Tal Wald
Tal Wald
Is there current work on this?
@AngledLuffa We saw that if you run the models directly on onnx runtime or TensorRT that you get a 2X-4X improvement in the inference runtime - which is critical for...
@michaelfeil I agree that the issue you mentioned is a blocker - however, by removing the dependency on torch you will enable people to choose what framework to use without...
I'll add that I can't find any official docker files for use on docker hub ☹