]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 438c2ca)
make : add optional CUDA_NATIVE_ARCH (#2482)
authorAlex <redacted>
Sun, 22 Oct 2023 19:56:53 +0000 (15:56 -0400)
committerGitHub <redacted>
Sun, 22 Oct 2023 19:56:53 +0000 (22:56 +0300)
commit96981f37b1e3f450d9e63e571514217bf60f0a7f
tree2c09acb1219bcae7385ee9adb97a43989820d264tree
parent438c2ca83045a00ef244093d27e9ed41a8cb4ea9commit | diff
make : add optional CUDA_NATIVE_ARCH (#2482)

Use the environment variable `CUDA_NATIVE_ARCH` if present to set NVCC arch. Otherwise, use `native`.
Makefile diff | blob | history
Packaging of ggml-org/llama.cpp