llama_cpp 0.13.0 → 0.14.1

data/vendor/tmp/llama.cpp/ggml-quants.c

@@ -1,6 +1,12 @@
+#define GGML_COMMON_IMPL_C
+#include "ggml-common.h"
+
 #include "ggml-quants.h"
 #include "ggml-impl.h"
 
+#define GGML_COMMON_IMPL_C
+#include "ggml-common.h"
+
 #include <math.h>
 #include <string.h>
 #include <assert.h>
@@ -51,6 +57,7 @@
 
 #define UNUSED GGML_UNUSED
 
+// some compilers don't provide _mm256_set_m128i, e.g. gcc 7
 #define MM256_SET_M128I(a, b) _mm256_insertf128_si256(_mm256_castsi128_si256(b), (a), 1)
 
 #if defined(__AVX__) || defined(__AVX2__) || defined(__AVX512F__) || defined(__SSSE3__)
@@ -463,8 +470,8 @@ inline static int8x16_t ggml_vqtbl1q_s8(int8x16_t a, uint8x16_t b) {
 }
 
 // NOTE: not tested
-inline static int8x16_t ggml_vqtbl1q_u8(uint8x16_t a, uint8x16_t b) {
-    int8x16_t res;
+inline static uint8x16_t ggml_vqtbl1q_u8(uint8x16_t a, uint8x16_t b) {
+    uint8x16_t res;
 
     res[ 0] = a[b[ 0]];
     res[ 1] = a[b[ 1]];
@@ -947,7 +954,7 @@ void quantize_row_q8_1_reference(const float * restrict x, block_q8_1 * restrict
         const float d = amax / ((1 << 7) - 1);
         const float id = d ? 1.0f/d : 0.0f;
 
-        y[i].d = d;
+        y[i].d = GGML_FP32_TO_FP16(d);
 
         int sum = 0;
 
@@ -962,7 +969,7 @@ void quantize_row_q8_1_reference(const float * restrict x, block_q8_1 * restrict
             sum += y[i].qs[QK8_1/2 + j];
         }
 
-        y[i].s = sum*d;
+        y[i].s = GGML_FP32_TO_FP16(sum*d);
     }
 }
 
@@ -990,7 +997,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
         const float d = amax / ((1 << 7) - 1);
         const float id = d ? 1.0f/d : 0.0f;
 
-        y[i].d = d;
+        y[i].d = GGML_FP32_TO_FP16(d);
 
         int32x4_t accv = vdupq_n_s32(0);
 
@@ -1006,7 +1013,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
             accv = vaddq_s32(accv, vi);
         }
 
-        y[i].s = d * vaddvq_s32(accv);
+        y[i].s = GGML_FP32_TO_FP16(d * vaddvq_s32(accv));
     }
 #elif defined(__wasm_simd128__)
     for (int i = 0; i < nb; i++) {
@@ -1029,7 +1036,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
         const float d = amax / ((1 << 7) - 1);
         const float id = d ? 1.0f/d : 0.0f;
 
-        y[i].d = d;
+        y[i].d = GGML_FP32_TO_FP16(d);
 
         v128_t accv = wasm_i32x4_splat(0);
 
@@ -1045,10 +1052,11 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
             accv = wasm_i32x4_add(accv, vi);
         }
 
-        y[i].s = d * (wasm_i32x4_extract_lane(accv, 0) +
-                      wasm_i32x4_extract_lane(accv, 1) +
-                      wasm_i32x4_extract_lane(accv, 2) +
-                      wasm_i32x4_extract_lane(accv, 3));
+        y[i].s = GGML_FP32_TO_FP16(
+                d * (wasm_i32x4_extract_lane(accv, 0) +
+                     wasm_i32x4_extract_lane(accv, 1) +
+                     wasm_i32x4_extract_lane(accv, 2) +
+                     wasm_i32x4_extract_lane(accv, 3)));
     }
 #elif defined(__AVX2__) || defined(__AVX__)
     for (int i = 0; i < nb; i++) {
@@ -1073,7 +1081,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
 
         // Quantize these floats
         const float d = maxScalar / 127.f;
-        y[i].d = d;
+        y[i].d = GGML_FP32_TO_FP16(d);
         const float id = ( maxScalar != 0.0f ) ? 127.f / maxScalar : 0.0f;
         const __m256 mul = _mm256_set1_ps( id );
 
@@ -1097,7 +1105,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
 
 #if defined(__AVX2__)
         // Compute the sum of the quants and set y[i].s
-        y[i].s = d * hsum_i32_8(_mm256_add_epi32(_mm256_add_epi32(i0, i1), _mm256_add_epi32(i2, i3)));
+        y[i].s = GGML_FP32_TO_FP16(d * hsum_i32_8(_mm256_add_epi32(_mm256_add_epi32(i0, i1), _mm256_add_epi32(i2, i3))));
 
         // Convert int32 to int16
         i0 = _mm256_packs_epi32( i0, i1 );	// 0, 1, 2, 3,  8, 9, 10, 11,  4, 5, 6, 7, 12, 13, 14, 15
@@ -1127,7 +1135,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
         // Compute the sum of the quants and set y[i].s
         const __m128i s0 = _mm_add_epi32(_mm_add_epi32(ni0, ni1), _mm_add_epi32(ni2, ni3));
         const __m128i s1 = _mm_add_epi32(_mm_add_epi32(ni4, ni5), _mm_add_epi32(ni6, ni7));
-        y[i].s = d * hsum_i32_4(_mm_add_epi32(s0, s1));
+        y[i].s = GGML_FP32_TO_FP16(d * hsum_i32_4(_mm_add_epi32(s0, s1)));
 
         // Convert int32 to int16
         ni0 = _mm_packs_epi32( ni0, ni1 );
@@ -1158,7 +1166,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
         const float d  = amax / ((1 << 7) - 1);
         const float id = d ? 1.0f/d : 0.0f;
 
-        y[i].d = d;
+        y[i].d = GGML_FP32_TO_FP16(d);
 
         vfloat32m4_t x0 = __riscv_vfmul_vf_f32m4(v_x, id, vl);
 
@@ -1175,7 +1183,7 @@ void quantize_row_q8_1(const float * restrict x, void * restrict vy, int k) {
 
         // set y[i].s
         int sum = __riscv_vmv_x_s_i16m1_i16(vwrs);
-        y[i].s = sum*d;
+        y[i].s = GGML_FP32_TO_FP16(sum*d);
     }
 #else
     GGML_UNUSED(nb);
@@ -1700,16 +1708,6 @@ void quantize_row_q2_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q2_K_reference(x, vy, k);
 }
 
-size_t ggml_quantize_q2_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q2_K * restrict y = (block_q2_K *)dst + j/QK_K;
-        quantize_row_q2_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q2_K));
-}
-
 static float make_qkx3_quants(int n, int nmax, const float * restrict x, const float * restrict weights,
         uint8_t * restrict L, float * restrict the_min, uint8_t * restrict Laux,
         float rmin, float rdelta, int nstep, bool use_mad) {
@@ -1962,8 +1960,7 @@ static void quantize_row_q2_K_impl(const float * restrict x, block_q2_K * restri
     }
 }
 
-size_t quantize_q2_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q2_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q2_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q2_K_reference(src, dst, nrow*n_per_row);
@@ -2182,16 +2179,6 @@ void quantize_row_q3_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q3_K_reference(x, vy, k);
 }
 
-size_t ggml_quantize_q3_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q3_K * restrict y = (block_q3_K *)dst + j/QK_K;
-        quantize_row_q3_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q3_K));
-}
-
 static void quantize_row_q3_K_impl(const float * restrict x, block_q3_K * restrict y, int n_per_row, const float * restrict quant_weights) {
 #if QK_K != 256
     (void)quant_weights;
@@ -2281,8 +2268,7 @@ static void quantize_row_q3_K_impl(const float * restrict x, block_q3_K * restri
 #endif
 }
 
-size_t quantize_q3_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q3_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q3_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q3_K_reference(src, dst, nrow*n_per_row);
@@ -2452,17 +2438,6 @@ void quantize_row_q4_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q4_K_reference(x, y, k);
 }
 
-size_t ggml_quantize_q4_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
-    assert(k % QK_K == 0);
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q4_K * restrict y = (block_q4_K *)dst + j/QK_K;
-        quantize_row_q4_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q4_K));
-}
-
 static void quantize_row_q4_K_impl(const float * restrict x, block_q4_K * restrict y, int n_per_row, const float * quant_weights) {
 #if QK_K != 256
     (void)quant_weights;
@@ -2541,8 +2516,7 @@ static void quantize_row_q4_K_impl(const float * restrict x, block_q4_K * restri
 #endif
 }
 
-size_t quantize_q4_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q4_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q4_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q4_K_reference(src, dst, nrow*n_per_row);
@@ -2753,17 +2727,6 @@ void quantize_row_q5_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q5_K_reference(x, y, k);
 }
 
-size_t ggml_quantize_q5_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
-    assert(k % QK_K == 0);
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q5_K * restrict y = (block_q5_K *)dst + j/QK_K;
-        quantize_row_q5_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q5_K));
-}
-
 static void quantize_row_q5_K_impl(const float * restrict x, block_q5_K * restrict y, int n_per_row, const float * quant_weights) {
 #if QK_K != 256
     (void)quant_weights;
@@ -2862,8 +2825,7 @@ static void quantize_row_q5_K_impl(const float * restrict x, block_q5_K * restri
 #endif
 }
 
-size_t quantize_q5_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q5_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q5_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q5_K_reference(src, dst, nrow*n_per_row);
@@ -3016,17 +2978,6 @@ void quantize_row_q6_K(const float * restrict x, void * restrict vy, int k) {
     quantize_row_q6_K_reference(x, y, k);
 }
 
-size_t ggml_quantize_q6_K(const float * src, void * dst, int n, int k, int64_t * hist) {
-    assert(k % QK_K == 0);
-    (void)hist; // TODO: collect histograms
-
-    for (int j = 0; j < n; j += k) {
-        block_q6_K * restrict y = (block_q6_K *)dst + j/QK_K;
-        quantize_row_q6_K_reference(src + j, y, k);
-    }
-    return (n/QK_K*sizeof(block_q6_K));
-}
-
 static void quantize_row_q6_K_impl(const float * restrict x, block_q6_K * restrict y, int n_per_row, const float * quant_weights) {
 #if QK_K != 256
     (void)quant_weights;
@@ -3116,8 +3067,7 @@ static void quantize_row_q6_K_impl(const float * restrict x, block_q6_K * restri
 #endif
 }
 
-size_t quantize_q6_K(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_q6_K(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     size_t row_size = ggml_row_size(GGML_TYPE_Q6_K, n_per_row);
     if (!quant_weights) {
         quantize_row_q6_K_reference(src, dst, nrow*n_per_row);
@@ -3161,9 +3111,10 @@ static void quantize_row_q4_0_impl(const float * restrict x, block_q4_0 * restri
     }
 }
 
-size_t quantize_q4_0(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_q4_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     if (!quant_weights) {
-        return ggml_quantize_q4_0(src, dst, nrow*n_per_row, n_per_row, hist);
+        quantize_row_q4_0_reference(src, dst, nrow*n_per_row);
+        return nrow * ggml_row_size(GGML_TYPE_Q4_0, n_per_row);
     }
     size_t row_size = ggml_row_size(GGML_TYPE_Q4_0, n_per_row);
     char * qrow = (char *)dst;
@@ -3205,9 +3156,10 @@ static void quantize_row_q4_1_impl(const float * restrict x, block_q4_1 * restri
     }
 }
 
-size_t quantize_q4_1(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_q4_1(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     if (!quant_weights) {
-        return ggml_quantize_q4_1(src, dst, nrow*n_per_row, n_per_row, hist);
+        quantize_row_q4_1_reference(src, dst, nrow*n_per_row);
+        return nrow * ggml_row_size(GGML_TYPE_Q4_1, n_per_row);
     }
     size_t row_size = ggml_row_size(GGML_TYPE_Q4_1, n_per_row);
     char * qrow = (char *)dst;
@@ -3258,9 +3210,10 @@ static void quantize_row_q5_0_impl(const float * restrict x, block_q5_0 * restri
     }
 }
 
-size_t quantize_q5_0(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_q5_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     if (!quant_weights) {
-        return ggml_quantize_q5_0(src, dst, nrow*n_per_row, n_per_row, hist);
+        quantize_row_q5_0_reference(src, dst, nrow*n_per_row);
+        return nrow * ggml_row_size(GGML_TYPE_Q5_0, n_per_row);
     }
     size_t row_size = ggml_row_size(GGML_TYPE_Q5_0, n_per_row);
     char * qrow = (char *)dst;
@@ -3310,9 +3263,10 @@ static void quantize_row_q5_1_impl(const float * restrict x, block_q5_1 * restri
     }
 }
 
-size_t quantize_q5_1(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_q5_1(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     if (!quant_weights) {
-        return ggml_quantize_q5_1(src, dst, nrow*n_per_row, n_per_row, hist);
+        quantize_row_q5_1_reference(src, dst, nrow*n_per_row);
+        return nrow * ggml_row_size(GGML_TYPE_Q5_1, n_per_row);
     }
     size_t row_size = ggml_row_size(GGML_TYPE_Q5_1, n_per_row);
     char * qrow = (char *)dst;
@@ -3324,712 +3278,14 @@ size_t quantize_q5_1(const float * src, void * dst, int nrow, int n_per_row, int
     return nrow * row_size;
 }
 
