llama.cpp
metal: add opt-in V skip for negligible attention weights
#21119

Open

metal: add opt-in V skip for negligible attention weights #21119

TheTom wants to merge 1 commit into ggml-org:master from TheTom:pr/fa-skip-negligible-v

metal: add opt-in V skip for negligible attention weights

b4e6aa86

TheTom requested a review 6 days ago

github-actions added ggml

github-actions added Apple Metal

Reviewers

No reviews

Assignees

No one assigned

Labels

ggml Apple Metal

Milestone

No milestone