make quantized model tests better

pytorch / executorch

On-device AI across mobile, embedded and edge for PyTorch

https://pytorch.org/executorch/

Other

1.31k stars 206 forks source link

make quantized model tests better #3495

Closed mcr229 closed 1 week ago

mcr229 commented 2 weeks ago

Summary: XNNPACK should be testing with random inputs and quantized models should be calibrated before lowering and testing. Right now there are some numerical issues being debugged and tracked by: T187799178. this has been a bit difficult, but for now, we can first make these tests better by giving random inptus and enabling calibration.

We don't fix the numerical issues in this diff.

Differential Revision: D56906440

pytorch-bot[bot] commented 2 weeks ago

:link: Helpful Links

:test_tube: See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/3495

:page_facing_up: Preview Python docs built from this PR

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

:white_check_mark: No Failures

As of commit 25b63528e7f8d1396f498b730268b3244004bb33 with merge base 4bd45c39a147f88748a19028593108e93e963474 (): :green_heart: Looks good so far! There are no failures yet. :green_heart:

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

facebook-github-bot commented 2 weeks ago

This pull request was exported from Phabricator. Differential Revision: D56906440

facebook-github-bot commented 2 weeks ago

This pull request was exported from Phabricator. Differential Revision: D56906440

facebook-github-bot commented 1 week ago

This pull request has been merged in pytorch/executorch@2835d01e32c9caeca9cc87229d80c3d4703f00ad.