Skip to content

GitLab

Switch branch/tag
Find file BlameHistoryPermalink
  • Tong WU's avatar
    [BugFix] Refactor attention kernel to handle OOB positions by filling with... · 0af3fd7c
    Tong WU authored 
    [BugFix] Refactor attention kernel to handle OOB positions by filling with `-inf` instead of clearing accumulators. (#1222)

* Refactor attention kernel to handle OOB positions by filling with `-inf` instead of clearing accumulators.

* lint

* pre-commit

* Update imports in flash attention test file to use new backward and forward examples for better clarity and consistency.
    0af3fd7c
example_mha_fwd_bhsd.py 9.32 KB