Revert #7714 to check if CI passes

[shoumikhin]

@digantdesai the recent fix seems to cause one issue, can you please take a look?

Traceback (most recent call last):
  File "<frozen runpy>", line 198, in _run_module_as_main
  File "<frozen runpy>", line 88, in _run_code
  File "/Users/shoumikhin/Temp/executorch/examples/xnnpack/aot_compiler.py", line 110, in <module>
    exec_prog = edge.to_executorch(
                ^^^^^^^^^^^^^^^^^^^
  File "/Users/shoumikhin/Temp/executorch/.venv/lib/python3.12/site-packages/executorch/exir/program/_program.py", line 99, in wrapper
    return func(self, *args, **kwargs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/shoumikhin/Temp/executorch/.venv/lib/python3.12/site-packages/executorch/exir/program/_program.py", line 1385, in to_executorch
    new_gm_res = p(new_gm)
                 ^^^^^^^^^
  File "/Users/shoumikhin/Temp/executorch/.venv/lib/python3.12/site-packages/torch/fx/passes/infra/pass_base.py", line 44, in __call__
    res = self.call(graph_module)
          ^^^^^^^^^^^^^^^^^^^^^^^
  File "/Users/shoumikhin/Temp/executorch/.venv/lib/python3.12/site-packages/executorch/exir/passes/__init__.py", line 427, in call
    raise RuntimeError(f"Missing out variants: {missing_out_vars}")
RuntimeError: Missing out variants: {'quantized_decomposed::dequantize_per_tensor', 'quantized_decomposed::quantize_per_tensor'}

Here's how you can reproduce it on the latest main branch:

git clone https://github.com/pytorch/executorch.git --depth 1 --recurse-submodules --shallow-submodules
cd executorch

python3 -m venv .venv && source .venv/bin/activate && pip install --upgrade pip

./install_executorch.sh --pybind xnnpack # install any missing pip dep manually if this script currently fails

python3 -m examples.xnnpack.aot_compiler --model_name=emformer_transcribe --delegate --quantize

For context, our CI signals were lagging at the time this PR landed, so we couldn't catch it earlier, and now they're back.

Thanks!

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7849

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit e99e25b with merge base f2720fa ():

NEW FAILURE - The following job has failed:

• pull / unittest / macos / macos-job (gh)
  backends/xnnpack/test/ops/test_conv1d.py::TestConv1d::test_qs8_conv1d_batchnorm_seq

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

[shoumikhin]

@pytorchbot label "topic: not user facing"

[swolchok]

do we need to land this or should it be closed?

[digantdesai]

Without this we will not quantize, under --quantize so its just wrong. We should fix whatever else is broken rather than reverting this IMHO.