onnxruntime
Add --use_multi_head_attention in transformers fusion
#14198
Merged

Add --use_multi_head_attention in transformers fusion #14198

tianleiwu merged 4 commits into main from tlwu/cross_attention_fusion
tianleiwu
tianleiwu add --use_cross_attention in transformers fusion
64f23c36
tianleiwu tianleiwu marked this pull request as draft 2 years ago
tianleiwu Merge branch 'main' into tlwu/cross_attention_fusion
da5a244e
tianleiwu change CrossAttention to MultiHeadAttention
72379cff
tianleiwu tianleiwu changed the title Add --use_cross_attention in transformers fusion Add --use_multi_head_attention in transformers fusion 2 years ago
tianleiwu tianleiwu requested a review from wangyems wangyems 2 years ago
tianleiwu tianleiwu marked this pull request as ready for review 2 years ago
tianleiwu tianleiwu marked this pull request as draft 2 years ago
tianleiwu add test case
cb27f6e5
tianleiwu tianleiwu marked this pull request as ready for review 2 years ago
tianleiwu tianleiwu requested a review from yufenglee yufenglee 2 years ago
wangyems
wangyems approved these changes on 2023-01-11
tianleiwu tianleiwu merged 012b34dc into main 2 years ago
tianleiwu tianleiwu deleted the tlwu/cross_attention_fusion branch 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone