fixing the falsh attn mask

[HamidShojanazeri]

Description

This PR fixes the flash attn by passing masks to avoid junk output.

Fixes #(issue)

Type of change

Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• New feature (non-breaking change which adds functionality)
• This change requires a documentation update

Feature/Issue validation/testing

Please describe the Unit or Integration tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

• Test A
  response after fixing the mask,

• Test B
  response before the fix

Checklist:

• Did you have fun?
• Have you added tests that prove your fix is effective or that this feature works?
• Has code been commented, particularly in hard-to-understand areas?
• Have you made corresponding changes to the documentation?

[codecov]

Codecov Report

Merging #2689 (dcd5605) into master (504c734) will not change coverage.
The diff coverage is n/a.

❗ Current head dcd5605 differs from pull request most recent head 16ad186. Consider uploading reports for the commit 16ad186 to get more accurate results

@@           Coverage Diff           @@
##           master    #2689   +/-   ##
=======================================
  Coverage   72.39%   72.39%           
=======================================
  Files          85       85           
  Lines        3956     3956           
  Branches       58       58           
=======================================
  Hits         2864     2864           
  Misses       1088     1088           
  Partials        4        4           

📣 We’re building smart automated test selection to slash your CI/CD build times. Learn more