-// ====================== "True" 2-bit (de)-quantization
-
-static const  uint64_t iq2xxs_grid[256] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x08080808082b0808,
-    0x08080808082b082b, 0x08080808082b2b08, 0x08080808082b2b2b, 0x0808080819080819,
-    0x0808080819081908, 0x0808080819190808, 0x0808080819192b08, 0x08080808192b0819,
-    0x08080808192b1908, 0x080808082b080808, 0x080808082b08082b, 0x080808082b082b2b,
-    0x080808082b2b082b, 0x0808081908080819, 0x0808081908081908, 0x0808081908190808,
-    0x0808081908191919, 0x0808081919080808, 0x080808192b081908, 0x080808192b192b08,
-    0x0808082b08080808, 0x0808082b0808082b, 0x0808082b082b082b, 0x0808082b2b08082b,
-    0x0808190808080819, 0x0808190808081908, 0x0808190808190808, 0x08081908082b0819,
-    0x08081908082b1908, 0x0808190819080808, 0x080819081908082b, 0x0808190819082b08,
-    0x08081908192b0808, 0x080819082b080819, 0x080819082b081908, 0x080819082b190808,
-    0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b, 0x0808191908082b08,
-    0x08081919082b0808, 0x080819191908192b, 0x08081919192b2b19, 0x080819192b080808,
-    0x080819192b190819, 0x0808192b08082b19, 0x0808192b08190808, 0x0808192b19080808,
-    0x0808192b2b081908, 0x0808192b2b2b1908, 0x08082b0808080808, 0x08082b0808081919,
-    0x08082b0808082b08, 0x08082b0808191908, 0x08082b08082b2b08, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b081919082b, 0x08082b082b082b08,
-    0x08082b1908081908, 0x08082b1919080808, 0x08082b2b0808082b, 0x08082b2b08191908,
-    0x0819080808080819, 0x0819080808081908, 0x0819080808190808, 0x08190808082b0819,
-    0x0819080819080808, 0x08190808192b0808, 0x081908082b081908, 0x081908082b190808,
-    0x081908082b191919, 0x0819081908080808, 0x0819081908082b08, 0x08190819082b0808,
-    0x0819081919190808, 0x0819081919192b2b, 0x081908192b080808, 0x0819082b082b1908,
-    0x0819082b19081919, 0x0819190808080808, 0x0819190808082b08, 0x08191908082b0808,
-    0x08191908082b1919, 0x0819190819082b19, 0x081919082b080808, 0x0819191908192b08,
-    0x08191919192b082b, 0x0819192b08080808, 0x0819192b0819192b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b0808190808, 0x08192b0819080808, 0x08192b082b080819,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b192b2b0808, 0x08192b2b19190819,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808082b2b, 0x082b080819081908,
-    0x082b0808192b0819, 0x082b08082b080808, 0x082b08082b08082b, 0x082b0819082b2b19,
-    0x082b081919082b08, 0x082b082b08080808, 0x082b082b0808082b, 0x082b190808080819,
-    0x082b190808081908, 0x082b190808190808, 0x082b190819080808, 0x082b19081919192b,
-    0x082b191908080808, 0x082b191919080819, 0x082b1919192b1908, 0x082b192b2b190808,
-    0x082b2b0808082b08, 0x082b2b08082b0808, 0x082b2b082b191908, 0x082b2b2b19081908,
-    0x1908080808080819, 0x1908080808081908, 0x1908080808190808, 0x1908080808192b08,
-    0x19080808082b0819, 0x19080808082b1908, 0x1908080819080808, 0x1908080819082b08,
-    0x190808081919192b, 0x19080808192b0808, 0x190808082b080819, 0x190808082b081908,
-    0x190808082b190808, 0x1908081908080808, 0x19080819082b0808, 0x19080819192b0819,
-    0x190808192b080808, 0x190808192b081919, 0x1908082b08080819, 0x1908082b08190808,
-    0x1908082b19082b08, 0x1908082b1919192b, 0x1908082b192b2b08, 0x1908190808080808,
-    0x1908190808082b08, 0x19081908082b0808, 0x190819082b080808, 0x190819082b192b19,
-    0x190819190819082b, 0x19081919082b1908, 0x1908192b08080808, 0x19082b0808080819,
-    0x19082b0808081908, 0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919,
-    0x19082b1908080808, 0x19082b1919192b08, 0x19082b19192b0819, 0x19082b192b08082b,
-    0x19082b2b19081919, 0x19082b2b2b190808, 0x1919080808080808, 0x1919080808082b08,
-    0x1919080808190819, 0x1919080808192b19, 0x19190808082b0808, 0x191908082b080808,
-    0x191908082b082b08, 0x1919081908081908, 0x191908191908082b, 0x191908192b2b1908,
-    0x1919082b2b190819, 0x191919082b190808, 0x191919082b19082b, 0x1919191908082b2b,
-    0x1919192b08080819, 0x1919192b19191908, 0x19192b0808080808, 0x19192b0808190819,
-    0x19192b0808192b19, 0x19192b08192b1908, 0x19192b1919080808, 0x19192b2b08082b08,
-    0x192b080808081908, 0x192b080808190808, 0x192b080819080808, 0x192b0808192b2b08,
-    0x192b081908080808, 0x192b081919191919, 0x192b082b08192b08, 0x192b082b192b0808,
-    0x192b190808080808, 0x192b190808081919, 0x192b191908190808, 0x192b19190819082b,
-    0x192b19192b081908, 0x192b2b081908082b, 0x2b08080808080808, 0x2b0808080808082b,
-    0x2b08080808082b2b, 0x2b08080819080819, 0x2b0808082b08082b, 0x2b08081908081908,
-    0x2b08081908192b08, 0x2b08081919080808, 0x2b08082b08190819, 0x2b08190808080819,
-    0x2b08190808081908, 0x2b08190808190808, 0x2b08190808191919, 0x2b08190819080808,
-    0x2b081908192b0808, 0x2b08191908080808, 0x2b0819191908192b, 0x2b0819192b191908,
-    0x2b08192b08082b19, 0x2b08192b19080808, 0x2b08192b192b0808, 0x2b082b080808082b,
-    0x2b082b1908081908, 0x2b082b2b08190819, 0x2b19080808081908, 0x2b19080808190808,
-    0x2b190808082b1908, 0x2b19080819080808, 0x2b1908082b2b0819, 0x2b1908190819192b,
-    0x2b1908192b080808, 0x2b19082b19081919, 0x2b19190808080808, 0x2b191908082b082b,
-    0x2b19190819081908, 0x2b19191919190819, 0x2b192b082b080819, 0x2b192b19082b0808,
-    0x2b2b08080808082b, 0x2b2b080819190808, 0x2b2b08082b081919, 0x2b2b081908082b19,
-    0x2b2b082b08080808, 0x2b2b190808192b08, 0x2b2b2b0819190808, 0x2b2b2b1908081908,
-};
-
-static const uint64_t iq2xs_grid[512] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x080808082b080808,
-    0x080808082b08082b, 0x080808082b081919, 0x080808082b082b08, 0x080808082b190819,
-    0x080808082b191908, 0x080808082b192b19, 0x080808082b2b0808, 0x0808081908080819,
-    0x0808081908081908, 0x080808190808192b, 0x0808081908082b19, 0x0808081908190808,
-    0x080808190819082b, 0x0808081908191919, 0x0808081908192b08, 0x0808081908192b2b,
-    0x08080819082b0819, 0x08080819082b1908, 0x0808081919080808, 0x080808191908082b,
-    0x0808081919081919, 0x0808081919082b08, 0x0808081919190819, 0x0808081919191908,
-    0x08080819192b0808, 0x08080819192b2b08, 0x080808192b080819, 0x080808192b081908,
-    0x080808192b190808, 0x0808082b08080808, 0x0808082b0808082b, 0x0808082b08081919,
-    0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908, 0x0808082b082b0808,
-    0x0808082b19080819, 0x0808082b19081908, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b082b2b, 0x0808190808080819, 0x0808190808081908,
-    0x080819080808192b, 0x0808190808082b19, 0x0808190808190808, 0x080819080819082b,
-    0x0808190808191919, 0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908,
-    0x0808190819080808, 0x080819081908082b, 0x0808190819081919, 0x0808190819082b08,
-    0x0808190819190819, 0x0808190819191908, 0x080819081919192b, 0x08081908192b0808,
-    0x080819082b080819, 0x080819082b081908, 0x080819082b190808, 0x0808191908080808,
-    0x080819190808082b, 0x0808191908081919, 0x0808191908082b08, 0x0808191908190819,
-    0x0808191908191908, 0x08081919082b0808, 0x0808191919080819, 0x0808191919081908,
-    0x0808191919190808, 0x08081919192b0819, 0x080819192b080808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b08190808, 0x0808192b082b192b, 0x0808192b19080808,
-    0x0808192b1908082b, 0x0808192b2b081908, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808082b2b, 0x08082b0808190819,
-    0x08082b0808191908, 0x08082b08082b0808, 0x08082b08082b1919, 0x08082b0819080819,
-    0x08082b0819081908, 0x08082b0819190808, 0x08082b0819192b08, 0x08082b082b080808,
-    0x08082b082b2b0808, 0x08082b082b2b2b2b, 0x08082b1908080819, 0x08082b1908081908,
-    0x08082b1908190808, 0x08082b1919080808, 0x08082b192b080819, 0x08082b192b082b19,
-    0x08082b2b08080808, 0x08082b2b082b0808, 0x08082b2b082b2b08, 0x08082b2b2b19192b,
-    0x08082b2b2b2b0808, 0x0819080808080819, 0x0819080808081908, 0x081908080808192b,
-    0x0819080808082b19, 0x0819080808190808, 0x081908080819082b, 0x0819080808191919,
-    0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908, 0x0819080819080808,
-    0x081908081908082b, 0x0819080819081919, 0x0819080819082b08, 0x0819080819190819,
-    0x0819080819191908, 0x08190808192b0808, 0x08190808192b2b2b, 0x081908082b080819,
-    0x081908082b081908, 0x081908082b190808, 0x0819081908080808, 0x081908190808082b,
-    0x0819081908081919, 0x0819081908082b08, 0x0819081908190819, 0x0819081908191908,
-    0x08190819082b0808, 0x0819081919080819, 0x0819081919081908, 0x0819081919190808,
-    0x081908192b080808, 0x081908192b191908, 0x081908192b19192b, 0x0819082b08080819,
-    0x0819082b08081908, 0x0819082b0808192b, 0x0819082b08190808, 0x0819082b19080808,
-    0x0819082b192b0808, 0x0819190808080808, 0x081919080808082b, 0x0819190808081919,
-    0x0819190808082b08, 0x0819190808190819, 0x0819190808191908, 0x08191908082b0808,
-    0x0819190819080819, 0x0819190819081908, 0x0819190819082b19, 0x0819190819190808,
-    0x08191908192b1908, 0x081919082b080808, 0x0819191908080819, 0x0819191908081908,
-    0x0819191908190808, 0x0819191919080808, 0x0819192b08080808, 0x0819192b08191908,
-    0x0819192b19082b19, 0x08192b0808080819, 0x08192b0808081908, 0x08192b0808190808,
-    0x08192b080819082b, 0x08192b0819080808, 0x08192b0819191908, 0x08192b082b08192b,
-    0x08192b1908080808, 0x08192b1908081919, 0x08192b19192b192b, 0x08192b2b19190819,
-    0x08192b2b2b2b2b19, 0x082b080808080808, 0x082b08080808082b, 0x082b080808081919,
-    0x082b080808082b08, 0x082b080808082b2b, 0x082b080808190819, 0x082b080808191908,
-    0x082b0808082b0808, 0x082b080819080819, 0x082b080819081908, 0x082b080819190808,
-    0x082b08082b080808, 0x082b08082b2b0808, 0x082b081908080819, 0x082b081908081908,
-    0x082b081908190808, 0x082b081919080808, 0x082b081919082b08, 0x082b0819192b1919,
-    0x082b082b08080808, 0x082b082b082b082b, 0x082b082b2b080808, 0x082b082b2b2b2b08,
-    0x082b190808080819, 0x082b190808081908, 0x082b190808190808, 0x082b1908082b2b19,
-    0x082b190819080808, 0x082b191908080808, 0x082b191919080819, 0x082b19191919082b,
-    0x082b19192b192b19, 0x082b192b08080819, 0x082b192b08192b2b, 0x082b192b2b2b192b,
-    0x082b2b0808080808, 0x082b2b0808082b08, 0x082b2b0808082b2b, 0x082b2b08082b0808,
-    0x082b2b0819191919, 0x082b2b082b082b08, 0x082b2b082b2b082b, 0x082b2b19192b2b08,
-    0x082b2b192b190808, 0x082b2b2b08082b08, 0x082b2b2b082b0808, 0x082b2b2b2b08082b,
-    0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819, 0x1908080808081908,
-    0x190808080808192b, 0x1908080808082b19, 0x1908080808190808, 0x190808080819082b,
-    0x1908080808191919, 0x1908080808192b08, 0x19080808082b0819, 0x19080808082b1908,
-    0x1908080819080808, 0x190808081908082b, 0x1908080819081919, 0x1908080819082b08,
-    0x1908080819082b2b, 0x1908080819190819, 0x1908080819191908, 0x19080808192b0808,
-    0x19080808192b1919, 0x190808082b080819, 0x190808082b081908, 0x190808082b190808,
-    0x1908081908080808, 0x190808190808082b, 0x1908081908081919, 0x1908081908082b08,
-    0x1908081908190819, 0x1908081908191908, 0x19080819082b0808, 0x1908081919080819,
-    0x1908081919081908, 0x1908081919190808, 0x190808192b080808, 0x190808192b081919,
-    0x190808192b2b082b, 0x1908082b08080819, 0x1908082b08081908, 0x1908082b08190808,
-    0x1908082b0819082b, 0x1908082b082b2b19, 0x1908082b19080808, 0x1908190808080808,
-    0x190819080808082b, 0x1908190808081919, 0x1908190808082b08, 0x1908190808190819,
-    0x1908190808191908, 0x1908190808192b19, 0x19081908082b0808, 0x1908190819080819,
-    0x1908190819081908, 0x1908190819190808, 0x190819082b080808, 0x190819082b191908,
-    0x1908191908080819, 0x1908191908081908, 0x1908191908190808, 0x19081919082b1908,
-    0x1908191919080808, 0x190819192b192b2b, 0x1908192b08080808, 0x1908192b08082b2b,
-    0x1908192b19081908, 0x1908192b19190808, 0x19082b0808080819, 0x19082b0808081908,
-    0x19082b0808190808, 0x19082b0819080808, 0x19082b0819081919, 0x19082b0819191908,
-    0x19082b08192b082b, 0x19082b1908080808, 0x19082b1908190819, 0x19082b1919081908,
-    0x19082b1919190808, 0x19082b19192b2b19, 0x19082b2b08081908, 0x1919080808080808,
-    0x191908080808082b, 0x1919080808081919, 0x1919080808082b08, 0x1919080808190819,
-    0x1919080808191908, 0x19190808082b0808, 0x19190808082b2b08, 0x1919080819080819,
-    0x1919080819081908, 0x1919080819190808, 0x191908082b080808, 0x1919081908080819,
-    0x1919081908081908, 0x1919081908190808, 0x1919081908191919, 0x1919081919080808,
-    0x191908191908082b, 0x1919082b08080808, 0x1919082b19081908, 0x1919082b2b2b2b2b,
-    0x1919190808080819, 0x1919190808081908, 0x1919190808190808, 0x19191908082b0819,
-    0x1919190819080808, 0x19191908192b0808, 0x191919082b080819, 0x191919082b2b0819,
-    0x1919191908080808, 0x1919191908082b08, 0x191919192b080808, 0x191919192b082b08,
-    0x1919192b082b0819, 0x1919192b192b2b08, 0x1919192b2b2b0819, 0x19192b0808080808,
-    0x19192b0808191908, 0x19192b0819080819, 0x19192b0819190808, 0x19192b082b192b19,
-    0x19192b1908192b2b, 0x19192b1919080808, 0x19192b191908082b, 0x19192b2b2b081919,
-    0x192b080808080819, 0x192b080808081908, 0x192b080808190808, 0x192b080819080808,
-    0x192b080819191908, 0x192b0808192b082b, 0x192b08082b08192b, 0x192b08082b2b2b19,
-    0x192b081908080808, 0x192b082b082b1908, 0x192b082b19082b2b, 0x192b082b2b19082b,
-    0x192b190808080808, 0x192b19080819192b, 0x192b191908190808, 0x192b191919080808,
-    0x192b191919081919, 0x192b19192b2b1908, 0x192b2b0808080819, 0x192b2b08192b2b2b,
-    0x192b2b19082b1919, 0x192b2b2b0808192b, 0x192b2b2b19191908, 0x192b2b2b192b082b,
-    0x2b08080808080808, 0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08,
-    0x2b08080808190819, 0x2b08080808191908, 0x2b080808082b0808, 0x2b080808082b2b2b,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808082b080808,
-    0x2b0808082b08082b, 0x2b0808082b2b2b08, 0x2b0808082b2b2b2b, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b0808190808192b, 0x2b08081908190808, 0x2b08081919080808,
-    0x2b08081919190819, 0x2b08081919192b19, 0x2b08082b08080808, 0x2b08082b082b0808,
-    0x2b08082b2b080808, 0x2b08082b2b08082b, 0x2b08082b2b2b0808, 0x2b08082b2b2b2b08,
-    0x2b08190808080819, 0x2b08190808081908, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190819080808, 0x2b081908192b0808, 0x2b0819082b082b19,
-    0x2b08191908080808, 0x2b08191919081908, 0x2b0819192b2b1919, 0x2b08192b08192b08,
-    0x2b08192b192b2b2b, 0x2b082b0808080808, 0x2b082b0808082b08, 0x2b082b08082b1919,
-    0x2b082b0819192b2b, 0x2b082b082b080808, 0x2b082b082b08082b, 0x2b082b082b2b2b08,
-    0x2b082b190808192b, 0x2b082b2b082b082b, 0x2b082b2b2b080808, 0x2b082b2b2b082b08,
-    0x2b082b2b2b19192b, 0x2b082b2b2b2b2b08, 0x2b19080808080819, 0x2b19080808081908,
-    0x2b19080808190808, 0x2b19080819080808, 0x2b1908081919192b, 0x2b1908082b081908,
-    0x2b19081908080808, 0x2b190819082b082b, 0x2b190819192b1908, 0x2b19082b1919192b,
-    0x2b19082b2b082b19, 0x2b19190808080808, 0x2b19190808081919, 0x2b19190819081908,
