]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 2cc4a5e)
CUDA: compress mode option and default to size (#12029)
authorErik Scholz <redacted>
Sat, 1 Mar 2025 11:57:22 +0000 (12:57 +0100)
committerGitHub <redacted>
Sat, 1 Mar 2025 11:57:22 +0000 (12:57 +0100)
commit80c41ddd8f11b8094018296d9820c2b6c119ac12
tree00e5be5c7fe7b751b01398009f151ce38d16a2b1tree
parent2cc4a5e44a3a9ab94426816770d611b33fae8f77commit | diff
CUDA: compress mode option and default to size (#12029)

cuda 12.8 added the option to specify stronger compression for binaries, so we now default to "size".
ggml/CMakeLists.txt diff | blob | history
ggml/src/ggml-cuda/CMakeLists.txt diff | blob | history
Packaging of ggml-org/llama.cpp