llama.cpp
kleidiai: use SME2 kernels for CPU flash attention
#29394

Open

kleidiai: use SME2 kernels for CPU flash attention #29394

arm-bhanuarya wants to merge 2 commits into ggml-org:master from arm-bhanuarya:review/sme2-fa-current-upstream

arm-bhanuarya requested a review from

ggerganov 3 days ago

ggml-gh-bot added draft

github-actions marked this pull request as draft 3 days ago

github-actions removed draft

github-actions added testing

github-actions added ggml

arm-bhanuarya closed this 2 days ago

arm-bhanuarya reopened this 2 days ago

kleidiai: use SME2 kernels for CPU flash attention

8e4b55b4

arm-bhanuarya force pushed from 5e302ca1 to 8e4b55b4 2 days ago

arm-bhanuarya marked this pull request as ready for review 2 days ago

Merge branch 'master' into review/sme2-fa-current-upstream

34659b33

Reviewers

ggerganov

Assignees

No one assigned

Labels

testing ggml

Milestone

No milestone