PyTorch model with Nvidia Inference Server

1

I want to run my PyTorch model over Nvidia Inference Server with high performance. Instead of convert PyTorch model to Torch Script, is it possible to convert pytorch -> onnx -> tensorrt -> nvidia inference server? Which one is better for performance?

2

If I’m not mistaken, ONNX uses TorchScript under the hood, so you won’t be able to directly export to ONNX.
Please correct me, if I’m wrong.