Closed
Description
Hi,
I got the following error when run //cpp/trtorchexec for my own jit graph model.
ERROR: [TRTorch - Debug Build] - Method requested cannot be compiled by TRTorch.
Unsupported operators listed below:
- aten::Int.Tensor(Tensor a) -> (int)
- aten::floor.int(int a) -> (int)
- aten::transpose.int(Tensor(a) self, int dim0, int dim1) -> (Tensor(a))
You can either implement converters for these ops in your application or request implementation
https://www.github.com/nvidia/TRTorch/issues
Method is not currently supported by TRTorch