Dedup _choose_qparams_per_token_asymmetric

[andrewor14]

No description provided.

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/233

• 📄 Preview Python docs built from this PR

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

❌ 2 New Failures

As of commit bf5c816 with merge base b91b6be ():

NEW FAILURES - The following jobs have failed:

• Run Regression Tests / test (CPU 2.3, linux.4xlarge, torch==2.3.0 --index-url https://download.pytorch.org/whl/cpu, cpu) / linux-job (gh)
  test/quantization/test_qat.py::TestQAT::test_qat_8da4w_quantizer_disable_fake_quant
• Run Regression Tests / test (CUDA 2.3, linux.g5.12xlarge.nvidia.gpu, torch==2.3.0, cuda, 12.1) / linux-job (gh)
  test/quantization/test_qat.py::TestQAT::test_qat_8da4w_quantizer_disable_fake_quant

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

[jerryzh168]

please make sure CI is green before landing.

just curious, why do we replicate this before?

[andrewor14]

It was waiting for this change: pytorch/pytorch#123452. Basically the op didn't work in backward pass before

[andrewor14]

Closing this for now. #229 made some further changes to the choose_qparams op that will need to be propagated to PyTorch core first. This is not ready to land yet