Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
OrchestrationScript, InputTensors -> OutputTensors
Execute custom model-orchestration scripts that dynamically invoke other models based on intermediate inference outputs.
Problem it solves
Static pipeline configurations cannot express conditional branching, loops, or complex pre/post-processing logic.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.