-    0x2b19190819190808, 0x2b19190819192b08, 0x2b191919082b2b19, 0x2b1919192b190808,
-    0x2b1919192b19082b, 0x2b19192b19080819, 0x2b192b0819190819, 0x2b192b082b2b192b,
-    0x2b192b1919082b19, 0x2b192b2b08191919, 0x2b192b2b192b0808, 0x2b2b080808080808,
-    0x2b2b08080808082b, 0x2b2b080808082b08, 0x2b2b080808082b2b, 0x2b2b0808082b0808,
-    0x2b2b0808082b2b2b, 0x2b2b08082b2b0808, 0x2b2b081919190819, 0x2b2b081919192b19,
-    0x2b2b08192b2b192b, 0x2b2b082b08080808, 0x2b2b082b0808082b, 0x2b2b082b08082b08,
-    0x2b2b082b082b2b2b, 0x2b2b082b2b080808, 0x2b2b082b2b2b0808, 0x2b2b190819080808,
-    0x2b2b19082b191919, 0x2b2b192b192b1919, 0x2b2b192b2b192b08, 0x2b2b2b0808082b2b,
-    0x2b2b2b08082b0808, 0x2b2b2b08082b082b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b0808,
-    0x2b2b2b082b2b2b08, 0x2b2b2b1908081908, 0x2b2b2b192b081908, 0x2b2b2b192b08192b,
-    0x2b2b2b2b082b2b08, 0x2b2b2b2b082b2b2b, 0x2b2b2b2b2b190819, 0x2b2b2b2b2b2b2b2b,
-};
-
-static const uint64_t iq2s_grid[1024] = {
-    0x0808080808080808, 0x080808080808082b, 0x0808080808081919, 0x0808080808082b08,
-    0x0808080808082b2b, 0x0808080808190819, 0x0808080808191908, 0x080808080819192b,
-    0x0808080808192b19, 0x08080808082b0808, 0x08080808082b082b, 0x08080808082b1919,
-    0x08080808082b2b08, 0x0808080819080819, 0x0808080819081908, 0x080808081908192b,
-    0x0808080819082b19, 0x0808080819190808, 0x080808081919082b, 0x0808080819191919,
-    0x0808080819192b08, 0x08080808192b0819, 0x08080808192b1908, 0x08080808192b192b,
-    0x08080808192b2b19, 0x080808082b080808, 0x080808082b08082b, 0x080808082b081919,
-    0x080808082b082b08, 0x080808082b190819, 0x080808082b191908, 0x080808082b2b0808,
-    0x080808082b2b1919, 0x080808082b2b2b2b, 0x0808081908080819, 0x0808081908081908,
-    0x080808190808192b, 0x0808081908082b19, 0x0808081908190808, 0x080808190819082b,
-    0x0808081908191919, 0x0808081908192b08, 0x08080819082b0819, 0x08080819082b1908,
-    0x0808081919080808, 0x080808191908082b, 0x0808081919081919, 0x0808081919082b08,
-    0x0808081919190819, 0x0808081919191908, 0x080808191919192b, 0x0808081919192b19,
-    0x08080819192b0808, 0x08080819192b1919, 0x08080819192b2b08, 0x080808192b080819,
-    0x080808192b081908, 0x080808192b190808, 0x080808192b19082b, 0x080808192b191919,
-    0x080808192b2b0819, 0x080808192b2b1908, 0x0808082b08080808, 0x0808082b0808082b,
-    0x0808082b08081919, 0x0808082b08082b08, 0x0808082b08190819, 0x0808082b08191908,
-    0x0808082b082b0808, 0x0808082b082b2b2b, 0x0808082b19080819, 0x0808082b19081908,
-    0x0808082b1908192b, 0x0808082b19082b19, 0x0808082b19190808, 0x0808082b19191919,
-    0x0808082b2b080808, 0x0808082b2b081919, 0x0808082b2b082b2b, 0x0808082b2b191908,
-    0x0808082b2b2b082b, 0x0808190808080819, 0x0808190808081908, 0x080819080808192b,
-    0x0808190808082b19, 0x0808190808190808, 0x080819080819082b, 0x0808190808191919,
-    0x0808190808192b08, 0x08081908082b0819, 0x08081908082b1908, 0x08081908082b192b,
-    0x08081908082b2b19, 0x0808190819080808, 0x080819081908082b, 0x0808190819081919,
-    0x0808190819082b08, 0x0808190819082b2b, 0x0808190819190819, 0x0808190819191908,
-    0x080819081919192b, 0x0808190819192b19, 0x08081908192b0808, 0x08081908192b082b,
-    0x08081908192b1919, 0x080819082b080819, 0x080819082b081908, 0x080819082b08192b,
-    0x080819082b082b19, 0x080819082b190808, 0x080819082b191919, 0x080819082b192b08,
-    0x080819082b2b0819, 0x080819082b2b1908, 0x0808191908080808, 0x080819190808082b,
-    0x0808191908081919, 0x0808191908082b08, 0x0808191908082b2b, 0x0808191908190819,
-    0x0808191908191908, 0x080819190819192b, 0x0808191908192b19, 0x08081919082b0808,
-    0x08081919082b1919, 0x08081919082b2b08, 0x0808191919080819, 0x0808191919081908,
-    0x080819191908192b, 0x0808191919082b19, 0x0808191919190808, 0x080819191919082b,
-    0x0808191919191919, 0x0808191919192b08, 0x08081919192b0819, 0x08081919192b1908,
-    0x080819192b080808, 0x080819192b08082b, 0x080819192b081919, 0x080819192b082b08,
-    0x080819192b190819, 0x080819192b191908, 0x080819192b2b0808, 0x0808192b08080819,
-    0x0808192b08081908, 0x0808192b0808192b, 0x0808192b08082b19, 0x0808192b08190808,
-    0x0808192b08191919, 0x0808192b19080808, 0x0808192b19081919, 0x0808192b19082b08,
-    0x0808192b19190819, 0x0808192b19191908, 0x0808192b192b0808, 0x0808192b2b080819,
-    0x0808192b2b081908, 0x0808192b2b190808, 0x08082b0808080808, 0x08082b080808082b,
-    0x08082b0808081919, 0x08082b0808082b08, 0x08082b0808190819, 0x08082b0808191908,
-    0x08082b080819192b, 0x08082b0808192b19, 0x08082b08082b0808, 0x08082b08082b1919,
-    0x08082b08082b2b2b, 0x08082b0819080819, 0x08082b0819081908, 0x08082b081908192b,
-    0x08082b0819082b19, 0x08082b0819190808, 0x08082b081919082b, 0x08082b0819191919,
-    0x08082b0819192b08, 0x08082b08192b0819, 0x08082b08192b1908, 0x08082b082b080808,
-    0x08082b082b081919, 0x08082b082b191908, 0x08082b082b2b2b2b, 0x08082b1908080819,
-    0x08082b1908081908, 0x08082b1908190808, 0x08082b190819082b, 0x08082b1908191919,
-    0x08082b1908192b08, 0x08082b19082b0819, 0x08082b1919080808, 0x08082b1919081919,
-    0x08082b1919082b08, 0x08082b1919190819, 0x08082b1919191908, 0x08082b19192b0808,
-    0x08082b192b080819, 0x08082b192b190808, 0x08082b2b08080808, 0x08082b2b08190819,
-    0x08082b2b08191908, 0x08082b2b082b082b, 0x08082b2b082b2b08, 0x08082b2b082b2b2b,
-    0x08082b2b19190808, 0x08082b2b2b192b19, 0x0819080808080819, 0x0819080808081908,
-    0x081908080808192b, 0x0819080808082b19, 0x0819080808190808, 0x081908080819082b,
-    0x0819080808191919, 0x0819080808192b08, 0x08190808082b0819, 0x08190808082b1908,
-    0x08190808082b192b, 0x0819080819080808, 0x081908081908082b, 0x0819080819081919,
-    0x0819080819082b08, 0x0819080819190819, 0x0819080819191908, 0x081908081919192b,
-    0x0819080819192b19, 0x08190808192b0808, 0x08190808192b082b, 0x08190808192b1919,
-    0x08190808192b2b08, 0x081908082b080819, 0x081908082b081908, 0x081908082b08192b,
-    0x081908082b190808, 0x081908082b191919, 0x081908082b192b08, 0x081908082b2b0819,
-    0x081908082b2b1908, 0x0819081908080808, 0x081908190808082b, 0x0819081908081919,
-    0x0819081908082b08, 0x0819081908082b2b, 0x0819081908190819, 0x0819081908191908,
-    0x081908190819192b, 0x0819081908192b19, 0x08190819082b0808, 0x08190819082b082b,
-    0x08190819082b1919, 0x08190819082b2b08, 0x0819081919080819, 0x0819081919081908,
-    0x081908191908192b, 0x0819081919082b19, 0x0819081919190808, 0x081908191919082b,
-    0x0819081919191919, 0x0819081919192b08, 0x08190819192b0819, 0x08190819192b1908,
-    0x081908192b080808, 0x081908192b08082b, 0x081908192b081919, 0x081908192b082b08,
-    0x081908192b190819, 0x081908192b191908, 0x0819082b08080819, 0x0819082b08081908,
-    0x0819082b08082b19, 0x0819082b08190808, 0x0819082b08191919, 0x0819082b082b0819,
-    0x0819082b082b1908, 0x0819082b19080808, 0x0819082b19081919, 0x0819082b19190819,
-    0x0819082b19191908, 0x0819082b2b080819, 0x0819082b2b081908, 0x0819082b2b190808,
-    0x0819190808080808, 0x081919080808082b, 0x0819190808081919, 0x0819190808082b08,
-    0x0819190808190819, 0x0819190808191908, 0x081919080819192b, 0x0819190808192b19,
-    0x08191908082b0808, 0x08191908082b1919, 0x08191908082b2b08, 0x0819190819080819,
-    0x0819190819081908, 0x081919081908192b, 0x0819190819082b19, 0x0819190819190808,
-    0x081919081919082b, 0x0819190819191919, 0x0819190819192b08, 0x08191908192b0819,
-    0x08191908192b1908, 0x081919082b080808, 0x081919082b08082b, 0x081919082b081919,
-    0x081919082b082b08, 0x081919082b190819, 0x081919082b191908, 0x081919082b2b0808,
-    0x0819191908080819, 0x0819191908081908, 0x081919190808192b, 0x0819191908082b19,
-    0x0819191908190808, 0x081919190819082b, 0x0819191908191919, 0x0819191908192b08,
-    0x08191919082b0819, 0x08191919082b1908, 0x0819191919080808, 0x081919191908082b,
-    0x0819191919081919, 0x0819191919082b08, 0x0819191919190819, 0x0819191919191908,
-    0x08191919192b0808, 0x081919192b080819, 0x081919192b081908, 0x081919192b190808,
-    0x0819192b08080808, 0x0819192b08081919, 0x0819192b08082b08, 0x0819192b08190819,
-    0x0819192b08191908, 0x0819192b082b0808, 0x0819192b19080819, 0x0819192b19081908,
-    0x0819192b19190808, 0x0819192b2b080808, 0x0819192b2b2b2b2b, 0x08192b0808080819,
-    0x08192b0808081908, 0x08192b080808192b, 0x08192b0808082b19, 0x08192b0808190808,
-    0x08192b0808191919, 0x08192b0808192b08, 0x08192b08082b0819, 0x08192b0819080808,
-    0x08192b081908082b, 0x08192b0819081919, 0x08192b0819082b08, 0x08192b0819190819,
-    0x08192b0819191908, 0x08192b08192b0808, 0x08192b082b080819, 0x08192b082b081908,
-    0x08192b1908080808, 0x08192b190808082b, 0x08192b1908081919, 0x08192b1908082b08,
-    0x08192b1908190819, 0x08192b1908191908, 0x08192b19082b0808, 0x08192b1919080819,
-    0x08192b1919081908, 0x08192b1919190808, 0x08192b19192b2b19, 0x08192b192b2b082b,
-    0x08192b2b08081908, 0x08192b2b08190808, 0x08192b2b19080808, 0x08192b2b1919192b,
-    0x082b080808080808, 0x082b08080808082b, 0x082b080808081919, 0x082b080808082b08,
-    0x082b080808190819, 0x082b080808191908, 0x082b08080819192b, 0x082b080808192b19,
-    0x082b0808082b0808, 0x082b0808082b1919, 0x082b0808082b2b2b, 0x082b080819080819,
-    0x082b080819081908, 0x082b080819190808, 0x082b08081919082b, 0x082b080819191919,
-    0x082b0808192b1908, 0x082b08082b080808, 0x082b08082b082b2b, 0x082b08082b191908,
-    0x082b08082b2b2b2b, 0x082b081908080819, 0x082b081908081908, 0x082b081908190808,
-    0x082b08190819082b, 0x082b081908191919, 0x082b0819082b0819, 0x082b081919080808,
-    0x082b08191908082b, 0x082b081919081919, 0x082b081919190819, 0x082b081919191908,
-    0x082b0819192b0808, 0x082b08192b080819, 0x082b08192b081908, 0x082b08192b190808,
-    0x082b082b08080808, 0x082b082b08082b2b, 0x082b082b082b082b, 0x082b082b082b2b08,
-    0x082b082b082b2b2b, 0x082b082b19081908, 0x082b082b19190808, 0x082b082b2b082b08,
-    0x082b082b2b082b2b, 0x082b082b2b2b2b08, 0x082b190808080819, 0x082b190808081908,
-    0x082b19080808192b, 0x082b190808082b19, 0x082b190808190808, 0x082b190808191919,
-    0x082b190808192b08, 0x082b1908082b0819, 0x082b1908082b1908, 0x082b190819080808,
-    0x082b19081908082b, 0x082b190819081919, 0x082b190819082b08, 0x082b190819190819,
-    0x082b190819191908, 0x082b1908192b0808, 0x082b19082b080819, 0x082b19082b081908,
-    0x082b19082b190808, 0x082b191908080808, 0x082b191908081919, 0x082b191908082b08,
-    0x082b191908190819, 0x082b191908191908, 0x082b1919082b0808, 0x082b191919080819,
-    0x082b191919081908, 0x082b191919190808, 0x082b1919192b192b, 0x082b19192b080808,
-    0x082b192b08080819, 0x082b192b08081908, 0x082b192b08190808, 0x082b192b19080808,
-    0x082b192b19192b19, 0x082b2b0808080808, 0x082b2b0808081919, 0x082b2b0808190819,
-    0x082b2b0808191908, 0x082b2b0819080819, 0x082b2b0819081908, 0x082b2b0819190808,
-    0x082b2b082b082b2b, 0x082b2b082b2b2b2b, 0x082b2b1908080819, 0x082b2b1908081908,
-    0x082b2b1908190808, 0x082b2b192b191919, 0x082b2b2b08082b2b, 0x082b2b2b082b082b,
-    0x082b2b2b192b1908, 0x082b2b2b2b082b08, 0x082b2b2b2b082b2b, 0x1908080808080819,
-    0x1908080808081908, 0x190808080808192b, 0x1908080808082b19, 0x1908080808190808,
-    0x190808080819082b, 0x1908080808191919, 0x1908080808192b08, 0x1908080808192b2b,
-    0x19080808082b0819, 0x19080808082b1908, 0x19080808082b192b, 0x1908080819080808,
-    0x190808081908082b, 0x1908080819081919, 0x1908080819082b08, 0x1908080819082b2b,
-    0x1908080819190819, 0x1908080819191908, 0x190808081919192b, 0x1908080819192b19,
-    0x19080808192b0808, 0x19080808192b082b, 0x19080808192b1919, 0x190808082b080819,
-    0x190808082b081908, 0x190808082b190808, 0x190808082b191919, 0x190808082b192b08,
-    0x190808082b2b0819, 0x190808082b2b1908, 0x1908081908080808, 0x190808190808082b,
-    0x1908081908081919, 0x1908081908082b08, 0x1908081908190819, 0x1908081908191908,
-    0x190808190819192b, 0x1908081908192b19, 0x19080819082b0808, 0x19080819082b082b,
-    0x19080819082b1919, 0x1908081919080819, 0x1908081919081908, 0x190808191908192b,
-    0x1908081919082b19, 0x1908081919190808, 0x190808191919082b, 0x1908081919191919,
-    0x1908081919192b08, 0x19080819192b0819, 0x19080819192b1908, 0x190808192b080808,
-    0x190808192b08082b, 0x190808192b081919, 0x190808192b082b08, 0x190808192b190819,
-    0x190808192b191908, 0x190808192b2b0808, 0x1908082b08080819, 0x1908082b08081908,
-    0x1908082b08190808, 0x1908082b0819082b, 0x1908082b08191919, 0x1908082b08192b08,
-    0x1908082b082b1908, 0x1908082b19080808, 0x1908082b19081919, 0x1908082b19082b08,
-    0x1908082b19190819, 0x1908082b19191908, 0x1908082b192b0808, 0x1908082b2b080819,
-    0x1908082b2b081908, 0x1908190808080808, 0x190819080808082b, 0x1908190808081919,
-    0x1908190808082b08, 0x1908190808082b2b, 0x1908190808190819, 0x1908190808191908,
-    0x190819080819192b, 0x1908190808192b19, 0x19081908082b0808, 0x19081908082b082b,
-    0x19081908082b1919, 0x19081908082b2b08, 0x1908190819080819, 0x1908190819081908,
-    0x190819081908192b, 0x1908190819082b19, 0x1908190819190808, 0x190819081919082b,
-    0x1908190819191919, 0x1908190819192b08, 0x19081908192b0819, 0x19081908192b1908,
-    0x190819082b080808, 0x190819082b08082b, 0x190819082b081919, 0x190819082b082b08,
-    0x190819082b190819, 0x190819082b191908, 0x190819082b2b0808, 0x1908191908080819,
-    0x1908191908081908, 0x190819190808192b, 0x1908191908082b19, 0x1908191908190808,
-    0x190819190819082b, 0x1908191908191919, 0x1908191908192b08, 0x19081919082b0819,
-    0x19081919082b1908, 0x1908191919080808, 0x190819191908082b, 0x1908191919081919,
-    0x1908191919082b08, 0x1908191919190819, 0x1908191919191908, 0x19081919192b0808,
-    0x19081919192b2b2b, 0x190819192b080819, 0x190819192b081908, 0x190819192b190808,
-    0x1908192b08080808, 0x1908192b0808082b, 0x1908192b08081919, 0x1908192b08082b08,
-    0x1908192b08190819, 0x1908192b08191908, 0x1908192b082b0808, 0x1908192b19080819,
-    0x1908192b19081908, 0x1908192b19190808, 0x1908192b2b080808, 0x1908192b2b2b1919,
-    0x19082b0808080819, 0x19082b0808081908, 0x19082b0808082b19, 0x19082b0808190808,
-    0x19082b080819082b, 0x19082b0808191919, 0x19082b0808192b08, 0x19082b08082b0819,
-    0x19082b08082b1908, 0x19082b0819080808, 0x19082b081908082b, 0x19082b0819081919,
-    0x19082b0819082b08, 0x19082b0819190819, 0x19082b0819191908, 0x19082b08192b0808,
-    0x19082b082b081908, 0x19082b082b190808, 0x19082b1908080808, 0x19082b190808082b,
-    0x19082b1908081919, 0x19082b1908082b08, 0x19082b1908190819, 0x19082b1908191908,
-    0x19082b19082b0808, 0x19082b1919080819, 0x19082b1919081908, 0x19082b1919190808,
-    0x19082b192b080808, 0x19082b192b19192b, 0x19082b2b08080819, 0x19082b2b08081908,
-    0x19082b2b08190808, 0x19082b2b19080808, 0x1919080808080808, 0x191908080808082b,
-    0x1919080808081919, 0x1919080808082b08, 0x1919080808190819, 0x1919080808191908,
-    0x191908080819192b, 0x1919080808192b19, 0x19190808082b0808, 0x19190808082b082b,
