🐛 [Bug] Half precision index tensor detected when converting `mistralai/Mistral-7B-v0.3`

Bug Description

mistralai/Mistral-7B-v0.3 is not fully supported because the index inputs to torch.ops.aten.index.Tensor are half-precision according to the fake tensor metadata.
 

To Reproduce

torch.compile and run inference on the mistralai/Mistral-7B-v0.3 model

Expected behavior

The graph consists of 2895 Total Operators, of which 2831 operators are supported, 97.79% coverage

The following ops are currently unsupported or excluded from conversion, and are listed with their op-count in the graph:
 torch.ops.aten.index.Tensor: 64

Environment

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

• Torch-TensorRT Version (e.g. 1.0.0): 2.3.0
• PyTorch Version (e.g. 1.0): 2.3.1+cu121
• Transformers Version: 4.40.2

Start by reproducing the issue with torch.compile on mistralai/Mistral-7B-v0.3 using the reported PyTorch, Transformers, and Torch-TensorRT versions. Inspect the fake tensor metadata for torch.ops.aten.index.Tensor and compare the resulting operator coverage with the reported 2,895-operator graph; done means the half-precision index inputs no longer prevent the model conversion.