APIs.
list_cached_models([model_name, worker_ip])	Get a list of cached models.
list_deletable_models(model_version[, worker_ip])	Get the cached models with the model path cached on the server.
list_model_registrations(model_type)	List models registered on the server.
list_models()	Retrieve the model specifications from the Server.
login(username, password)
query_engine_by_model_name(model_name)	Get the engine parameters with the model name registered on the server.
register_model(model_type, model, persist)	Register a custom model.
terminate_model(model_uid)	Terminate the specific model running on the server.
unregister_model(model_type, model_name)	Unregister a custom model.
vllm_models()