-    0x19190808082b1919, 0x19190808082b2b08, 0x1919080819080819, 0x1919080819081908,
-    0x191908081908192b, 0x1919080819082b19, 0x1919080819190808, 0x191908081919082b,
-    0x1919080819191919, 0x1919080819192b08, 0x19190808192b0819, 0x19190808192b1908,
-    0x191908082b080808, 0x191908082b08082b, 0x191908082b081919, 0x191908082b082b08,
-    0x191908082b190819, 0x191908082b191908, 0x1919081908080819, 0x1919081908081908,
-    0x191908190808192b, 0x1919081908082b19, 0x1919081908190808, 0x191908190819082b,
-    0x1919081908191919, 0x1919081908192b08, 0x19190819082b0819, 0x19190819082b1908,
-    0x1919081919080808, 0x191908191908082b, 0x1919081919081919, 0x1919081919082b08,
-    0x1919081919190819, 0x1919081919191908, 0x19190819192b0808, 0x191908192b080819,
-    0x191908192b081908, 0x191908192b190808, 0x1919082b08080808, 0x1919082b08081919,
-    0x1919082b08082b08, 0x1919082b08190819, 0x1919082b08191908, 0x1919082b082b0808,
-    0x1919082b19080819, 0x1919082b19081908, 0x1919082b19190808, 0x1919082b192b2b19,
-    0x1919082b2b080808, 0x1919190808080819, 0x1919190808081908, 0x191919080808192b,
-    0x1919190808082b19, 0x1919190808190808, 0x191919080819082b, 0x1919190808191919,
-    0x1919190808192b08, 0x19191908082b0819, 0x19191908082b1908, 0x1919190819080808,
-    0x191919081908082b, 0x1919190819081919, 0x1919190819082b08, 0x1919190819190819,
-    0x1919190819191908, 0x19191908192b0808, 0x191919082b080819, 0x191919082b081908,
-    0x191919082b190808, 0x1919191908080808, 0x191919190808082b, 0x1919191908081919,
-    0x1919191908082b08, 0x1919191908190819, 0x1919191908191908, 0x19191919082b0808,
-    0x1919191919080819, 0x1919191919081908, 0x1919191919190808, 0x191919192b080808,
-    0x1919192b08080819, 0x1919192b08081908, 0x1919192b08190808, 0x1919192b082b192b,
-    0x1919192b19080808, 0x19192b0808080808, 0x19192b080808082b, 0x19192b0808081919,
-    0x19192b0808082b08, 0x19192b0808190819, 0x19192b0808191908, 0x19192b08082b0808,
-    0x19192b0819080819, 0x19192b0819081908, 0x19192b0819190808, 0x19192b0819192b2b,
-    0x19192b082b080808, 0x19192b1908080819, 0x19192b1908081908, 0x19192b1908190808,
-    0x19192b1919080808, 0x19192b2b08080808, 0x19192b2b08192b19, 0x19192b2b2b081919,
-    0x19192b2b2b2b2b08, 0x192b080808080819, 0x192b080808081908, 0x192b08080808192b,
-    0x192b080808190808, 0x192b08080819082b, 0x192b080808191919, 0x192b080808192b08,
-    0x192b0808082b0819, 0x192b0808082b1908, 0x192b080819080808, 0x192b080819081919,
-    0x192b080819082b08, 0x192b080819190819, 0x192b080819191908, 0x192b0808192b0808,
-    0x192b08082b081908, 0x192b08082b190808, 0x192b081908080808, 0x192b08190808082b,
-    0x192b081908081919, 0x192b081908082b08, 0x192b081908190819, 0x192b081908191908,
-    0x192b0819082b0808, 0x192b081919080819, 0x192b081919081908, 0x192b081919190808,
-    0x192b08192b080808, 0x192b08192b192b19, 0x192b082b08081908, 0x192b082b08190808,
-    0x192b082b19080808, 0x192b082b1919192b, 0x192b082b2b2b0819, 0x192b190808080808,
-    0x192b190808081919, 0x192b190808082b08, 0x192b190808190819, 0x192b190808191908,
-    0x192b1908082b0808, 0x192b190819080819, 0x192b190819081908, 0x192b190819190808,
-    0x192b19082b080808, 0x192b191908080819, 0x192b191908081908, 0x192b191908190808,
-    0x192b191919080808, 0x192b191919082b2b, 0x192b1919192b2b08, 0x192b19192b19082b,
-    0x192b192b08080808, 0x192b192b2b191908, 0x192b2b0808080819, 0x192b2b0808081908,
-    0x192b2b0808190808, 0x192b2b08192b1919, 0x192b2b082b192b08, 0x192b2b1908080808,
-    0x192b2b19082b2b2b, 0x192b2b2b1908082b, 0x192b2b2b2b2b0819, 0x2b08080808080808,
-    0x2b0808080808082b, 0x2b08080808081919, 0x2b08080808082b08, 0x2b08080808190819,
-    0x2b08080808191908, 0x2b08080808192b19, 0x2b080808082b0808, 0x2b080808082b1919,
-    0x2b08080819080819, 0x2b08080819081908, 0x2b08080819190808, 0x2b0808081919082b,
-    0x2b08080819191919, 0x2b08080819192b08, 0x2b080808192b0819, 0x2b0808082b080808,
-    0x2b0808082b081919, 0x2b0808082b190819, 0x2b0808082b191908, 0x2b08081908080819,
-    0x2b08081908081908, 0x2b08081908082b19, 0x2b08081908190808, 0x2b0808190819082b,
-    0x2b08081908191919, 0x2b08081908192b08, 0x2b080819082b0819, 0x2b080819082b1908,
-    0x2b08081919080808, 0x2b0808191908082b, 0x2b08081919081919, 0x2b08081919082b08,
-    0x2b08081919190819, 0x2b08081919191908, 0x2b0808192b080819, 0x2b0808192b081908,
-    0x2b0808192b190808, 0x2b0808192b2b2b19, 0x2b08082b08080808, 0x2b08082b08081919,
-    0x2b08082b08082b2b, 0x2b08082b08190819, 0x2b08082b08191908, 0x2b08082b19080819,
-    0x2b08082b19081908, 0x2b08082b19190808, 0x2b08190808080819, 0x2b08190808081908,
-    0x2b0819080808192b, 0x2b08190808082b19, 0x2b08190808190808, 0x2b0819080819082b,
-    0x2b08190808191919, 0x2b08190808192b08, 0x2b081908082b0819, 0x2b08190819080808,
-    0x2b0819081908082b, 0x2b08190819081919, 0x2b08190819082b08, 0x2b08190819190819,
-    0x2b08190819191908, 0x2b081908192b0808, 0x2b0819082b080819, 0x2b0819082b081908,
-    0x2b0819082b190808, 0x2b08191908080808, 0x2b0819190808082b, 0x2b08191908081919,
-    0x2b08191908082b08, 0x2b08191908190819, 0x2b08191908191908, 0x2b081919082b0808,
-    0x2b08191919080819, 0x2b08191919081908, 0x2b08191919190808, 0x2b0819192b080808,
-    0x2b0819192b082b2b, 0x2b08192b08080819, 0x2b08192b08081908, 0x2b08192b08190808,
-    0x2b08192b082b2b19, 0x2b08192b19080808, 0x2b082b0808080808, 0x2b082b0808081919,
-    0x2b082b0808190819, 0x2b082b0808191908, 0x2b082b0819080819, 0x2b082b0819081908,
-    0x2b082b0819190808, 0x2b082b082b2b082b, 0x2b082b1908080819, 0x2b082b1908081908,
-    0x2b082b1919080808, 0x2b082b19192b1919, 0x2b082b2b082b082b, 0x2b082b2b19192b08,
-    0x2b082b2b19192b2b, 0x2b082b2b2b08082b, 0x2b082b2b2b2b082b, 0x2b19080808080819,
-    0x2b19080808081908, 0x2b19080808082b19, 0x2b19080808190808, 0x2b1908080819082b,
-    0x2b19080808191919, 0x2b19080808192b08, 0x2b190808082b1908, 0x2b19080819080808,
-    0x2b1908081908082b, 0x2b19080819081919, 0x2b19080819082b08, 0x2b19080819190819,
-    0x2b19080819191908, 0x2b190808192b0808, 0x2b1908082b080819, 0x2b1908082b081908,
-    0x2b1908082b190808, 0x2b19081908080808, 0x2b19081908081919, 0x2b19081908190819,
-    0x2b19081908191908, 0x2b19081919080819, 0x2b19081919081908, 0x2b19081919190808,
-    0x2b19081919192b2b, 0x2b19082b08080819, 0x2b19082b08081908, 0x2b19082b08190808,
-    0x2b19082b19080808, 0x2b19082b2b2b192b, 0x2b19190808080808, 0x2b1919080808082b,
-    0x2b19190808081919, 0x2b19190808082b08, 0x2b19190808190819, 0x2b19190808191908,
-    0x2b191908082b0808, 0x2b19190819080819, 0x2b19190819081908, 0x2b19190819190808,
-    0x2b1919082b080808, 0x2b1919082b19192b, 0x2b19191908080819, 0x2b19191908081908,
-    0x2b19191908190808, 0x2b19191919080808, 0x2b1919192b192b08, 0x2b1919192b2b0819,
-    0x2b19192b08080808, 0x2b19192b1908192b, 0x2b19192b192b1908, 0x2b192b0808080819,
-    0x2b192b0808081908, 0x2b192b0808190808, 0x2b192b08082b192b, 0x2b192b0819080808,
-    0x2b192b082b2b2b19, 0x2b192b1908080808, 0x2b192b1919082b19, 0x2b192b191919082b,
-    0x2b192b2b2b190808, 0x2b2b080808080808, 0x2b2b080808081919, 0x2b2b080808082b2b,
-    0x2b2b080808191908, 0x2b2b0808082b082b, 0x2b2b0808082b2b2b, 0x2b2b080819080819,
-    0x2b2b080819081908, 0x2b2b080819190808, 0x2b2b08082b2b082b, 0x2b2b08082b2b2b2b,
-    0x2b2b081919080808, 0x2b2b0819192b1919, 0x2b2b082b0808082b, 0x2b2b082b08082b2b,
-    0x2b2b082b082b082b, 0x2b2b082b082b2b08, 0x2b2b082b082b2b2b, 0x2b2b082b2b08082b,
-    0x2b2b082b2b082b08, 0x2b2b082b2b082b2b, 0x2b2b082b2b2b2b08, 0x2b2b190808080819,
-    0x2b2b190808081908, 0x2b2b190808190808, 0x2b2b190819080808, 0x2b2b19082b082b19,
-    0x2b2b19082b2b1908, 0x2b2b191908080808, 0x2b2b191908192b19, 0x2b2b192b19190819,
-    0x2b2b2b0808082b2b, 0x2b2b2b08082b2b08, 0x2b2b2b082b2b082b, 0x2b2b2b1919191908,
-    0x2b2b2b192b08192b, 0x2b2b2b2b08082b08, 0x2b2b2b2b08082b2b, 0x2b2b2b2b082b0808,
-    0x2b2b2b2b082b082b, 0x2b2b2b2b082b2b08, 0x2b2b2b2b2b082b08, 0x2b2b2b2b2b2b2b2b,
-};
-
-static const uint32_t iq3xxs_grid[256] = {
-    0x04040404, 0x04040414, 0x04040424, 0x04040c0c, 0x04040c1c, 0x04040c3e, 0x04041404, 0x04041414,
-    0x04041c0c, 0x04042414, 0x04043e1c, 0x04043e2c, 0x040c040c, 0x040c041c, 0x040c0c04, 0x040c0c14,
-    0x040c140c, 0x040c142c, 0x040c1c04, 0x040c1c14, 0x040c240c, 0x040c2c24, 0x040c3e04, 0x04140404,
-    0x04140414, 0x04140424, 0x04140c0c, 0x04141404, 0x04141414, 0x04141c0c, 0x04141c1c, 0x04141c3e,
-    0x04142c0c, 0x04142c3e, 0x04143e2c, 0x041c040c, 0x041c043e, 0x041c0c04, 0x041c0c14, 0x041c142c,
-    0x041c3e04, 0x04240c1c, 0x04241c3e, 0x04242424, 0x04242c3e, 0x04243e1c, 0x04243e2c, 0x042c040c,
-    0x042c043e, 0x042c1c14, 0x042c2c14, 0x04341c2c, 0x04343424, 0x043e0c04, 0x043e0c24, 0x043e0c34,
-    0x043e241c, 0x043e340c, 0x0c04040c, 0x0c04041c, 0x0c040c04, 0x0c040c14, 0x0c04140c, 0x0c04141c,
-    0x0c041c04, 0x0c041c14, 0x0c041c24, 0x0c04243e, 0x0c042c04, 0x0c0c0404, 0x0c0c0414, 0x0c0c0c0c,
-    0x0c0c1404, 0x0c0c1414, 0x0c14040c, 0x0c14041c, 0x0c140c04, 0x0c140c14, 0x0c14140c, 0x0c141c04,
-    0x0c143e14, 0x0c1c0404, 0x0c1c0414, 0x0c1c1404, 0x0c1c1c0c, 0x0c1c2434, 0x0c1c3434, 0x0c24040c,
-    0x0c24042c, 0x0c242c04, 0x0c2c1404, 0x0c2c1424, 0x0c2c2434, 0x0c2c3e0c, 0x0c34042c, 0x0c3e1414,
-    0x0c3e2404, 0x14040404, 0x14040414, 0x14040c0c, 0x14040c1c, 0x14041404, 0x14041414, 0x14041434,
-    0x14041c0c, 0x14042414, 0x140c040c, 0x140c041c, 0x140c042c, 0x140c0c04, 0x140c0c14, 0x140c140c,
-    0x140c1c04, 0x140c341c, 0x140c343e, 0x140c3e04, 0x14140404, 0x14140414, 0x14140c0c, 0x14140c3e,
-    0x14141404, 0x14141414, 0x14141c3e, 0x14142404, 0x14142c2c, 0x141c040c, 0x141c0c04, 0x141c0c24,
-    0x141c3e04, 0x141c3e24, 0x14241c2c, 0x14242c1c, 0x142c041c, 0x142c143e, 0x142c240c, 0x142c3e24,
-    0x143e040c, 0x143e041c, 0x143e0c34, 0x143e242c, 0x1c04040c, 0x1c040c04, 0x1c040c14, 0x1c04140c,
-    0x1c04141c, 0x1c042c04, 0x1c04342c, 0x1c043e14, 0x1c0c0404, 0x1c0c0414, 0x1c0c1404, 0x1c0c1c0c,
-    0x1c0c2424, 0x1c0c2434, 0x1c14040c, 0x1c14041c, 0x1c140c04, 0x1c14142c, 0x1c142c14, 0x1c143e14,
-    0x1c1c0c0c, 0x1c1c1c1c, 0x1c241c04, 0x1c24243e, 0x1c243e14, 0x1c2c0404, 0x1c2c0434, 0x1c2c1414,
-    0x1c2c2c2c, 0x1c340c24, 0x1c341c34, 0x1c34341c, 0x1c3e1c1c, 0x1c3e3404, 0x24040424, 0x24040c3e,
-    0x24041c2c, 0x24041c3e, 0x24042c1c, 0x24042c3e, 0x240c3e24, 0x24141404, 0x24141c3e, 0x24142404,
-    0x24143404, 0x24143434, 0x241c043e, 0x241c242c, 0x24240424, 0x24242c0c, 0x24243424, 0x242c142c,
-    0x242c241c, 0x242c3e04, 0x243e042c, 0x243e0c04, 0x243e0c14, 0x243e1c04, 0x2c040c14, 0x2c04240c,
-    0x2c043e04, 0x2c0c0404, 0x2c0c0434, 0x2c0c1434, 0x2c0c2c2c, 0x2c140c24, 0x2c141c14, 0x2c143e14,
-    0x2c1c0414, 0x2c1c2c1c, 0x2c240c04, 0x2c24141c, 0x2c24143e, 0x2c243e14, 0x2c2c0414, 0x2c2c1c0c,
-    0x2c342c04, 0x2c3e1424, 0x2c3e2414, 0x34041424, 0x34042424, 0x34042434, 0x34043424, 0x340c140c,
-    0x340c340c, 0x34140c3e, 0x34143424, 0x341c1c04, 0x341c1c34, 0x34242424, 0x342c042c, 0x342c2c14,
-    0x34341c1c, 0x343e041c, 0x343e140c, 0x3e04041c, 0x3e04042c, 0x3e04043e, 0x3e040c04, 0x3e041c14,
-    0x3e042c14, 0x3e0c1434, 0x3e0c2404, 0x3e140c14, 0x3e14242c, 0x3e142c14, 0x3e1c0404, 0x3e1c0c2c,
-    0x3e1c1c1c, 0x3e1c3404, 0x3e24140c, 0x3e24240c, 0x3e2c0404, 0x3e2c0414, 0x3e2c1424, 0x3e341c04,
-};
-
-static const uint32_t iq3xs_grid[512] = {
-    0x04040404, 0x0404040c, 0x04040414, 0x0404042c, 0x0404043e, 0x04040c04, 0x04040c0c, 0x04040c14,
-    0x04040c24, 0x04040c34, 0x04041404, 0x0404140c, 0x0404142c, 0x04041c1c, 0x04042404, 0x04042414,
-    0x0404242c, 0x0404243e, 0x04042c0c, 0x04042c1c, 0x04043404, 0x04043414, 0x04043e0c, 0x04043e24,
-    0x04043e3e, 0x040c0404, 0x040c040c, 0x040c0414, 0x040c0424, 0x040c0c04, 0x040c0c0c, 0x040c0c2c,
-    0x040c1404, 0x040c141c, 0x040c143e, 0x040c1c0c, 0x040c1c2c, 0x040c2424, 0x040c340c, 0x040c342c,
-    0x040c3e14, 0x04140404, 0x0414040c, 0x0414042c, 0x0414043e, 0x04140c04, 0x04140c1c, 0x04140c34,
-    0x0414140c, 0x0414142c, 0x04141c04, 0x04141c24, 0x04142414, 0x0414242c, 0x0414243e, 0x04142c0c,
-    0x04142c1c, 0x04143e04, 0x04143e1c, 0x041c041c, 0x041c0c0c, 0x041c0c2c, 0x041c1404, 0x041c1414,
-    0x041c1c0c, 0x041c1c1c, 0x041c1c34, 0x041c2424, 0x041c2c04, 0x041c2c14, 0x041c343e, 0x041c3e0c,
-    0x041c3e2c, 0x04240404, 0x04240c1c, 0x04240c3e, 0x0424140c, 0x04241424, 0x04241c14, 0x04242404,
-    0x0424241c, 0x04242c0c, 0x04243e04, 0x042c0414, 0x042c0424, 0x042c1404, 0x042c1414, 0x042c1434,
-    0x042c1c1c, 0x042c240c, 0x042c242c, 0x042c243e, 0x042c3434, 0x042c3e1c, 0x04340434, 0x04340c0c,
-    0x04340c1c, 0x04341c0c, 0x04342c14, 0x04343e0c, 0x043e0404, 0x043e0414, 0x043e0424, 0x043e1404,
-    0x043e1414, 0x043e1434, 0x043e1c1c, 0x043e2c04, 0x043e2c24, 0x0c040404, 0x0c04040c, 0x0c040414,
-    0x0c040424, 0x0c040c04, 0x0c040c0c, 0x0c040c1c, 0x0c040c2c, 0x0c040c3e, 0x0c041404, 0x0c041414,
-    0x0c041c0c, 0x0c041c24, 0x0c041c34, 0x0c042c24, 0x0c042c34, 0x0c04340c, 0x0c043e14, 0x0c0c0404,
-    0x0c0c040c, 0x0c0c041c, 0x0c0c0434, 0x0c0c0c04, 0x0c0c0c24, 0x0c0c140c, 0x0c0c1c04, 0x0c0c1c1c,
-    0x0c0c240c, 0x0c0c2c04, 0x0c0c2c14, 0x0c0c3e04, 0x0c0c3e34, 0x0c140404, 0x0c140c14, 0x0c140c2c,
-    0x0c140c3e, 0x0c141404, 0x0c141424, 0x0c141c14, 0x0c142404, 0x0c14241c, 0x0c142c2c, 0x0c143404,
-    0x0c143e14, 0x0c1c040c, 0x0c1c0424, 0x0c1c043e, 0x0c1c0c04, 0x0c1c0c1c, 0x0c1c140c, 0x0c1c143e,
-    0x0c1c1c04, 0x0c1c1c24, 0x0c1c240c, 0x0c1c3414, 0x0c1c3e04, 0x0c24041c, 0x0c24042c, 0x0c240c14,
-    0x0c240c24, 0x0c241c0c, 0x0c241c1c, 0x0c242414, 0x0c242434, 0x0c242c04, 0x0c242c24, 0x0c2c040c,
-    0x0c2c0c04, 0x0c2c0c1c, 0x0c2c140c, 0x0c2c1c04, 0x0c2c1c14, 0x0c2c2c0c, 0x0c341404, 0x0c341424,
-    0x0c34143e, 0x0c342424, 0x0c342434, 0x0c3e040c, 0x0c3e041c, 0x0c3e0c04, 0x0c3e0c14, 0x0c3e140c,
-    0x0c3e1c2c, 0x0c3e240c, 0x0c3e3414, 0x0c3e3e04, 0x14040404, 0x1404040c, 0x1404041c, 0x1404042c,
-    0x1404043e, 0x14040c04, 0x14040c14, 0x14040c24, 0x14040c34, 0x1404140c, 0x1404141c, 0x1404143e,
-    0x14041c04, 0x14041c14, 0x1404240c, 0x1404241c, 0x1404242c, 0x14042c04, 0x14042c14, 0x1404343e,
-    0x14043e04, 0x14043e1c, 0x14043e2c, 0x140c0404, 0x140c0414, 0x140c0c04, 0x140c0c1c, 0x140c0c3e,
-    0x140c1414, 0x140c142c, 0x140c1c0c, 0x140c1c24, 0x140c2414, 0x140c2c0c, 0x1414040c, 0x14140424,
-    0x1414043e, 0x1414140c, 0x1414141c, 0x14141c04, 0x14141c3e, 0x1414240c, 0x14142c1c, 0x14142c3e,
-    0x14143e0c, 0x14143e24, 0x141c0404, 0x141c0414, 0x141c042c, 0x141c0c0c, 0x141c1414, 0x141c1424,
-    0x141c1c0c, 0x141c1c1c, 0x141c2414, 0x141c2c04, 0x141c3434, 0x1424040c, 0x1424043e, 0x14241404,
-    0x1424141c, 0x14241c14, 0x14241c2c, 0x1424240c, 0x14243e14, 0x14243e2c, 0x142c0424, 0x142c0c0c,
-    0x142c1414, 0x142c1c3e, 0x142c2404, 0x142c2c1c, 0x142c3e04, 0x14340404, 0x14340414, 0x1434043e,
-    0x1434140c, 0x14342c2c, 0x1434340c, 0x143e042c, 0x143e0c0c, 0x143e1434, 0x143e1c04, 0x143e241c,
-    0x143e2c04, 0x1c040414, 0x1c040c0c, 0x1c040c1c, 0x1c040c2c, 0x1c040c3e, 0x1c041414, 0x1c041c0c,
