onnxruntime
optimization for whisper model with decoder masked multihead attention
#15827
Merged

optimization for whisper model with decoder masked multihead attention #15827

zhanghuanrong merged 7 commits into main from zhalei/whisper-pr
zhanghuanrong
github-advanced-security
github-advanced-security commented on 2023-05-06
github-advanced-security
github-advanced-security commented on 2023-05-06
zhanghuanrong zhanghuanrong force pushed from 90186c4f to 16efe74a 2 years ago
zhanghuanrong zhanghuanrong requested a review from wangyems wangyems 2 years ago
zhanghuanrong zhanghuanrong requested a review from hariharans29 hariharans29 2 years ago
zhanghuanrong zhanghuanrong requested a review from yufenglee yufenglee 2 years ago
yufenglee
yufenglee commented on 2023-05-15
yufenglee
yufenglee commented on 2023-05-15
zhanghuanrong Support whisper model to use MaskedDecoderMultiheadAttention
c4cbce67
zhanghuanrong fix py lint warning
ab5945da
zhanghuanrong fix change fail unit test
763fc305
zhanghuanrong zhanghuanrong force pushed from f0c071c8 to 763fc305 2 years ago
yufenglee
yufenglee commented on 2023-05-16
yufenglee
yufenglee commented on 2023-05-16
zhanghuanrong Fix som pr feedback
bdf3281d
zhanghuanrong Fix bug caused by remove optional attention mask
2ad6ac93
zhanghuanrong Fix bug during adding initial decoder ids
40925961
zhanghuanrong docs update
e20ad994
yufenglee
yufenglee approved these changes on 2023-05-17
zhanghuanrong zhanghuanrong merged 0f8e66d9 into main 2 years ago
zhanghuanrong zhanghuanrong deleted the zhalei/whisper-pr branch 2 years ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone