[xnnpack] Reexport after quantize in aot_compiler

[digantdesai]

Summary

It was not using quantized model even when quantize flag, this fixes that.

Test plan

local tests and ci.

• Before

-rw-r--r--  1 digantdesai  staff  13974408 Jan 16 15:44 mv2_xnnpack_fp32.pte
-rw-r--r--  1 digantdesai  staff  13974408 Jan 16 15:45 mv2_xnnpack_q8.pte

• After

-rw-r--r--  1 digantdesai  staff  13974408 Jan 16 15:44 mv2_xnnpack_fp32.pte
-rw-r--r--  1 digantdesai  staff   3572400 Jan 16 16:05 mv2_xnnpack_q8.pte

cc @mcr229

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7714

• 📄 Preview Python docs built from this PR

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

⏳ No Failures, 1 Pending

As of commit bf5367a with merge base a18f6e8 ():
💚 Looks good so far! There are no failures yet. 💚

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

[facebook-github-bot]

@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator.

[huydhn]

@digantdesai @shoumikhin I believe this is the PR that is causing the trunk failure with emformer_transcribe. I attempted to revert the change in #7879 and the signal recovered. I see that @shoumikhin is attempting the same revert here, so maybe he could also confirm this.

GH job link HUD commit link