-    0x1c041c1c, 0x1c041c2c, 0x1c042414, 0x1c042424, 0x1c04243e, 0x1c042c0c, 0x1c04341c, 0x1c043e0c,
-    0x1c0c040c, 0x1c0c041c, 0x1c0c042c, 0x1c0c0c24, 0x1c0c140c, 0x1c0c141c, 0x1c0c2404, 0x1c0c3404,
-    0x1c0c3e14, 0x1c0c3e34, 0x1c140404, 0x1c140c14, 0x1c141404, 0x1c141c14, 0x1c141c24, 0x1c142c04,
-    0x1c1c040c, 0x1c1c0c04, 0x1c1c0c24, 0x1c1c140c, 0x1c1c141c, 0x1c1c143e, 0x1c1c1c04, 0x1c1c240c,
-    0x1c1c241c, 0x1c1c243e, 0x1c1c2c2c, 0x1c1c3e1c, 0x1c24041c, 0x1c240c0c, 0x1c240c34, 0x1c241414,
-    0x1c241c0c, 0x1c242c14, 0x1c243404, 0x1c243424, 0x1c2c040c, 0x1c2c0c04, 0x1c2c0c14, 0x1c2c142c,
-    0x1c2c1c14, 0x1c2c2424, 0x1c2c2c34, 0x1c2c3e1c, 0x1c340c34, 0x1c34240c, 0x1c3e040c, 0x1c3e041c,
-    0x1c3e1404, 0x1c3e1414, 0x1c3e1c2c, 0x24040404, 0x24040424, 0x24040c14, 0x24041404, 0x24041424,
-    0x2404143e, 0x24041c14, 0x2404240c, 0x24042c04, 0x24043e04, 0x240c0414, 0x240c043e, 0x240c0c0c,
-    0x240c0c1c, 0x240c1414, 0x240c1c04, 0x240c1c2c, 0x240c241c, 0x240c2c0c, 0x240c2c2c, 0x2414040c,
-    0x2414041c, 0x24140c04, 0x24140c2c, 0x2414140c, 0x24141c1c, 0x24142404, 0x24142c3e, 0x24143414,
-    0x24143e04, 0x241c0424, 0x241c0c0c, 0x241c0c1c, 0x241c1404, 0x241c1414, 0x241c1c0c, 0x241c1c2c,
-    0x24240404, 0x24240414, 0x24241424, 0x24241c3e, 0x24242404, 0x24243e0c, 0x242c042c, 0x242c043e,
-    0x242c140c, 0x242c3414, 0x24340c1c, 0x24341c24, 0x24343404, 0x243e0c04, 0x243e0c2c, 0x243e1c04,
-    0x243e241c, 0x243e2c0c, 0x2c040414, 0x2c040c04, 0x2c040c24, 0x2c041414, 0x2c042404, 0x2c042424,
-    0x2c04243e, 0x2c042c14, 0x2c043434, 0x2c043e24, 0x2c0c040c, 0x2c0c041c, 0x2c0c042c, 0x2c0c0c14,
-    0x2c0c140c, 0x2c0c1c14, 0x2c0c3e14, 0x2c140404, 0x2c140c0c, 0x2c14141c, 0x2c141c04, 0x2c141c34,
-    0x2c142c1c, 0x2c1c0414, 0x2c1c043e, 0x2c1c0c04, 0x2c1c143e, 0x2c1c2424, 0x2c1c2c0c, 0x2c1c342c,
-    0x2c1c3e1c, 0x2c24040c, 0x2c240424, 0x2c241404, 0x2c241c14, 0x2c242434, 0x2c2c0c14, 0x2c2c1434,
-    0x2c2c2c0c, 0x2c2c2c1c, 0x2c342414, 0x2c3e0414, 0x2c3e0424, 0x2c3e1414, 0x34040c0c, 0x34040c1c,
-    0x34040c2c, 0x34041c0c, 0x34041c1c, 0x34043404, 0x340c0404, 0x340c1404, 0x340c143e, 0x340c3424,
-    0x34140c14, 0x34141c24, 0x34142414, 0x34142c2c, 0x34143414, 0x34143e04, 0x341c0404, 0x341c0c24,
-    0x341c140c, 0x341c2404, 0x3424142c, 0x3424241c, 0x34243414, 0x342c0404, 0x342c041c, 0x342c1c24,
-    0x342c3404, 0x3434042c, 0x34342404, 0x343e0c0c, 0x343e0c1c, 0x3e040404, 0x3e040424, 0x3e04043e,
-    0x3e041404, 0x3e041414, 0x3e041c34, 0x3e042404, 0x3e042c24, 0x3e043414, 0x3e0c0414, 0x3e0c0c0c,
-    0x3e0c1424, 0x3e0c241c, 0x3e0c242c, 0x3e14040c, 0x3e140424, 0x3e140c04, 0x3e140c34, 0x3e14140c,
-    0x3e141c04, 0x3e142c0c, 0x3e1c0414, 0x3e1c1c14, 0x3e1c1c2c, 0x3e1c2c1c, 0x3e24040c, 0x3e24042c,
-    0x3e240c1c, 0x3e241404, 0x3e242c04, 0x3e2c1414, 0x3e2c2414, 0x3e340414, 0x3e341c0c, 0x3e3e0404,
-};
-
-#define NGRID_IQ2XXS 512
-static const  uint64_t iq1s_grid[NGRID_IQ2XXS] = {
-    0xffffffffffff0101, 0xffffffffff01ff00, 0xffffffffff010100, 0xffffffff00000000,
-    0xffffffff01ff00ff, 0xffffffff01ff0001, 0xffffffff0101ffff, 0xffffffff0101ff01,
-    0xffffff00ff000000, 0xffffff000000ff00, 0xffffff00000000ff, 0xffffff0000000100,
-    0xffffff0000010000, 0xffffff0001000000, 0xffffff01ffff00ff, 0xffffff01ff01ff00,
-    0xffffff01ff010100, 0xffffff0100000001, 0xffffff0101ffff00, 0xffffff0101ff0101,
-    0xffffff0101010100, 0xffff00ffff00ff01, 0xffff00ffff0000ff, 0xffff00ff00ff0100,
-    0xffff00ff0100ff00, 0xffff00ff010001ff, 0xffff0000ff0101ff, 0xffff000000ffff00,
-    0xffff000000000000, 0xffff00000001ff01, 0xffff000001000101, 0xffff0000010100ff,
-    0xffff0001ffff0100, 0xffff00010000ff00, 0xffff000100010101, 0xffff000101000000,
-    0xffff01ffffff0000, 0xffff01ffff01ffff, 0xffff01ffff010100, 0xffff01ff00000000,
-    0xffff01ff01ffffff, 0xffff01ff01ff0001, 0xffff01ff0101ffff, 0xffff01ff01010001,
-    0xffff0100ffffff01, 0xffff01000000ffff, 0xffff010000000100, 0xffff010001ff01ff,
-    0xffff010001000000, 0xffff0101ff000000, 0xffff0101000101ff, 0xffff010101ffff01,
-    0xffff01010101ff00, 0xff00ffffff000000, 0xff00ffff00ffff00, 0xff00ffff00000001,
-    0xff00ffff000001ff, 0xff00ffff01010000, 0xff00ff00ffff0000, 0xff00ff00ff00ff00,
-    0xff00ff00ff0000ff, 0xff00ff00ff000100, 0xff00ff00ff010001, 0xff00ff0000ff0001,
-    0xff00ff000000ffff, 0xff00ff0000000000, 0xff00ff000001ff00, 0xff00ff0000010100,
-    0xff00ff0001ff0000, 0xff00ff000100ff00, 0xff00ff0001000100, 0xff00ff01ff000000,
-    0xff00ff0100ff0000, 0xff00ff01000001ff, 0xff00ff0101010001, 0xff0000ff00000000,
-    0xff0000ff0001ff00, 0xff0000ff00010100, 0xff000000ffff0101, 0xff000000ff000000,
-    0xff000000ff01ff00, 0xff00000000ff0000, 0xff0000000000ff00, 0xff000000000000ff,
-    0xff00000000000000, 0xff00000000000001, 0xff00000000000100, 0xff0000000001ffff,
-    0xff00000000010000, 0xff00000001000000, 0xff00000001010100, 0xff000001ff00ff01,
-    0xff000001ff0100ff, 0xff00000100000000, 0xff0000010001ff00, 0xff00000101ff0100,
-    0xff0000010100ff00, 0xff0001ff00ff00ff, 0xff0001ff00000101, 0xff0001ff000100ff,
-    0xff0001ff01000000, 0xff000100ff0001ff, 0xff0001000000ff01, 0xff00010000000000,
-    0xff00010000010001, 0xff00010000010100, 0xff00010001ffff00, 0xff00010001ff0101,
-    0xff00010001010000, 0xff000101ffffffff, 0xff000101ff000101, 0xff00010101ff00ff,
-    0xff00010101000001, 0xff000101010100ff, 0xff01ffffff000101, 0xff01ffffff01ffff,
-    0xff01ffffff01ff01, 0xff01ffffff0101ff, 0xff01ffff00000000, 0xff01ffff01ff0001,
-    0xff01ffff0101ff01, 0xff01ff00ff000000, 0xff01ff0000ff0100, 0xff01ff000000ff01,
-    0xff01ff0000010000, 0xff01ff00010000ff, 0xff01ff01ff01ff00, 0xff01ff0100000101,
-    0xff0100ffffff0000, 0xff0100ffff010000, 0xff0100ff01ff00ff, 0xff0100ff01000100,
-    0xff0100ff010100ff, 0xff010000ffffff01, 0xff01000000000000, 0xff0100000101ff00,
-    0xff010001ffff00ff, 0xff010001ff000100, 0xff01000100ffff00, 0xff01000100010001,
-    0xff01000101ff0001, 0xff010001010001ff, 0xff0101ffffffffff, 0xff0101ffff01ffff,
-    0xff0101ffff010101, 0xff0101ff0000ff00, 0xff0101ff01010001, 0xff010100ff000000,
-    0xff010100ff01ff01, 0xff01010000ff0001, 0xff01010000000100, 0xff01010001000000,
-    0xff0101010100ffff, 0x00ffffff0000ff01, 0x00ffffff000000ff, 0x00ffffff00000100,
-    0x00ffffff00010000, 0x00ffff00ffff0001, 0x00ffff00ff0000ff, 0x00ffff00ff000100,
-    0x00ffff0000000000, 0x00ffff0001000100, 0x00ffff0001010001, 0x00ffff01ff00ff01,
-    0x00ffff0100ff0100, 0x00ffff010000ff00, 0x00ffff01000100ff, 0x00ffff0101ff00ff,
-    0x00ffff010101ff00, 0x00ff00ffffffffff, 0x00ff00ffffff01ff, 0x00ff00ffff000101,
-    0x00ff00ff00000000, 0x00ff00ff000101ff, 0x00ff00ff01010101, 0x00ff0000ff000000,
-    0x00ff0000ff01ffff, 0x00ff000000ff0000, 0x00ff00000000ff00, 0x00ff0000000000ff,
-    0x00ff000000000000, 0x00ff000000000001, 0x00ff000000000100, 0x00ff000000010000,
-    0x00ff000001ffff01, 0x00ff000001000000, 0x00ff0001ff000101, 0x00ff000100ffffff,
-    0x00ff000100000000, 0x00ff0001010001ff, 0x00ff01ffff000000, 0x00ff01ff0001ff00,
-    0x00ff01ff01ff0100, 0x00ff0100ff01ff01, 0x00ff010000ff00ff, 0x00ff010000ff0101,
-    0x00ff010000000000, 0x00ff010000010101, 0x00ff01000100ff00, 0x00ff010001010000,
-    0x00ff0101ffffff00, 0x00ff01010000ff01, 0x00ff010100000100, 0x00ff010101ff0000,
-    0x0000ffffffff0100, 0x0000ffffff00ff00, 0x0000ffffff0000ff, 0x0000ffffff010000,
-    0x0000ffff00000000, 0x0000ffff00010101, 0x0000ffff01ffff01, 0x0000ffff01000100,
-    0x0000ff00ff000000, 0x0000ff00ff01ff00, 0x0000ff00ff0101ff, 0x0000ff0000ff0000,
-    0x0000ff000000ff00, 0x0000ff00000000ff, 0x0000ff0000000000, 0x0000ff0000000001,
-    0x0000ff0000000100, 0x0000ff0000010000, 0x0000ff0001ffffff, 0x0000ff0001ff01ff,
-    0x0000ff0001000000, 0x0000ff000101ffff, 0x0000ff01ffff0101, 0x0000ff01ff010000,
-    0x0000ff0100000000, 0x0000ff0101000101, 0x000000ffffff0001, 0x000000ffff000000,
-    0x000000ff00ff0000, 0x000000ff0000ff00, 0x000000ff000000ff, 0x000000ff00000000,
-    0x000000ff00000001, 0x000000ff00000100, 0x000000ff00010000, 0x000000ff01000000,
-    0x000000ff0101ff00, 0x00000000ffff0000, 0x00000000ff00ff00, 0x00000000ff0000ff,
-    0x00000000ff000000, 0x00000000ff000001, 0x00000000ff000100, 0x00000000ff010000,
-    0x0000000000ffff00, 0x0000000000ff00ff, 0x0000000000ff0000, 0x0000000000ff0001,
-    0x0000000000ff0100, 0x000000000000ffff, 0x000000000000ff00, 0x000000000000ff01,
-    0x00000000000000ff, 0x0000000000000001, 0x00000000000001ff, 0x0000000000000100,
-    0x0000000000000101, 0x000000000001ff00, 0x00000000000100ff, 0x0000000000010000,
-    0x0000000000010001, 0x0000000000010100, 0x0000000001ff0000, 0x000000000100ff00,
-    0x00000000010000ff, 0x0000000001000000, 0x0000000001000001, 0x0000000001000100,
-    0x0000000001010000, 0x00000001ffff01ff, 0x00000001ff000000, 0x0000000100ff0000,
-    0x000000010000ff00, 0x00000001000000ff, 0x0000000100000000, 0x0000000100000001,
-    0x0000000100000100, 0x0000000100010000, 0x0000000101000000, 0x000001ffff00ff00,
-    0x000001ffff010001, 0x000001ffff0101ff, 0x000001ff00ffff01, 0x000001ff0000ffff,
-    0x000001ff00000000, 0x000001ff010000ff, 0x000001ff01010100, 0x00000100ffff0100,
-    0x00000100ff000000, 0x0000010000ff0000, 0x000001000000ff00, 0x00000100000000ff,
-    0x0000010000000000, 0x0000010000000001, 0x0000010000000100, 0x0000010000010000,
-    0x0000010001000000, 0x000001000101ff01, 0x00000101ffff0001, 0x00000101ff01ffff,
-    0x0000010100000000, 0x0000010101010100, 0x0001ffffff000000, 0x0001ffff00ffffff,
-    0x0001ffff00000100, 0x0001ffff0001ff00, 0x0001ffff01000000, 0x0001ff00ffffff00,
-    0x0001ff00ffff01ff, 0x0001ff00ff010000, 0x0001ff0000000000, 0x0001ff0000010001,
-    0x0001ff0001ff0000, 0x0001ff0001010100, 0x0001ff01ff0000ff, 0x0001ff01ff000001,
-    0x0001ff0100ffffff, 0x0001ff010001ffff, 0x0001ff01000101ff, 0x0001ff010100ff01,
-    0x000100ffff00ffff, 0x000100ffff00ff01, 0x000100ffff000100, 0x000100ff00000000,
-    0x000100ff000101ff, 0x000100ff01ff0101, 0x000100ff0100ffff, 0x000100ff01010101,
-    0x00010000ff000000, 0x00010000ff010100, 0x0001000000ff0000, 0x000100000000ff00,
-    0x00010000000000ff, 0x0001000000000000, 0x0001000000000001, 0x0001000000000100,
-    0x0001000000010000, 0x0001000001ffff01, 0x0001000001000000, 0x0001000100ff0101,
-    0x0001000100000000, 0x00010001010100ff, 0x000101ffffff01ff, 0x000101ffffff0101,
-    0x000101ff00010000, 0x000101ff01ff0000, 0x000101ff0100ff01, 0x00010100ffff0000,
-    0x0001010000000000, 0x000101000001ffff, 0x0001010000010101, 0x00010100010001ff,
-    0x00010101ff00ff00, 0x00010101ff010001, 0x0001010100ffffff, 0x0001010100ff01ff,
-    0x00010101000101ff, 0x0001010101ff0000, 0x000101010100ff01, 0x0001010101000101,
-    0x01ffffffffff0101, 0x01ffffffff01ffff, 0x01ffffffff01ff01, 0x01ffffffff0101ff,
-    0x01ffffffff010101, 0x01ffffff00000000, 0x01ffffff01ff01ff, 0x01ffffff01000101,
-    0x01ffffff0101ff01, 0x01ffffff010100ff, 0x01ffff000000ff00, 0x01ffff0000000001,
-    0x01ffff00000001ff, 0x01ffff0000010000, 0x01ffff0001ff0000, 0x01ffff01ffffffff,
-    0x01ffff01ffff01ff, 0x01ffff01ff000000, 0x01ffff01ff01ffff, 0x01ffff01ff0101ff,
-    0x01ffff010100ffff, 0x01ff00ffffff0000, 0x01ff00ffff010000, 0x01ff00ff00ffff01,
-    0x01ff0000ff0000ff, 0x01ff000000000000, 0x01ff00000001ff01, 0x01ff000001ffffff,
-    0x01ff000001010100, 0x01ff0001ffffff01, 0x01ff0001ff010001, 0x01ff000101ff0100,
-    0x01ff000101000001, 0x01ff0001010100ff, 0x01ff01ffff00ffff, 0x01ff01ff00010001,
-    0x01ff01ff01000000, 0x01ff01ff010101ff, 0x01ff0100ff000001, 0x01ff010000ffff00,
-    0x01ff010000000100, 0x01ff010001ff01ff, 0x01ff01000101ffff, 0x01ff0101ffff00ff,
-    0x01ff0101ffff0101, 0x01ff0101ff0101ff, 0x01ff010100010000, 0x0100ffff00ff00ff,
-    0x0100ffff00ff0001, 0x0100ffff00000100, 0x0100ffff0100ff00, 0x0100ff00ffff0000,
-    0x0100ff00ff00ffff, 0x0100ff00ff00ff01, 0x0100ff00ff000100, 0x0100ff00ff010000,
-    0x0100ff0000000000, 0x0100ff00000100ff, 0x0100ff0001ff0101, 0x0100ff0001010101,
-    0x0100ff0100ff00ff, 0x0100ff0100ff0001, 0x0100ff0100000100, 0x0100ff0100010001,
-    0x0100ff0101000000, 0x010000ffff00ff00, 0x010000ff0000ffff, 0x010000ff00000000,
-    0x010000ff010001ff, 0x010000ff01010001, 0x01000000ffffff00, 0x01000000ffff0101,
-    0x01000000ff000000, 0x01000000ff0100ff, 0x01000000ff010101, 0x0100000000ff0000,
-    0x010000000000ff00, 0x01000000000000ff, 0x0100000000000000, 0x0100000000000001,
-    0x0100000000000100, 0x0100000000010000, 0x0100000001000000, 0x0100000100000000,
-    0x01000001000101ff, 0x0100000101ffff01, 0x010001ffff000101, 0x010001ff00ff0100,
-    0x010001ff0000ff00, 0x010001ff000100ff, 0x010001ff01ffffff, 0x01000100ffff0000,
-    0x01000100ff0001ff, 0x0100010000000000, 0x010001000001ff00, 0x0100010001ff0000,
-    0x01000100010000ff, 0x0100010001000101, 0x01000101ff00ff01, 0x0100010100ff0100,
-    0x010001010000ffff, 0x0100010101010001, 0x0101ffffffff0101, 0x0101ffffff0001ff,
-    0x0101ffffff01ffff, 0x0101ffffff010101, 0x0101ffff00000000, 0x0101ffff0101ffff,
-    0x0101ffff010101ff, 0x0101ff00ff000000, 0x0101ff0000ff0100, 0x0101ff000000ff00,
-    0x0101ff0000010000, 0x0101ff00010000ff, 0x0101ff0001000001, 0x0101ff01ff010101,
-    0x0101ff0100000000, 0x0101ff010101ff00, 0x010100ffffff0000, 0x010100ffff010000,
-    0x010100ff00ff01ff, 0x010100ff000000ff, 0x010100ff00000101, 0x010100ff01ffff00,
-    0x01010000ffffff01, 0x01010000ff000100, 0x01010000ff01ff01, 0x0101000000000000,
-    0x01010000000100ff, 0x010100000101ff01, 0x01010001ffff0000, 0x01010001ff00ffff,
-    0x01010001ff010000, 0x0101000101ffffff, 0x0101000101ff01ff, 0x0101000101010101,
-    0x010101ffff01ffff, 0x010101ff00000000, 0x010101ff0001ff01, 0x010101ff0101ffff,
-    0x010101ff010101ff, 0x01010100ffffffff, 0x01010100ff000001, 0x010101000000ff00,
-    0x0101010001010000, 0x0101010100ff0001, 0x010101010001ff01, 0x010101010101ffff,
-
-};
-
-static const uint8_t ksigns_iq2xs[128] = {
-      0, 129, 130,   3, 132,   5,   6, 135, 136,   9,  10, 139,  12, 141, 142,  15,
-    144,  17,  18, 147,  20, 149, 150,  23,  24, 153, 154,  27, 156,  29,  30, 159,
-    160,  33,  34, 163,  36, 165, 166,  39,  40, 169, 170,  43, 172,  45,  46, 175,
-     48, 177, 178,  51, 180,  53,  54, 183, 184,  57,  58, 187,  60, 189, 190,  63,
-    192,  65,  66, 195,  68, 197, 198,  71,  72, 201, 202,  75, 204,  77,  78, 207,
-     80, 209, 210,  83, 212,  85,  86, 215, 216,  89,  90, 219,  92, 221, 222,  95,
-     96, 225, 226,  99, 228, 101, 102, 231, 232, 105, 106, 235, 108, 237, 238, 111,
-    240, 113, 114, 243, 116, 245, 246, 119, 120, 249, 250, 123, 252, 125, 126, 255,
-};
+size_t quantize_q8_0(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
+    (void)quant_weights; // not used
+    const size_t row_size = ggml_row_size(GGML_TYPE_Q8_0, n_per_row);
+    quantize_row_q8_0_reference(src, dst, nrow*n_per_row);
+    return nrow * row_size;
+}
 
