🐛 [Bug] 0-D Tensor input for TensorRT subgraph is usually on cpu, not cuda

[Njuapp]

Bug Description

When encountered aten::Int operations, the graph is usually partitioned, and the TensorRT subgraph may accept a 0-D Tensor as its input. This 0-D Tensor input is usually put on CPU, not cuda, as it is done so on Torchscript/Torch.

To Reproduce

Traceback (most recent call last):
File "reproduce.py", line 39, in
trt_output = trt_model(img_input)
File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
RuntimeError: The following operation failed in the TorchScript interpreter.
Traceback of TorchScript (most recent call last):
RuntimeError: [Error thrown at core/runtime/execute_engine.cpp:87] Expected inputs[pyt_idx].is_cuda() to be true but got false
Expected input tensors to have device cuda, found device cpu

Expected behavior

Environment

Build information about Torch-TensorRT can be found by turning on debug messages

• Torch-TensorRT Version (e.g. 1.0.0):
• PyTorch Version (e.g. 1.0):
• CPU Architecture:
• OS (e.g., Linux):
• How you installed PyTorch (conda, pip, libtorch, source):
• Build command you used (if compiling from source):
• Are you using local sources or building from archives:
• Python version:
• CUDA version:
• GPU models and configuration:
• Any other relevant information:

Additional context