PR #22629 Update attention fusion to support SDPA pattern

Update attention fusion to support SDPA pattern #22629

tianleiwu merged 9 commits into main from tlwu/bert_sdpa_fusion_script

Update attention fusion to support SDPA pattern

2ff9e5eb

tianleiwu marked this pull request as draft 1 year ago

github-actions dismissed these changes on 2024-10-28

Merge branch 'main' into tlwu/bert_sdpa_fusion_script

cfe46a9f

Add test

9eed3691

tianleiwu force pushed from 74d770e5 to 9eed3691 1 year ago

tianleiwu dismissed their stale review 1 year ago

out of date

tianleiwu marked this pull request as ready for review 1 year ago

tianleiwu requested a review from

kunal-vaishnavi 1 year ago

tianleiwu requested a review from

jiafatom 1 year ago

kunal-vaishnavi dismissed these changes on 2024-11-19

kunal-vaishnavi commented on 2024-11-19

tianleiwu marked this pull request as draft 1 year ago

check mask value; add test for xlm-roberta

899ed78e

tianleiwu dismissed their stale review via 899ed78e 1 year ago

update typing

69cbc4a5

rename input to first_input

2b610228

fix CI error

6ade92ef

use torch.testing.assert_close

b0d9e563

update phi3 moe tests

2b5c0d30

tianleiwu marked this pull request as ready for review 1 year ago

tianleiwu requested a review from

kunal-vaishnavi 1 year ago

kunal-vaishnavi approved these changes on 2024-11-21

tianleiwu merged 55f0559e into main 1 year ago

tianleiwu deleted the tlwu/bert_sdpa_fusion_script branch 1 year ago

Reviewers

kunal-vaishnavi

github-actions

jiafatom

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

onnxruntime Update attention fusion to support SDPA pattern #22629 Merged

Update attention fusion to support SDPA pattern #22629

onnxruntime
Update attention fusion to support SDPA pattern
#22629

Merged