-static const uint8_t kmask_iq2xs[8] = {1, 2, 4, 8, 16, 32, 64, 128};
+// ====================== "True" 2-bit (de)-quantization
 
 void dequantize_row_iq2_xxs(const block_iq2_xxs * restrict x, float * restrict y, int k) {
     assert(k % QK_K == 0);
@@ -4162,11 +3418,11 @@ void dequantize_row_iq3_s(const block_iq3_s * restrict x, float * restrict y, in
         const uint8_t * signs = x[i].signs;
 
         for (int ib32 = 0; ib32 < QK_K/32; ib32 += 2) {
-            const float db1 = d * (0.5f + (x[i].scales[ib32/2] & 0xf)) * 0.5f;
-            const float db2 = d * (0.5f + (x[i].scales[ib32/2] >>  4)) * 0.5f;
+            const float db1 = d * (1 + 2*(x[i].scales[ib32/2] & 0xf));
+            const float db2 = d * (1 + 2*(x[i].scales[ib32/2] >>  4));
             for (int l = 0; l < 4; ++l) {
-                const uint8_t * grid1 = (const uint8_t *)(iq3xs_grid + (qs[2*l+0] | ((qh[0] << (8-2*l)) & 256)));
-                const uint8_t * grid2 = (const uint8_t *)(iq3xs_grid + (qs[2*l+1] | ((qh[0] << (7-2*l)) & 256)));
+                const uint8_t * grid1 = (const uint8_t *)(iq3s_grid + (qs[2*l+0] | ((qh[0] << (8-2*l)) & 256)));
+                const uint8_t * grid2 = (const uint8_t *)(iq3s_grid + (qs[2*l+1] | ((qh[0] << (7-2*l)) & 256)));
                 for (int j = 0; j < 4; ++j) {
                     y[j+0] = db1 * grid1[j] * (signs[l] & kmask_iq2xs[j+0] ? -1.f : 1.f);
                     y[j+4] = db1 * grid2[j] * (signs[l] & kmask_iq2xs[j+4] ? -1.f : 1.f);
@@ -4176,8 +3432,8 @@ void dequantize_row_iq3_s(const block_iq3_s * restrict x, float * restrict y, in
             qs += 8;
             signs += 4;
             for (int l = 0; l < 4; ++l) {
-                const uint8_t * grid1 = (const uint8_t *)(iq3xs_grid + (qs[2*l+0] | ((qh[1] << (8-2*l)) & 256)));
-                const uint8_t * grid2 = (const uint8_t *)(iq3xs_grid + (qs[2*l+1] | ((qh[1] << (7-2*l)) & 256)));
+                const uint8_t * grid1 = (const uint8_t *)(iq3s_grid + (qs[2*l+0] | ((qh[1] << (8-2*l)) & 256)));
+                const uint8_t * grid2 = (const uint8_t *)(iq3s_grid + (qs[2*l+1] | ((qh[1] << (7-2*l)) & 256)));
                 for (int j = 0; j < 4; ++j) {
                     y[j+0] = db2 * grid1[j] * (signs[l] & kmask_iq2xs[j+0] ? -1.f : 1.f);
                     y[j+4] = db2 * grid2[j] * (signs[l] & kmask_iq2xs[j+4] ? -1.f : 1.f);
@@ -4197,39 +3453,23 @@ void dequantize_row_iq1_s(const block_iq1_s * restrict x, float * restrict y, in
     assert(k % QK_K == 0);
     const int nb = k / QK_K;
 
