PR #22352 [CUDA] Lean Attention

[CUDA] Lean Attention #22352

tianleiwu merged 10 commits into main from tlwu/lean_att

Add Lean Attention (by Srikant Bharadwaj)

1ee1aa14

tianleiwu marked this pull request as draft 2 years ago

github-advanced-security commented on 2024-10-08

Add Lean Att to MHA op

78c056b8

github-advanced-security commented on 2024-10-12

Add benchmark

b7034999

format

b44f4ee1

Disable Lean in Windows

8b380e24

tianleiwu requested a review from

aciddelgado 2 years ago

tianleiwu requested a review from

kunal-vaishnavi 2 years ago

tianleiwu marked this pull request as ready for review 2 years ago

fix flops

787b7ddd

fix build

7004bec3

clean up

2142b96f

refactoring; update tests

ef23fef3

github-advanced-security commented on 2024-10-14

conditional compile

a3c9e8ef

kunal-vaishnavi commented on 2024-10-14

kunal-vaishnavi approved these changes on 2024-10-14

tianleiwu merged de93f402 into main 2 years ago

tianleiwu deleted the tlwu/lean_att branch 2 years ago

Reviewers

kunal-vaishnavi

aciddelgado

Assignees

No one assigned

Labels

None yet

Milestone

No milestone