onnxruntime
Extend memory efficient attention coverage in Attention/MHA cuda op
#15064
Merged
Merged
Extend memory efficient attention coverage in Attention/MHA cuda op #15064
gh-yewang
merged
23 commits into
main
from
wangye/cutlass_bias
update to cutlass 3.0
d4cd2846
Merge branch 'main' of github.com:microsoft/onnxruntime into wangye/c…
07984e82
rpb parity is good
f8f0d8ca
ut
eb1f8184
fix batch issue and restrict seq_len
be29652b
update deps version
b7ab0a13
update
d6f4c450
Merge branch 'main' of github.com:microsoft/onnxruntime into wangye/c…
b8eafc07
patch
7423668b
fix commplex.hpp
71a74ea0
Revert "fix commplex.hpp"
48644cf3
Attempting pipeline fix using guards
cc1c7ddd
Adding patch command to cutlass cmake
bc96ff20
Combine cutlass patch files
6944277b
Merge branch 'main' into wangye/cutlass_bias
6f93ad60
Adding updated contrib ops doc
960b96f2
support batched rpb
7128682a
refine patch file
1872fb7a
Merge branch 'main' of github.com:microsoft/onnxruntime into wangye/c…
ea3a8553
tianleiwu
commented
on 2023-03-21
review comments
42e72f39
fix comment
bfefe03a
update docs
aad4941f
Merge branch 'main' of github.com:microsoft/onnxruntime into wangye/c…
b8be2bd6
tianleiwu
approved these changes
on 2023-03-23
jchen351
approved these changes
on 2023-03-23
pranavsharma
commented
on 2023-03-23
pranavsharma
approved these changes
on 2023-03-23
Reviewers
Assignees
No one assigned
Labels
None yet
Milestone
No milestone
Login to write a write a comment.
Login via GitHub