Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

In tutorials/quantize_vit, extract common methods to util.py #238

Merged
merged 8 commits into from
May 20, 2024

Conversation

lancerts
Copy link
Contributor

@lancerts lancerts commented May 12, 2024

In tutorials/quantize_vit, extract common methods to util.py

Local execution tested via ./run.sh

cc @msaroufim

Copy link

pytorch-bot bot commented May 12, 2024

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/238

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

✅ No Failures

As of commit b7d6811 with merge base adfe570 (image):
💚 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 facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label May 12, 2024
@lancerts lancerts changed the title Extract common methods to util.py In tutorials/quantize_vit, extract common methods to util.py May 12, 2024
@msaroufim msaroufim self-requested a review May 16, 2024 14:09
@lancerts
Copy link
Contributor Author

 =================================== FAILURES ===================================
  _____ TestWeightOnlyInt8Quant.test_weight_only_quant_force_mixed_mm_4_cuda _____
  
  a = (<test_integration.TestWeightOnlyInt8Quant testMethod=test_weight_only_quant_force_mixed_mm_4_cuda>,)
  kw = {}
  
      @wraps(func)
      def standalone_func(*a, **kw):
  >       return func(*(a + p.args), **p.kwargs, **kw)
  
  /opt/conda/envs/venv/lib/python3.9/site-packages/parameterized/parameterized.py:620: 
  _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ _ 
  /opt/conda/envs/venv/lib/python3.9/site-packages/torch/utils/_contextlib.py:115: in decorate_context
      return func(*args, **kwargs)
  test/integration/test_integration.py:1129: in test_weight_only_quant_force_mixed_mm
      self.assertTrue("mixed_mm" in code)
  E   AssertionError: False is not true

Not sure how this test failure relates to the code change....

@msaroufim
Copy link
Member

It's unrelated, we'll merge the fix then your change so no worries!

@msaroufim
Copy link
Member

@lancerts can you rebase to main? The error should go away

@lancerts
Copy link
Contributor Author

lancerts commented May 17, 2024

@lancerts can you rebase to main? The error should go away

The sync from your end seems still same failure https://github.com/pytorch/ao/actions/runs/9120697036/job/25078538641 So did a rebase on my end. TY

@lancerts lancerts force-pushed the minor-fix branch 2 times, most recently from ce7699d to b226a7e Compare May 17, 2024 01:04
@msaroufim msaroufim merged commit f0f00ce into pytorch:main May 20, 2024
13 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants