]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 8c0d6bb)
ggml-cpu: detect correct cpu flags for arm64 (#16229) (#16239)
authoriron <redacted>
Fri, 7 Nov 2025 16:18:14 +0000 (00:18 +0800)
committerGitHub <redacted>
Fri, 7 Nov 2025 16:18:14 +0000 (08:18 -0800)
commit7c23f3f0d4b9f5d6ea140756eb694b562d5acebb
treedda9c8e48fbb4047e70c9c0db75dc504ed6ec9adtree
parent8c0d6bb4559e15f1236035a0465781c1345324e5commit | diff
ggml-cpu: detect correct cpu flags for arm64 (#16229) (#16239)

When using GCC 9 and GCC 12 on the arm64 platform of ubuntu 2004,
the command "gcc -mcpu=native -E -v -" fails to detect the correct CPU flags,
which results in compilation failures for certain extended instructions,
but the correct CPU flags can be obtained by using gcc -march.

Signed-off-by: lizhenneng <redacted>
Co-authored-by: lizhenneng <redacted>
ggml/src/ggml-cpu/CMakeLists.txt diff | blob | history
Packaging of ggml-org/llama.cpp