PyTorch's TorchScript vs torch2trt

[ar13pit]

Hi,

I wanted to know what is the difference between serializing a model with torch2trt and PyTorch's TorchScript?

Both seem to have a similar process of serialization. Although I am not sure if TorchScript supports GPUs. Any insight into this will be highly appreciated.

Thanks

[xsacha]

TorchScript does support GPUs and runs over the model with a just in time compiler.
I'd like to see the performance difference of TorchScript vs TRT because TorchScript often makes Pytorch models run up to 3x faster.

Edit: See this specific comparison with IR_50/IR152:
#86 (bottom of page)