triton-inference-server / server

The Triton Inference Server provides an optimized cloud and edge inferencing solution.
https://docs.nvidia.com/deeplearning/triton-inference-server/user-guide/docs/index.html
BSD 3-Clause "New" or "Revised" License
8.3k stars 1.48k forks source link

ensemble logic control #7749

Open xiazi-yu opened 1 week ago

xiazi-yu commented 1 week ago

Here is a scenario: For vehicle license plate recognition, when there is no license plate target, I want to terminate the subsequent pipeline execution early, but I still want to be able to obtain the coordinates of the vehicle. How can this logic be handled?

rmccorm4 commented 1 week ago

Hi @xiazi-yu, this is exactly the use case for Business Logic Scripting (BLS), please check it out.