]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: eda7e1d)
CMake: default to -arch=native for CUDA build (#10320)
authorJohannes Gäßler <redacted>
Sun, 17 Nov 2024 08:06:34 +0000 (09:06 +0100)
committerGitHub <redacted>
Sun, 17 Nov 2024 08:06:34 +0000 (09:06 +0100)
commit467576b6cc7d2b9220f55bc635aa51469cf26fb5
tree0e98e470e007ab859003727497f6d41d50341cedtree
parenteda7e1d4f54711de1c9b40502d6c88bbc217da60commit | diff
CMake: default to -arch=native for CUDA build (#10320)
README.md diff | blob | history
ggml/src/ggml-cuda/CMakeLists.txt diff | blob | history
Packaging of ggml-org/llama.cpp