onnxruntime
Update Attention operator to support separated Q/K/V inputs
#13410
Merged

Update Attention operator to support separated Q/K/V inputs #13410

tianleiwu merged 2 commits into main from tlwu/attention_no_weights
tianleiwu
tianleiwu tianleiwu requested a review from yufenglee yufenglee 3 years ago
tianleiwu tianleiwu requested a review from gh-yewang gh-yewang 3 years ago
tianleiwu tianleiwu closed this 3 years ago
tianleiwu tianleiwu force pushed from 63809dfc to 14372560 3 years ago
tianleiwu update Attention for query, key and value inputs
56974b8c
tianleiwu tianleiwu reopened this 3 years ago
tianleiwu update Attention operator doc
75906d53
gh-yewang
gh-yewang commented on 2022-10-25
gh-yewang gh-yewang requested a review from gh-yewang gh-yewang 3 years ago
gh-yewang
gh-yewang approved these changes on 2022-10-25
tianleiwu tianleiwu merged 7aafd862 into main 3 years ago
tianleiwu tianleiwu deleted the tlwu/attention_no_weights branch 3 years ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone