Skip to content

Fused attention pass backward op replace. #50186

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 13 commits into from
Feb 3, 2023
Merged

Fused attention pass backward op replace. #50186

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
ec45a78
remove unused vars for fwd
FeixLiu Feb 2, 2023
71cec74
update
FeixLiu Feb 2, 2023
2048157
add node cache
FeixLiu Feb 2, 2023
cafdd8e
bug fix for cache
FeixLiu Feb 2, 2023
4972631
anchor key for cache
FeixLiu Feb 2, 2023
299e448
update to use matmul w as anchor
FeixLiu Feb 2, 2023
c0715d8
set attr
FeixLiu Feb 3, 2023
10ba917
add output
FeixLiu Feb 3, 2023
d55c73f
create op, link nodes
FeixLiu Feb 3, 2023
d419217
update ut
FeixLiu Feb 3, 2023
1e80f5b
udpate fused attention of cache kv output
FeixLiu Feb 3, 2023
79940d4
set ln_epsilon attr
FeixLiu Feb 3, 2023
530b66c
bug fix
FeixLiu Feb 3, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Loading