Brad Dwyer

Yeh GroundingDINO is probably a particularly perverse case given they wrote some of their own CUDA kernels that can’t possibly be supported on MPS out of the box.

What version of Jetpack are you running? Is this the original Jetson Nano from 2019 or an Orin Nano?

Have you tried [InferencePipeline](https://inference.roboflow.com/using_inference/inference_pipeline/) from our other open source repo? It handles multithreading for video and [can even handle processing multiple streams concurrently](https://blog.roboflow.com/vision-models-multiple-streams/).

Unfortunately I don't think the APIs are available (at least in the consumer drones) to be able to do that. I couldn't get the detailed telemetry needed except via the...

We don't plan to officially support this at the moment because we don't have any customers that need/use it and don't have any hardware to test with. But you should...

The CoreMLExecutionProvider is [included in the default `onnxruntime` wheels](https://github.com/microsoft/onnxruntime/pull/17844) for MacOS since the 1.17 release last year. You should get MPS acceleration by enabling it in the settings. We do...

The code snippet you posted should already work natively (and the error message you posted noted it's using the CoreML Execution Provider out of the box). Without any additional context,...

Closing for now since stale; will re-open if we want to revive it.

Any update on 3.13 support? I believe mediapipe is the last of our dependencies holding us back on supporting it now that PyTorch supports it.

@capjamesg - looks like the deploy-quickstart page is out of date. Could you update it to use `get_model` (or maybe `get_roboflow_model`.. not really sure the difference w/o digging in deeper)...