llama.cpp
ggml-cuda: use passed ops instead of hardcoded ops
#16712

Merged

ggml-cuda: use passed ops instead of hardcoded ops #16712

am17an merged 1 commit into ggml-org:master from am17an:cuda-refactor-can-fuse

ggml-cuda: use passed ops instead of hardcoded ops

94ba8b3c

am17an requested a review from

slaren 57 days ago

github-actions added Nvidia GPU

github-actions added ggml

am17an requested a review from

JohannesGaessler 57 days ago

JohannesGaessler approved these changes on 2025-10-23

am17an merged 061f0eff into master 56 days ago

am17an deleted the cuda-refactor-can-fuse branch 55 days ago

Reviewers

JohannesGaessler

slaren

Assignees

No one assigned

Labels

Nvidia GPU ggml

Milestone

No milestone