llama.cpp
CUDA: refactor and deduplicate vector FA kernels
#16208

Merged

CUDA: refactor and deduplicate vector FA kernels #16208

JohannesGaessler merged 2 commits into ggml-org:master from JohannesGaessler:cuda-fa-vec-128-4

CUDA: refactor and deduplicate vector FA kernels

e2679030

JohannesGaessler requested a review from

slaren 116 days ago

github-actions added Nvidia GPU

github-actions added python

github-actions added ggml

fix kernel selection logic

8ba0ff79

JohannesGaessler force pushed to 8ba0ff79 115 days ago

slaren approved these changes on 2025-09-27

JohannesGaessler merged 75a3a6c2 into master 112 days ago

Reviewers

slaren

Assignees

No one assigned

Labels

Nvidia GPU python ggml

Milestone

No milestone