]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 60f17f5)
Revert "ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (#18413...
authorAman Gupta <redacted>
Sun, 28 Dec 2025 12:53:36 +0000 (20:53 +0800)
committerGitHub <redacted>
Sun, 28 Dec 2025 12:53:36 +0000 (20:53 +0800)
commit07a0c4ba923a8caea3eeba060d399a28c461deac
tree97cbe83cb6ae8bd59ec91115fd9c5b95693cdba9tree
parent60f17f56da78d8fabc658279fd25e109700122dacommit | diff
Revert "ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when GGML_NATIVE=ON (#18413)" (#18426)
ggml/src/ggml-cuda/CMakeLists.txt diff | blob | history
Packaging of ggml-org/llama.cpp