PR #30546 opencl: apply flash attn softcap before mask

opencl: apply flash attn softcap before mask #30546

ggerganov merged 1 commit into ggml-org:master from qualcomm:lh/fa-softcap-fix

opencl: apply flash attn softcap before mask

66052053

github-actions added ggml

github-actions added OpenCL

lhez marked this pull request as ready for review 6 days ago

lhez requested a review 6 days ago

max-krasnyansky approved these changes on 2026-10-14

max-krasnyansky added merge ready

ggerganov merged 77c1f399 into master 6 days ago

Reviewers

max-krasnyansky

Assignees

No one assigned

Labels

ggml merge ready OpenCL

Milestone

No milestone