Fix MacOS Sonoma model quantization (ggml-org#4052)

Co-authored-by: Jared Van Bortel <[email protected]>
Co-authored-by: Georgi Gerganov <[email protected]>

Author: 3 people

CMakeLists.txt

@@ -458,6 +458,15 @@ if (LLAMA_LTO)
     endif()
 endif()
 
+# this version of Apple ld64 is buggy
+execute_process(
+    COMMAND ${CMAKE_C_COMPILER} ${CMAKE_EXE_LINKER_FLAGS} -Wl,-v
+    ERROR_VARIABLE output
+)
+if (output MATCHES "dyld-1015\.7")
+    add_compile_definitions(HAVE_BUGGY_APPLE_LINKER)
+endif()
+
 # Architecture specific
 # TODO: probably these flags need to be tweaked on some architectures
 #       feel free to update the Makefile for your architecture and send a pull request or issue

Makefile

@@ -239,6 +239,11 @@ else
 	endif
 endif
 
+# this version of Apple ld64 is buggy
+ifneq '' '$(findstring dyld-1015.7,$(shell $(CC) $(LDFLAGS) -Wl,-v 2>&1))'
+	MK_CPPFLAGS += -DHAVE_BUGGY_APPLE_LINKER
+endif
+
 # OS specific
 # TODO: support Windows
 ifneq '' '$(filter $(UNAME_S),Linux Darwin FreeBSD NetBSD OpenBSD Haiku)'

ggml-quants.c

@@ -1368,7 +1368,12 @@ static float make_qkx2_quants(int n, int nmax, const float * restrict x, const f
     float max = x[0];
     float sum_w = weights[0];
     float sum_x = sum_w * x[0];
+#ifdef HAVE_BUGGY_APPLE_LINKER
+    // use 'volatile' to prevent unroll and work around a bug in Apple ld64 1015.7
+    for (volatile int i = 1; i < n; ++i) {
+#else
     for (int i = 1; i < n; ++i) {
+#endif
         if (x[i] < min) min = x[i];
         if (x[i] > max) max = x[i];
         float w = weights[i];