I assumed model conversion worked like compilation. It doesn't.

Fri, 20 Feb 2026 11:00:00 -0600

I sit at an M3 Max MacBook Pro that runs x86 Docker images through Rosetta. I’ve spent my career watching architecture boundaries dissolve.

So when the ML engineer told me the TensorRT model conversion had to run on the Jetson — the actual ARM edge device, not the x86 GPU server sitting next to it — I assumed it was cargo cult.

It wasn’t.

The pipeline

We were shipping an RT-DETR object detection model to NVIDIA Jetson Orin devices on drones.

Jetson on ferkakta.dev

I assumed model conversion worked like compilation. It doesn't.

The pipeline