[quant][pt2e][quantizer] Support set_module_name_qconfig in X86InductorQuantizer

[yiliu30]

Summary:
Added set_module_name_qconfig support to allow users to set configurations based on module name in X86InductorQuantizer.

For example, only quantize the sub:

class M(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = torch.nn.Linear(5, 5)
        self.sub = Sub()

    def forward(self, x):
        x = self.linear(x)
        x = self.sub(x)
        return x

m = M().eval()
example_inputs = (torch.randn(3, 5),)
# Set config for a specific submodule.
quantizer = X86InductorQuantizer()
quantizer.set_module_name_qconfig("sub", xiq.get_default_x86_inductor_quantization_config())

• Added set_module_name_qconfig to allow user set the configuration at the module_name level.
• Unified the annotation process to follow this order: module_name_qconfig, operator_type_qconfig, and global_config.
• Added config_checker to validate all user configurations and prevent mixing of static/dynamic or QAT/non-QAT configs.
• Moved _get_module_name_filter from xnnpack_quantizer.py into utils.py as it common for all quantizer.

Test Plan

python -m pytest quantization/pt2e/test_x86inductor_quantizer.py -k test_set_module_name

@Xia-Weiwen @leslie-fang-intel @jgong5

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/126044

• 📄 Preview Python docs built from this PR
• 📄 Preview C++ docs built from this PR
• ❓ Need help or want to give feedback on the CI? Visit the bot commands wiki or our office hours

Note: Links to docs will display an error until the docs builds have been completed.

✅ You can merge normally! (1 Unrelated Failure)

As of commit 5378b56 with merge base 5001f41 ():

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• pull / linux-jammy-py3.8-gcc11 / test (distributed, 2, 2, linux.2xlarge) (gh) (similar failure)
  Process completed with exit code 1.

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[leslie-fang-intel]

I guess we also need to check here self.module_name_qconfig for dynamic quant here

pytorch/torch/ao/quantization/quantizer/x86_inductor_quantizer.py

Line 573 in b8308f9

if self.global_config and self.global_config.input_activation.is_dynamic: # type: ignore[union-attr]

[leslie-fang-intel]

Thanks for the PR. Add some comments.

[leslie-fang-intel]

Thanks for the PR. Add some comments.

[pytorch-bot]

Please seek CI approval before scheduling CIFlow labels

[leslie-fang-intel]

Thanks for the PR again. Looks good to me. @yiliu30 please kindly help to rebase this PR.

[leslie-fang-intel]

Hi @jerryzh168, looks like this PR needs your kindly approve to check the preCI.

[leslie-fang-intel]

nit: can we write as

if is_dynamic is None:
  is_dynamic = input_activation_spec.is_dynamic
else:
  assert is_dynamic == input_activation_spec.is_dynamic

and add some explanation for the code logic here? Same as above is_qat

[yiliu30]

Thanks, updated in 621ff11

[leslie-fang-intel]

@pytorchbot merge

[pytorchmergebot]

Merge started

Your change will be merged once all checks pass (ETA 0-4 Hours).

Learn more about merging in the wiki.

Questions? Feedback? Please reach out to the PyTorch DevX Team

Advanced Debugging

Check the merge workflow status
here