Add modified masking routine to Quantized Softmax Operator

[mvartani-meta]

Summary: This diff introduces a modified method for masking. Instead of using the mask tensor, the function uses a position tensor where it attends the values up to the position value. In addition, the current implementation only reads the first value from the position tensor and then increments by one for each additional row.

Differential Revision: D88997196

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/16907

• 📄 Preview Python docs built from this PR

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

❌ 1 New Failure

As of commit 3fbab11 with merge base 2e99d9e ():

NEW FAILURE - The following job has failed:

• pull / android / run-emulator (gh)
  The process '/opt/android/sdk/platform-tools/adb' failed with exit code 224

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

[meta-codesync]

@mvartani-meta has exported this pull request. If you are a Meta employee, you can view the originating Diff in D88997196.

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.