feat: Autocast

[zewenli98]

Description

Weak typing behavior in TensorRT is deprecated. However it is a good way to maximize performance. Therefore, we want to create similar PyTorch native system to use with Torch-TensorRT that recovers some of this behavior.

Fixes #3869

Type of change

• New feature (non-breaking change which adds functionality)

Checklist:

• My code follows the style guidelines of this project (You can use the linters)
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas and hacks
• I have made corresponding changes to the documentation
• I have added tests to verify my fix or my feature
• New and existing unit tests pass locally with my changes
• I have added the relevant labels to my PR in so that relevant reviewers are notified

[peri044]

Can you also update the documentation at https://github.com/pytorch/TensorRT/blob/main/docsrc/user_guide/mixed_precision.rst

[narendasan]

For Tests

1. Should external autocast in pytorch with strong typing
2. Whole graph autocast pass
3. a test case that exercises max_output_threshold fallback

L1 or L2 tests

[narendasan]

Nice its looking good, some final polishing details then I think its good to go