Scripts to convert model with MulitHeadAttention to packing mode #16925
script for packing mha
e43d16ee
add symbolic shape infer
c31d0eb9
remove duplicate
48560208
Merge branch 'main' into tlwu/packed_mha_script
87ca10b7
add logging
9f53fc67
yufenglee
approved these changes
on 2023-08-03
yufenglee
merged
bda012a4
into main 2 years ago
yufenglee
deleted the tlwu/packed_mha_script branch 2 years ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub