🐛 [Bug] aten::mul errors out for int Tensor * int

[mfeliz-cruise]

Bug Description

Currently the aten::mul converter for Tensor * Scalar assumes that the scalar value is a float. This causes errors for int Tensor * int.

GRAPH: [Torch-TensorRT - Debug Build] - graph(%in_tensor.1 : Tensor):
%2 : int = prim::Constantvalue=2
%3 : Tensor = aten::mul(%in_tensor.1, %2)
return (%3)

ERROR: [Torch-TensorRT TorchScript Conversion Context] - 4: [layers.cpp::validate::2385] Error Code 4: Internal Error (%3 : Tensor = aten::mul(%in_tensor.1, %2): operation PROD has incompatible input types Int32 and Float)

To Reproduce

Steps to reproduce the behavior:

1. Run the code below

import torch
import torch.nn as nn
import torch_tensorrt

class MulTest(nn.Module):
    def __init__(self):
        super(MulTest, self).__init__()
    
    def forward(self, in_tensor: torch.Tensor):
        return in_tensor * 2

def reproduce_error():
    torch_tensorrt.logging.set_reportable_log_level(torch_tensorrt.logging.Level.Graph)
    model = MulTest().eval().cuda()

    x = torch.randn(10, 5).int().cuda()
    test_output = model.forward(x)

    print(torch.jit.script(model).graph)
    trt_model = torch_tensorrt.compile(model, inputs=[x],  **{
            "truncate_long_and_double": True,
        })
    converted_output = trt_model.forward(x)

reproduce_error()

Expected behavior

Int Tensor * int should be a valid operation.

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

[github-actions]

This issue has not seen activity for 90 days, Remove stale label or comment or this will be closed in 10 days

[ncomly-nvidia]

Closing w/ #1095. @mfeliz-cruise please comment if this issue should stay open.