fix compilation errors

Author: xctan

ggml/src/ggml-cpu/arch/arm/quants.c

@@ -129,6 +129,10 @@ void quantize_row_q8_1(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, i
 #endif
 }
 
+// placeholder implementation for Apple targets
+void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k) {
+    quantize_row_q8_K_ref(x, y, k);
+}
 
 //===================================== Dot products =================================
 

ggml/src/ggml-cpu/arch/x86/quants.c

@@ -477,6 +477,10 @@ void quantize_row_q8_1(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, i
 #endif
 }
 
+// placeholder implementation for Apple targets
+void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k) {
+    quantize_row_q8_K_ref(x, y, k);
+}
 
 //===================================== Dot products =================================
 

ggml/src/ggml-cpu/ggml-cpu-impl.h

@@ -509,8 +509,11 @@ 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__)
-// weak alias not working
+#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
+// - on iOS, tvOS, and visionOS, if cmake cannot determine the target architecture, all `_generic` names are replaced by defines
 # define GGML_WEAK_ALIAS(name, alias)
 #elif defined(__GNUC__)
 // GCC/Clang on *nix

ggml/src/ggml-cuda/common.cuh

@@ -466,9 +466,6 @@ static __device__ __forceinline__ int ggml_cuda_dp4a(const int a, const int b, i
 #endif // defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)
 }
 
-// TODO: move to ggml-common.h
-static constexpr __device__ int8_t kvalues_iq4nl[16] = {-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113};
-
 typedef void (*dequantize_kernel_t)(const void * vx, const int64_t ib, const int iqs, dfloat2 & v);
 
 static __device__ __forceinline__ float get_alibi_slope(

ggml/src/ggml-sycl/common.hpp

@@ -149,8 +149,6 @@ typedef sycl::float2 dfloat2;
 
 #define MMVQ_MAX_BATCH_SIZE  8
 
-static const int8_t kvalues_iq4nl[16]={-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113};
-
 static int g_all_sycl_device_count = -1;
 static bool g_ggml_backend_sycl_buffer_type_initialized = false;