Make Long-Running NVIDIA TensorRT Engine Builds Observable and Cancelable in Python or C++ | NVIDIA Technical Blog

This post details the implementation of `IProgressMonitor` in Python and C++ for TensorRT engine builds. It demonstrates how to subclass `IProgressMonitor` to provide nested progress reporting and cancellation capabilities. The implementation includes thread-safe state management, rendering of nested ASCII progress bars using virtual-terminal escapes, and integration with the `IBuilderConfig`. The post highlights the `step_complete` method as the primary mechanism for cancellation, allowing builds to be aborted via Ctrl-C or programmatic signals.