Update ggml-quants.c

Author: CISC

ggml-quants.c

@@ -11543,6 +11543,7 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
 
     float  scales[QK_K/IQ1S_BLOCK_SIZE];
     float  weight[IQ1S_BLOCK_SIZE];
+    float  waux[IQ1S_BLOCK_SIZE];
     int8_t L[IQ1S_BLOCK_SIZE];
     float  sumx[IQ1S_BLOCK_SIZE+1];
     float  sumw[IQ1S_BLOCK_SIZE+1];
@@ -11562,12 +11563,13 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
         const float * xbl = x + QK_K*ibl;
         float sumx2 = 0;
         for (int i = 0; i < QK_K; ++i) sumx2 += xbl[i]*xbl[i];
-        float sigma2 = 2*sumx2/QK_K;
+        float sigma2 = sumx2/QK_K;
 
         for (int ib = 0; ib < QK_K/IQ1S_BLOCK_SIZE; ++ib) {
             const float * xb = xbl + IQ1S_BLOCK_SIZE*ib;
             const float * qw = quant_weights + QK_K*ibl + IQ1S_BLOCK_SIZE*ib;
             for (int i = 0; i < IQ1S_BLOCK_SIZE; ++i) weight[i] = qw[i] * sqrtf(sigma2 + xb[i]*xb[i]);
+            for (int i = 0; i < IQ1S_BLOCK_SIZE; ++i) waux[i] = sqrtf(weight[i]);
             float max = fabsf(xb[0]);
             for (int i = 1; i < IQ1S_BLOCK_SIZE; ++i) max = MAX(max, fabsf(xb[i]));
             if (!max) {
@@ -11629,7 +11631,7 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
                 if (grid_index < 0) {
                     all_on_grid = false;
                     const uint16_t * neighbours = kneighbors_q2xs - kmap_q2xs[u] - 1;
-                    grid_index = iq1_find_best_neighbour2(neighbours, kgrid_q2xs, xb + 8*k, weight + 8*k, scale, xx, L + 8*k, NGRID_IQ1S);
+                    grid_index = iq1_find_best_neighbour2(neighbours, kgrid_q2xs, xb + 8*k, waux + 8*k, scale, xx, L + 8*k, NGRID_IQ1S);
                     GGML_ASSERT(grid_index >= 0);
                 }
                 index[k] = grid_index;