transformers
Fix incorrect attention mask truncate in WhisperFlashAttention2
#36477

Merged

Fix incorrect attention mask truncate in WhisperFlashAttention2 #36477

eustlb merged 5 commits into huggingface:main from OliBomby:patch-1

Fix incorrect attention mask truncate in whisper flash attention

54feb174

github-actions marked this pull request as draft 1 year ago

OliBomby marked this pull request as ready for review 1 year ago

also fix incorrect attention mask truncate in qwen2 audio

28a41902

vasqu commented on 2025-03-07

Nit attention mask truncate modeling_qwen2_audio.py

44244b97

Nit attention mask truncate modeling_whisper.py

bcce0545

Merge branch 'main' into patch-1

ec3785a5

eustlb approved these changes on 2025-05-14

eustlb enabled auto-merge (squash) 1 year ago

eustlb merged 4005e30c into main 1 year ago

OliBomby deleted the patch-1 branch 1 year ago

Reviewers

eustlb

vasqu

Assignees

No one assigned

Labels

None yet

Milestone

No milestone