Apply fixes suggested to build on windows

Issue: ggml-org#22

Author: etra0

ggml.c

@@ -407,8 +407,8 @@ void quantize_row_q4_0(const float * restrict x, void * restrict y, int k) {
     const int nb = k / QK;
     const size_t bs = sizeof(float) + QK/2;
 
-    uint8_t * restrict pd = (uint8_t *) (y + 0*bs);
-    uint8_t * restrict pb = (uint8_t *) (y + 0*bs + sizeof(float));
+    uint8_t * restrict pd = ((uint8_t *)y + 0*bs);
+    uint8_t * restrict pb = ((uint8_t *)y + 0*bs + sizeof(float));
 
     uint8_t pp[QK/2];
 
@@ -654,8 +654,8 @@ void dequantize_row_q4_0(const void * restrict x, float * restrict y, int k) {
     const int nb = k / QK;
     const size_t bs = sizeof(float) + QK/2;
 
-    const uint8_t * restrict pd = (const uint8_t *) (x + 0*bs);
-    const uint8_t * restrict pb = (const uint8_t *) (x + 0*bs + sizeof(float));
+    const uint8_t * restrict pd = ((const uint8_t *)x + 0*bs);
+    const uint8_t * restrict pb = ((const uint8_t *)x + 0*bs + sizeof(float));
 
     // scalar
     for (int i = 0; i < nb; i++) {
@@ -1301,11 +1301,11 @@ inline static void ggml_vec_dot_q4_0(const int n, float * restrict s, const void
 
     const size_t bs = sizeof(float) + QK/2;
 
-    const uint8_t * restrict pd0 = (const uint8_t *) (x + 0*bs);
-    const uint8_t * restrict pd1 = (const uint8_t *) (y + 0*bs);
+    const uint8_t * restrict pd0 = ((const uint8_t *)x + 0*bs);
+    const uint8_t * restrict pd1 = ((const uint8_t *)y + 0*bs);
 
-    const uint8_t * restrict pb0 = (const uint8_t *) (x + 0*bs + sizeof(float));
-    const uint8_t * restrict pb1 = (const uint8_t *) (y + 0*bs + sizeof(float));
+    const uint8_t * restrict pb0 = ((const uint8_t *)x + 0*bs + sizeof(float));
+    const uint8_t * restrict pb1 = ((const uint8_t *)y + 0*bs + sizeof(float));
 
     float sumf = 0.0;
 
@@ -1731,8 +1731,8 @@ inline static void ggml_vec_mad_q4_0(const int n, float * restrict y, void * res
     const int nb = n / QK;
     const size_t bs = sizeof(float) + QK/2;
 
-    const uint8_t * restrict pd = (const uint8_t *) (x + 0*bs);
-    const uint8_t * restrict pb = (const uint8_t *) (x + 0*bs + sizeof(float));
+    const uint8_t * restrict pd = ((const uint8_t *)x + 0*bs);
+    const uint8_t * restrict pb = ((const uint8_t *)x + 0*bs + sizeof(float));
 
 #if __ARM_NEON
 #if QK == 32

ggml.h

@@ -183,6 +183,8 @@ extern "C" {
 #define GGML_MAX_CONTEXTS 64
 #define GGML_MAX_OPT      4
 
+#define QK 32
+
 #ifdef __ARM_NEON
 // we use the built-in 16-bit float type
 typedef __fp16 ggml_fp16_t;

main.cpp

@@ -733,6 +733,7 @@ bool llama_eval(
 }
 
 int main(int argc, char ** argv) {
+    ggml_time_init();
     const int64_t t_main_start_us = ggml_time_us();
 
     gpt_params params;

quantize.cpp

@@ -289,6 +289,7 @@ bool llama_model_quantize(const std::string & fname_inp, const std::string & fna
 //  ./llama-quantize models/llama/ggml-model.bin models/llama/ggml-model-quant.bin type
 //
 int main(int argc, char ** argv) {
+    ggml_time_init();
     if (argc != 4) {
         fprintf(stderr, "usage: %s model-f32.bin model-quant.bin type\n", argv[0]);
         fprintf(stderr, "  type = 2 - q4_0\n");

utils.cpp

@@ -1,4 +1,5 @@
 #include "utils.h"
+#define QK 32
 
 #include <cassert>
 #include <cstring>
@@ -453,7 +454,7 @@ size_t ggml_quantize_q4_0(float * src, void * dst, int n, int k, int qk, int64_t
 
     assert(k % qk == 0);
 
-    uint8_t pp[qk/2];
+    uint8_t pp[QK/2];
 
     char * pdst = (char *) dst;
 
@@ -507,7 +508,7 @@ size_t ggml_quantize_q4_1(float * src, void * dst, int n, int k, int qk, int64_t
 
     assert(k % qk == 0);
 
-    uint8_t pp[qk/2];
+    uint8_t pp[QK/2];
 
     char * pdst = (char *) dst;