Collected sources and patterns will appear here. Add from search, explore, or the patterns library.
ONNXModel -> TensorRTEngine
Compile an ONNX model graph directly on the target edge device to generate a hardware-optimized TensorRT execution engine.
Problem it solves
Pre-compiling engines on host machines leads to architecture mismatches and sub-optimal memory layouts for edge platforms like Jetson.
Consumes
Emits
The real projects this mechanism was found in. Attribution is the point — this is how the best teams actually do it.