onnxruntime
Scripts to convert model with MulitHeadAttention to packing mode
#16925
Merged

Scripts to convert model with MulitHeadAttention to packing mode #16925

yufenglee merged 5 commits into main from tlwu/packed_mha_script
tianleiwu
tianleiwu script for packing mha
e43d16ee
tianleiwu add symbolic shape infer
c31d0eb9
tianleiwu tianleiwu requested a review from yufenglee yufenglee 2 years ago
tianleiwu tianleiwu requested a review from gh-yewang gh-yewang 2 years ago
tianleiwu remove duplicate
48560208
tianleiwu Merge branch 'main' into tlwu/packed_mha_script
87ca10b7
tianleiwu add logging
9f53fc67
yufenglee
yufenglee approved these changes on 2023-08-03
yufenglee yufenglee merged bda012a4 into main 2 years ago
yufenglee yufenglee deleted the tlwu/packed_mha_script branch 2 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone