Function TRITONSERVER_ServerModelIndex

• Defined in File tritonserver.h

Function Documentation

TRITONSERVER_Error *TRITONSERVER_ServerModelIndex(TRITONSERVER_Server *server, uint32_t flags, TRITONSERVER_Message **model_index)

Get the index of all unique models in the model repositories as a TRITONSERVER_Message object.

The caller takes ownership of the message object and must call TRITONSERVER_MessageDelete to release the object.

If TRITONSERVER_INDEX_FLAG_READY is set in ‘flags’ only the models that are loaded into the server and ready for inferencing are returned.

Return

a TRITONSERVER_Error indicating success or failure.

Parameters

• server: The inference server object.

• flags: TRITONSERVER_ModelIndexFlag flags that control how to collect the index.

• model_index: Return the model index message that holds the index of all models contained in the server’s model repository(s).