[PT2E][X86] Migrate fusion passes in Inductor to torchao

[Xia-Weiwen]

Summary
In this PR, we copied the fusion passes of quantized ops for X86Inductor backend from PyTorch Inductor source code to Torchao. This is the first step to migrate quantization-related fusion passes in PyTorch core to Torchao.
We plan to do it in the following steps:

• Copy fusion passes from PyTorch core to Torchao (this PR)
• Depreacte and remove fusion passes in PyTorch core (TODO)
• Switch to new quantize/dequantize ops in Torchao (TODO)

With this PR landed, we can add fusion passes for new ops in Torchao instead of in PyTorch core.

Since fusion passes need to be registered to Inductor, this PR wrapped the registration in the API lower_pt2e_quantized_to_x86. So, users need to call lowerlower_pt2e_quantized_to_x86 instead of torch.compile to get lowered model with torch.compile. The API is updated as below:

def lower_pt2e_quantized_to_x86(
    model: torch.fx.GraphModule,
    example_inputs: Optional[tuple[torch.Tensor, ...]] = None,
    compile: bool = True,
    **compile_options: Optional[dict],
) -> torch.fx.GraphModule

The compile flag indicates using torch.compile or not (eager mode). For eager mode, users just set compile=False.

Test plan
We copied related UTs from https://github.com/pytorch/pytorch/blob/main/test/inductor/test_mkldnn_pattern_matcher.py

pytest test/quantization/pt2e/test_x86inductor_fusion.py

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/2140

• 📄 Preview Python docs built from this PR

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

❌ 6 New Failures, 2 Pending

As of commit 1c2a948 with merge base e3db2b2 ():

NEW FAILURES - The following jobs have failed:

• Run Regression Tests / test (CPU 2.5.1, linux.4xlarge, torch==2.5.1 --index-url https://download.pytorch.org/whl/cpu, cpu) / linux-job (gh)
  test/quantization/pt2e/test_x86inductor_fusion.py::TestDynamicPatternMatcher::test_qconv2d_maxpool2d_linear_dynamic_cpu
• Run Regression Tests / test (CPU 2.6, linux.4xlarge, torch==2.6.0 --index-url https://download.pytorch.org/whl/cpu, cpu) / linux-job (gh)
  test/quantization/pt2e/test_x86inductor_fusion.py::TestDynamicPatternMatcher::test_qconv2d_maxpool2d_linear_dynamic_cpu
• Run Regression Tests / test (CPU 2.7, linux.4xlarge, torch==2.7.0 --index-url https://download.pytorch.org/whl/cpu, cpu) / linux-job (gh)
  test/quantization/pt2e/test_x86inductor_fusion.py::TestDynamicPatternMatcher::test_qconv2d_maxpool2d_linear_dynamic_cpu
• Run Regression Tests / test (CUDA 2.5.1, linux.g5.12xlarge.nvidia.gpu, torch==2.5.1 --index-url https://download.pytorch... / linux-job (gh)
  test/quantization/pt2e/test_x86inductor_fusion.py::TestDynamicPatternMatcher::test_qconv2d_maxpool2d_linear_dynamic_cpu
• Run Regression Tests / test (CUDA 2.6, linux.g5.12xlarge.nvidia.gpu, torch==2.6.0, cuda, 12.6) / linux-job (gh)
  test/quantization/pt2e/test_x86inductor_fusion.py::TestDynamicPatternMatcher::test_qconv2d_maxpool2d_linear_dynamic_cpu
• Run Regression Tests / test (CUDA 2.7, linux.g5.12xlarge.nvidia.gpu, torch==2.7.0, cuda, 12.6) / linux-job (gh)
  test/quantization/pt2e/test_x86inductor_fusion.py::TestDynamicPatternMatcher::test_qconv2d_maxpool2d_linear_dynamic_cpu

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