PR #22102 GQA MLFloat16 cpu

GQA MLFloat16 cpu #22102

gh-yewang merged 10 commits into main from wangye/gqa_fp16

init

b1a88d55

update

0b60013b

eigen MLFloat16

a5a6ae0b

tianleiwu commented on 2024-09-16

tianleiwu commented on 2024-09-17

restore fp32 softmax

bbbdfc3f

update

4b4b17ac

use constexpr

d3b43f43

update

d6357828

tianleiwu commented on 2024-09-20

update

a9a07e1d

fix tests

3c559483

gh-yewang changed the title ~~[draft]GQA MLFloat16 cpu~~ GQA MLFloat16 cpu 1 year ago

gh-yewang marked this pull request as ready for review 1 year ago

docs

91fe0e82

tianleiwu approved these changes on 2024-09-24

gh-yewang merged 6cc06ad0 into main 1 year ago

gh-yewang deleted the wangye/gqa_fp16 branch 1 year ago

Reviewers

tianleiwu

yufenglee

Assignees

No one assigned

Labels

None yet

Milestone

No milestone