Triton’s ensemble feature supports many use cases where multiple models are composed into a pipeline (or more generally a DAG, directed acyclic graph). However, there are many other use cases that are not supported because as part of the model pipeline they require loops, conditionals (if-then-else), data-dependent control-flow and other custom logic to be intermixed with model execution. We call this combination of custom logic and model executions Business Logic Scripting (BLS) .
Starting from 21.08, you can implement BLS in your Python model. A new set of utility functions allows you to execute inference requests on other models being served by Triton as a part of executing your Python model. Note that BLS should only be used inside the execute function and is not supported in the initialize or finalize methods.