tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-20 17:49:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu : rework weak alias on apple targets (#14146)

Browse Source 
* ggml-cpu : rework weak alias on apple targets

* fix powerpc detection

* fix ppc detection

* fix powerpc detection on darwin
This commit is contained in:
xctan
2025-06-16 13:54:15 +08:00
committed by GitHub
parent d7da8dc83a
commit 3555b3004b
7 changed files with 99 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@ -509,7 +509,7 @@ void ggml_barrier(struct ggml_threadpool * tp);
#define GGML_DO_PRAGMA_(x) _Pragma (#x)
#define GGML_DO_PRAGMA(x) GGML_DO_PRAGMA_(x)
#if defined(GGML_CPU_GENERIC) || defined(__HIPCC__)
#if defined(GGML_CPU_GENERIC) || defined(__HIPCC__) || defined(__APPLE__)
// Note for Apple targets:
// - clang: aliases are not supported on darwin
// - all native kernels need to be implemented in both x86 and arm files