-    float db[4];
-    uint16_t idx[4];
-    //const int8_t * grid[4];
-
     for (int i = 0; i < nb; i++) {
 
         const float d = GGML_FP16_TO_FP32(x[i].d);
-        const uint8_t * sc = x[i].scales;
-        const uint8_t * qs = x[i].qs;
+        const uint8_t  * qs = x[i].qs;
+        const uint16_t * qh = x[i].qh;
 
-        for (int i8 = 0; i8 < QK_K/8; i8 += 4) {
-            idx[0] = qs[0] | ((sc[0] & 0x08) << 5);
-            idx[1] = qs[1] | ((sc[0] & 0x80) << 1);
-            idx[2] = qs[2] | ((sc[1] & 0x08) << 5);
-            idx[3] = qs[3] | ((sc[1] & 0x80) << 1);
-            //grid[0] = (const int8_t *)(iq1s_grid + (qs[0] | ((sc[0] & 0x08) << 5)));
-            //grid[1] = (const int8_t *)(iq1s_grid + (qs[1] | ((sc[0] & 0x80) << 1)));
-            //grid[2] = (const int8_t *)(iq1s_grid + (qs[2] | ((sc[1] & 0x08) << 5)));
-            //grid[3] = (const int8_t *)(iq1s_grid + (qs[3] | ((sc[1] & 0x80) << 1)));
-            db[0] = d * (2*(sc[0] & 7) + 1);
-            db[1] = d * (2*((sc[0] >> 4) & 7) + 1);
-            db[2] = d * (2*(sc[1] & 7) + 1);
-            db[3] = d * (2*((sc[1] >> 4) & 7) + 1);
+        for (int ib = 0; ib < QK_K/32; ++ib) {
+            const float dl = d * (2*((qh[ib] >> 12) & 7) + 1);
+            const float delta = qh[ib] & 0x8000 ? -IQ1S_DELTA : IQ1S_DELTA;
             for (int l = 0; l < 4; ++l) {
-                const int8_t * grid = (const int8_t *)(iq1s_grid + idx[l]);
+                const int8_t * grid = (const int8_t *)(iq1s_grid + (qs[l] | (((qh[ib] >> 3*l) & 7) << 8)));
                 for (int j = 0; j < 8; ++j) {
-                    //y[j] = db[l] * grid[l][j];
-                    y[j] = db[l] * grid[j];
+                    y[j] = dl * (grid[j] + delta);
                 }
                 y += 8;
             }
             qs += 4;
-            sc += 2;
         }
     }
 }
@@ -4783,10 +4023,10 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
             const block_q8_1 * restrict b_y0 = &vy0[i];
             const block_q8_1 * restrict b_y1 = &vy1[i];
 
-            float32x4_t summs_t = {GGML_FP16_TO_FP32(b_x0->m) * b_y0->s,
-                                   GGML_FP16_TO_FP32(b_x1->m) * b_y0->s,
-                                   GGML_FP16_TO_FP32(b_x0->m) * b_y1->s,
-                                   GGML_FP16_TO_FP32(b_x1->m) * b_y1->s};
+            float32x4_t summs_t = {GGML_FP16_TO_FP32(b_x0->m) * GGML_FP16_TO_FP32(b_y0->s),
+                                   GGML_FP16_TO_FP32(b_x1->m) * GGML_FP16_TO_FP32(b_y0->s),
+                                   GGML_FP16_TO_FP32(b_x0->m) * GGML_FP16_TO_FP32(b_y1->s),
+                                   GGML_FP16_TO_FP32(b_x1->m) * GGML_FP16_TO_FP32(b_y1->s)};
             summs0 += summs_t;
 
             const uint8x16_t m4b = vdupq_n_u8(0x0F);
@@ -4807,10 +4047,10 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
             const int8x16_t y1_h = vld1q_s8(b_y1->qs + 16);
 
