llama.cpp
metal : gemma2 flash attention support
#9159
Merged

metal : gemma2 flash attention support #9159

slaren merged 2 commits into master from sl/metal-logit-softcap
slaren
slaren metal : gemma2 flash attention support
054203ae
github-actions github-actions added testing
slaren slaren marked this pull request as draft 1 year ago
ggerganov
slaren use precise::tanh
edc2e273
slaren
slaren slaren marked this pull request as ready for review 1 year ago
ggerganov
ggerganov approved these changes on 2024-08-26
slaren slaren merged 0c41e03c into master 1 year ago
slaren slaren deleted the sl/metal-logit-softcap branch 1 year ago

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone