CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-27 08:21:30 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml : fix build broken with -march=armv9-a on MacOS (#16520)

Browse Source 
* ggml : fix build broken with -march=armv9-a on MacOS

Signed-off-by: Jie Fu <jiefu@tencent.com>

* Add #pragma message

Signed-off-by: Jie Fu <jiefu@tencent.com>

* Address review comment.

Signed-off-by: Jie Fu <jiefu@tencent.com>

* Update ggml/src/ggml-cpu/ggml-cpu.c

---------

Signed-off-by: Jie Fu <jiefu@tencent.com>
Co-authored-by: Diego Devesa <slarengh@gmail.com>
This commit is contained in:
Jie Fu (傅杰)
2025-10-13 20:48:47 +08:00
committed by GitHub
parent 56fc38b965
commit 01d2bdc2bc
2 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml/src/ggml-cpu/ggml-cpu-impl.h
View File

@@ -68,7 +68,7 @@ struct ggml_compute_params {
#endif // __VXE2__
#endif // __s390x__ && __VEC__
#if defined(__ARM_FEATURE_SVE)
#if defined(__ARM_FEATURE_SVE) && defined(__linux__)
#include <sys/prctl.h>
#endif

7
ggml/src/ggml-cpu/ggml-cpu.c
View File

@@ -689,8 +689,13 @@ bool ggml_is_numa(void) {
#endif
static void ggml_init_arm_arch_features(void) {
#if defined(__linux__) && defined(__aarch64__) && defined(__ARM_FEATURE_SVE)
#if defined(__aarch64__) && defined(__ARM_FEATURE_SVE)
#if defined(__linux__)
ggml_arm_arch_features.sve_cnt = PR_SVE_VL_LEN_MASK & prctl(PR_SVE_GET_VL);
#else
// TODO: add support of SVE for non-linux systems
#error "TODO: SVE is not supported on this platform. To use SVE, sve_cnt needs to be initialized here."
#endif
#endif
}