llama.cpp
kv-cache : optimize KQ mask construction
#18842
Merged

kv-cache : optimize KQ mask construction #18842

ggerganov merged 3 commits into master from gg/kv-mask-opt
ggerganov
ggerganov kv-cache : optimize KQ mask construction
6628f518
ggerganov cont : add explanation + improve
bac56aef
ggerganov ggerganov force pushed from edd29726 to bac56aef 1 day ago
ggerganov cont : fix
490f6f70
ggerganov ggerganov marked this pull request as ready for review 1 day ago
ggerganov ggerganov merged 2fbde785 into master 16 hours ago
ggerganov ggerganov deleted the gg/kv-mask-opt branch 16 hours ago

Login to write a write a comment.

Login via GitHub

Reviewers
No reviews
Assignees
No one assigned
Labels
Milestone