]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
CUDA: re-use MLA K data for V in MMA FA (#19057)
authorJohannes Gäßler <redacted>
Sat, 24 Jan 2026 09:09:36 +0000 (10:09 +0100)
committerGitHub <redacted>
Sat, 24 Jan 2026 09:09:36 +0000 (10:09 +0100)
commit8f91ca54ec0b22f3ff3a495f32be8e8300638cdf
tree15955200919ca5e9bab408020c2f032ea838d910
parent81ab64f3c858c0db8c7c3a6bccd4cbbe624f52a3
CUDA: re-use MLA K data for V in MMA FA (#19057)
ggml/src/ggml-cuda/fattn-common.cuh
ggml/src/ggml-cuda/fattn-mma-f16.cuh
ggml/src/ggml-cuda/fattn.cu