feat: add quantizer algorithm

[minettekaum]

Description

Added torchao_autoquant alogrithm.

• You can find the torchao_autoquant algorithm in src/pruna/algorithms/torchao_autoquant.py
• You can find the test in tests/algorithms/testers/autoquant.py

Type of Change

• Bug fix (non-breaking change which fixes an issue)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

How Has This Been Tested?

The algorithm has been tested by the test in tests/algorithms/testers/autoquant.py

Checklist

• My code follows the style guidelines of this project
• I have performed a self-review of my own code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• I have added tests that prove my fix is effective or that my feature works
• New and existing unit tests pass locally with my changes

[cursor]

Comment @cursor review or bugbot run to trigger another review on this PR

[cursor]

Bug: Autoquant assumes model.transformer always exists

model_check_fn returns True for any torch.nn.Module, but _apply unconditionally reads model.transformer. For valid inputs that are torch.nn.Module instances without a transformer attribute (or when the input is itself a diffusers transformer module), this triggers an attribute error and breaks applying torchao_autoquant.

Additional Locations (1)

• src/pruna/algorithms/torchao_autoquant.py#L57-L80