PR #16829 cpu: introduce chunking for flash attention

cpu: introduce chunking for flash attention #16829

ggerganov merged 1 commit into ggml-org:master from qualcomm:flashattn-chunking

cpu: introduce chunking for flash attention

e2364c9c

max-krasnyansky requested a review from

ggerganov 219 days ago

max-krasnyansky requested a review from

slaren 219 days ago

github-actions added ggml

slaren approved these changes on 2025-10-30

ggerganov merged dcca0d3a into master 217 days ago

max-krasnyansky deleted the flashattn-chunking branch 217 days ago

Reviewers

slaren

ggerganov

Assignees

No one assigned

Labels

ggml

Milestone

No milestone