🐛 [Bug] Flux perf scripts issue

Bug Description

1) Add a README,md with clear instructions on how to run this. Also add `pip install gradio` or any other deps required to the README.  The instructions need to cover all cases (with and without DS)

2) Fix parse_args import error 

3)  Fix the following error 

Error : File "/root/.pyenv/versions/3.11.13/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1767, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/root/.pyenv/versions/3.11.13/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1778, in _call_impl
    return forward_call(*args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/work/TensorRT/py/torch_tensorrt/dynamo/runtime/_PythonTorchTensorRTModule.py", line 714, in forward
    return run_standard_execution()
           ^^^^^^^^^^^^^^^^^^^^^^^^
  File "/work/TensorRT/py/torch_tensorrt/dynamo/runtime/_PythonTorchTensorRTModule.py", line 460, in run_standard_execution
    self.setup_input_tensors(
  File "/work/TensorRT/py/torch_tensorrt/dynamo/runtime/_PythonTorchTensorRTModule.py", line 374, in setup_input_tensors
    contiguous_inputs[i].dtype == self.input_dtypes[i]
AssertionError: Dtype mismatch for 0th input(timestep). Expect dtype.f16, got torch.float32

To Reproduce

Steps to reproduce the behavior:

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