Unify float8 scale selection for per-tensor quantization

[MagellaX]

Summary

• Remove the per-tensor special case in _choose_scale_float8 and use the unified reduction path
• Update float8 tests to use per-tensor block_size == input_tensor.shape

#3414

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/3635

• 📄 Preview Python docs built from this PR

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

✅ No Failures

As of commit 0dc6470 with merge base c6d21f9 ():
💚 Looks good so far! There are no failures yet. 💚

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

[meta-cla]

Hi @MagellaX!

Thank you for your pull request and welcome to our community.

Action Required

In order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you.

Process

In order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA.

Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[meta-cla]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[jerryzh168]

could you split this change to a separate PR? seems it's not related to the fp8 choose_scale op change right?

[MagellaX]

Thanks! You’re right, that change is unrelated. I’m cleaning the branch now and will update the PR with only the float8 scale change.

[jerryzh168]

@MagellaX seems still not updated yet

[MagellaX]

i think it is now!!!

[meta-codesync]

@jerryzh168 has imported this pull request. If you are a Meta employee, you can view this in D91344844.

[jerryzh168]

this breaks BC for _choose_scale_float8 for per tensor block_size but since _choose_scale_float8 is a private op, we don't need to mark it as BC breaking