             // mmla into int32x4_t
-            float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y0->d),
-                                 GGML_FP16_TO_FP32(b_x0->d)*GGML_FP16_TO_FP32(b_y1->d),
-                                 GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y0->d),
-                                 GGML_FP16_TO_FP32(b_x1->d)*GGML_FP16_TO_FP32(b_y1->d)};
+            float32x4_t scale = {GGML_FP16_TO_FP32(b_x0->d)*b_y0->d,
+                                 GGML_FP16_TO_FP32(b_x0->d)*b_y1->d,
+                                 GGML_FP16_TO_FP32(b_x1->d)*b_y0->d,
+                                 GGML_FP16_TO_FP32(b_x1->d)*b_y1->d};
 
             int8x16_t l0 = vreinterpretq_s8_s64(vzip1q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l)));
             int8x16_t l1 = vreinterpretq_s8_s64(vzip2q_s64(vreinterpretq_s64_s8(x0_l), vreinterpretq_s64_s8(x1_l)));
@@ -4851,7 +4091,7 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
         const block_q8_1 * restrict y0 = &y[i + 0];
         const block_q8_1 * restrict y1 = &y[i + 1];
 
-        summs += GGML_FP16_TO_FP32(x0->m) * y0->s + GGML_FP16_TO_FP32(x1->m) * y1->s;
+        summs += GGML_FP16_TO_FP32(x0->m) * GGML_FP16_TO_FP32(y0->s) + GGML_FP16_TO_FP32(x1->m) * GGML_FP16_TO_FP32(y1->s);
 
         const uint8x16_t m4b = vdupq_n_u8(0x0F);
 
@@ -4874,8 +4114,8 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
         const int32x4_t p_0 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), v0_0l, v1_0l), v0_0h, v1_0h);
         const int32x4_t p_1 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), v0_1l, v1_1l), v0_1h, v1_1h);
 
-        sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(p_0), GGML_FP16_TO_FP32(x0->d)*y0->d);
-        sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(p_1), GGML_FP16_TO_FP32(x1->d)*y1->d);
+        sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(p_0), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d));
+        sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(p_1), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d));
     }
 
     *s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1) + summs;
@@ -4888,9 +4128,9 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
     // Main loop
     for (int i = 0; i < nb; ++i) {
         const float d0 = GGML_FP16_TO_FP32(x[i].d);
-        const float d1 = y[i].d;
+        const float d1 = GGML_FP16_TO_FP32(y[i].d);
 
-        summs += GGML_FP16_TO_FP32(x[i].m) * y[i].s;
+        summs += GGML_FP16_TO_FP32(x[i].m) * GGML_FP16_TO_FP32(y[i].s);
 
         const __m256 d0v = _mm256_set1_ps( d0 );
         const __m256 d1v = _mm256_set1_ps( d1 );
@@ -4942,7 +4182,7 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
 
         int sumi = __riscv_vmv_x_s_i32m1_i32(vs2);
 
-        sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s;
+        sumf += (GGML_FP16_TO_FP32(x[i].d)*GGML_FP16_TO_FP32(y[i].d))*sumi + GGML_FP16_TO_FP32(x[i].m)*GGML_FP16_TO_FP32(y[i].s);
     }
 
     *s = sumf;
@@ -4960,7 +4200,7 @@ void ggml_vec_dot_q4_1_q8_1(int n, float * restrict s, size_t bs, const void * r
             sumi += (v0 * y[i].qs[j]) + (v1 * y[i].qs[j + qk/2]);
         }
 
-        sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s;
+        sumf += (GGML_FP16_TO_FP32(x[i].d)*GGML_FP16_TO_FP32(y[i].d))*sumi + GGML_FP16_TO_FP32(x[i].m)*GGML_FP16_TO_FP32(y[i].s);
     }
 
     *s = sumf;
@@ -5296,8 +4536,8 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
 
         const uint8x16_t m4b = vdupq_n_u8(0x0F);
 
-        summs0 += GGML_FP16_TO_FP32(x0->m) * y0->s;
-        summs1 += GGML_FP16_TO_FP32(x1->m) * y1->s;
+        summs0 += GGML_FP16_TO_FP32(x0->m) * GGML_FP16_TO_FP32(y0->s);
+        summs1 += GGML_FP16_TO_FP32(x1->m) * GGML_FP16_TO_FP32(y1->s);
 
         // extract the 5th bit via lookup table ((b) << 4)
         memcpy(&qh0, x0->qh, sizeof(qh0));
@@ -5341,10 +4581,10 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
 
         sumv0 = vmlaq_n_f32(sumv0, vcvtq_f32_s32(vaddq_s32(
                         ggml_vdotq_s32(vdupq_n_s32(0), v0_0lf, v1_0l),
-                        ggml_vdotq_s32(vdupq_n_s32(0), v0_0hf, v1_0h))), GGML_FP16_TO_FP32(x0->d)*y0->d);
+                        ggml_vdotq_s32(vdupq_n_s32(0), v0_0hf, v1_0h))), GGML_FP16_TO_FP32(x0->d)*GGML_FP16_TO_FP32(y0->d));
         sumv1 = vmlaq_n_f32(sumv1, vcvtq_f32_s32(vaddq_s32(
                         ggml_vdotq_s32(vdupq_n_s32(0), v0_1lf, v1_1l),
-                        ggml_vdotq_s32(vdupq_n_s32(0), v0_1hf, v1_1h))), GGML_FP16_TO_FP32(x1->d)*y1->d);
+                        ggml_vdotq_s32(vdupq_n_s32(0), v0_1hf, v1_1h))), GGML_FP16_TO_FP32(x1->d)*GGML_FP16_TO_FP32(y1->d));
     }
 
     *s = vaddvq_f32(sumv0) + vaddvq_f32(sumv1) + summs0 + summs1;
@@ -5361,7 +4601,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
         const block_q5_1 * restrict x0 = &x[i];
         const block_q8_1 * restrict y0 = &y[i];
 
-        summs += GGML_FP16_TO_FP32(x0->m) * y0->s;
+        summs += GGML_FP16_TO_FP32(x0->m) * GGML_FP16_TO_FP32(y0->s);
 
         const v128_t m4b = wasm_i8x16_splat(0x0F);
 
@@ -5408,7 +4648,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
                                            wasm_i32x4_dot_i16x8(v0lfh, v1lh)),
                             wasm_i32x4_add(wasm_i32x4_dot_i16x8(v0hfl, v1hl),
                                            wasm_i32x4_dot_i16x8(v0hfh, v1hh)))),
-                    wasm_f32x4_splat(GGML_FP16_TO_FP32(x0->d) * y0->d)));
+                    wasm_f32x4_splat(GGML_FP16_TO_FP32(x0->d) * GGML_FP16_TO_FP32(y0->d))));
     }
 
     *s = wasm_f32x4_extract_lane(sumv, 0) + wasm_f32x4_extract_lane(sumv, 1) +
@@ -5423,14 +4663,14 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
     for (int i = 0; i < nb; i++) {
         const __m256 dx = _mm256_set1_ps(GGML_FP16_TO_FP32(x[i].d));
 
-        summs += GGML_FP16_TO_FP32(x[i].m) * y[i].s;
+        summs += GGML_FP16_TO_FP32(x[i].m) * GGML_FP16_TO_FP32(y[i].s);
 
         __m256i qx = bytes_from_nibbles_32(x[i].qs);
         __m256i bxhi = bytes_from_bits_32(x[i].qh);
         bxhi = _mm256_and_si256(bxhi, _mm256_set1_epi8(0x10));
         qx = _mm256_or_si256(qx, bxhi);
 
-        const __m256 dy = _mm256_set1_ps(y[i].d);
+        const __m256 dy = _mm256_set1_ps(GGML_FP16_TO_FP32(y[i].d));
         const __m256i qy = _mm256_loadu_si256((const __m256i *)y[i].qs);
 
         const __m256 q = mul_sum_us8_pairs_float(qx, qy);
@@ -5450,7 +4690,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
     for (int i = 0; i < nb; i++) {
         const __m256 dx = _mm256_set1_ps(GGML_FP16_TO_FP32(x[i].d));
 
-        summs += GGML_FP16_TO_FP32(x[i].m) * y[i].s;
+        summs += GGML_FP16_TO_FP32(x[i].m) * GGML_FP16_TO_FP32(y[i].s);
 
         __m256i bx_0 = bytes_from_nibbles_32(x[i].qs);
         const __m256i bxhi = bytes_from_bits_32(x[i].qh);
@@ -5464,7 +4704,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
         bxh = _mm_or_si128(bxh, bxhih);
         bx_0 = MM256_SET_M128I(bxh, bxl);
 
-        const __m256 dy = _mm256_set1_ps(y[i].d);
+        const __m256 dy = _mm256_set1_ps(GGML_FP16_TO_FP32(y[i].d));
         const __m256i by_0 = _mm256_loadu_si256((const __m256i *)y[i].qs);
 
         const __m256 q = mul_sum_us8_pairs_float(bx_0, by_0);
@@ -5531,7 +4771,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
 
         int sumi = __riscv_vmv_x_s_i32m1_i32(vs2);
 
-        sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s;
+        sumf += (GGML_FP16_TO_FP32(x[i].d)*GGML_FP16_TO_FP32(y[i].d))*sumi + GGML_FP16_TO_FP32(x[i].m)*GGML_FP16_TO_FP32(y[i].s);
     }
 
     *s = sumf;
@@ -5555,7 +4795,7 @@ void ggml_vec_dot_q5_1_q8_1(int n, float * restrict s, size_t bs, const void * r
             sumi += (x0 * y[i].qs[j]) + (x1 * y[i].qs[j + qk/2]);
         }
 
-        sumf += (GGML_FP16_TO_FP32(x[i].d)*y[i].d)*sumi + GGML_FP16_TO_FP32(x[i].m)*y[i].s;
+        sumf += (GGML_FP16_TO_FP32(x[i].d)*GGML_FP16_TO_FP32(y[i].d))*sumi + GGML_FP16_TO_FP32(x[i].m)*GGML_FP16_TO_FP32(y[i].s);
     }
 
     *s = sumf;
@@ -9563,7 +8803,7 @@ void ggml_vec_dot_iq2_xs_q8_K(int n, float * restrict s, size_t bs, const void *
 
         const __m128i odd_bits = _mm_shuffle_epi8(bit_helper, partial_sign_bits_for_counting);
         const __m128i full_sign_bits = _mm_or_si128(partial_sign_bits, odd_bits);
-        const __m256i full_signs = _mm256_set_m128i(full_sign_bits, full_sign_bits);
+        const __m256i full_signs = MM256_SET_M128I(full_sign_bits, full_sign_bits);
 
         const __m256i q8_1 = _mm256_loadu_si256((const __m256i *)y[i].qs);
         const __m256i q8_2 = _mm256_loadu_si256((const __m256i *)(y[i].qs+32));
@@ -9585,8 +8825,8 @@ void ggml_vec_dot_iq2_xs_q8_K(int n, float * restrict s, size_t bs, const void *
         const __m256i dot1  = _mm256_maddubs_epi16(q2_1, q8s_1);
         const __m256i dot2  = _mm256_maddubs_epi16(q2_2, q8s_2);
 
-        const __m256i sc1 = _mm256_set_m128i(_mm_set1_epi16(2*(x[i].scales[0] >> 4)+1), _mm_set1_epi16(2*(x[i].scales[0] & 0xf)+1));
-        const __m256i sc2 = _mm256_set_m128i(_mm_set1_epi16(2*(x[i].scales[1] >> 4)+1), _mm_set1_epi16(2*(x[i].scales[1] & 0xf)+1));
+        const __m256i sc1 = MM256_SET_M128I(_mm_set1_epi16(2*(x[i].scales[0] >> 4)+1), _mm_set1_epi16(2*(x[i].scales[0] & 0xf)+1));
+        const __m256i sc2 = MM256_SET_M128I(_mm_set1_epi16(2*(x[i].scales[1] >> 4)+1), _mm_set1_epi16(2*(x[i].scales[1] & 0xf)+1));
 
         const __m256i sum = _mm256_add_epi32(_mm256_madd_epi16(sc1, dot1), _mm256_madd_epi16(sc2, dot2));
 
@@ -9653,8 +8893,8 @@ void ggml_vec_dot_iq2_xs_q8_K(int n, float * restrict s, size_t bs, const void *
 
             const __m128i full_signs_l = _mm256_castsi256_si128(full_sign_bits);
             const __m128i full_signs_h = _mm256_extractf128_si256(full_sign_bits, 1);
-            const __m256i full_signs_1 = _mm256_set_m128i(full_signs_l, full_signs_l);
-            const __m256i full_signs_2 = _mm256_set_m128i(full_signs_h, full_signs_h);
+            const __m256i full_signs_1 = MM256_SET_M128I(full_signs_l, full_signs_l);
+            const __m256i full_signs_2 = MM256_SET_M128I(full_signs_h, full_signs_h);
 
             __m256i signs;
             signs = _mm256_shuffle_epi8(full_signs_1, block_sign_shuffle_1);
@@ -9757,8 +8997,8 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void *
 
     static const uint8_t k_mask2[16] = {0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80,};
 
-    const uint8x16x2_t mask1 = vld1q_u8_x2(k_mask1);
-    const uint8x16_t   mask2 = vld1q_u8(k_mask2);
+    const ggml_uint8x16x2_t mask1 = ggml_vld1q_u8_x2(k_mask1);
+    const uint8x16_t        mask2 = vld1q_u8(k_mask2);
     const uint8x16_t m1 = vdupq_n_u8(1);
     const int32x4_t vzero = vdupq_n_s32(0);
 
@@ -9789,7 +9029,7 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void *
                                      vld1_s8((const int8_t *)(iq2s_grid + (qs[7] | ((qh[ib32+1] << 2) & 0x300)))));
             qs += 8;
 
-            vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | (signs[1] << 16)));
+            vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | ((uint32_t) signs[1] << 16)));
             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
             vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2);
             vs.val[0] = vceqq_u8(vs.val[0], mask2);
@@ -9798,7 +9038,7 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void *
             q2s.val[0] = vmulq_s8(vreinterpretq_s8_u8(vorrq_u8(vs.val[0], m1)), q2s.val[0]);
             q2s.val[1] = vmulq_s8(vreinterpretq_s8_u8(vorrq_u8(vs.val[1], m1)), q2s.val[1]);
 
-            vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[2] | (signs[3] << 16)));
+            vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[2] | ((uint32_t) signs[3] << 16)));
             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
             vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2);
             vs.val[0] = vceqq_u8(vs.val[0], mask2);
@@ -9869,12 +9109,12 @@ void ggml_vec_dot_iq2_s_q8_K(int n, float * restrict s, size_t bs, const void *
                                                    iq2s_grid[qs[4] | ((qh[ib32+1] << 8) & 0x300)]);
             qs += 8;
 
-            __m256i aux256 = _mm256_set1_epi32(signs[0] | (signs[1] << 16));
+            __m256i aux256 = _mm256_set1_epi32(signs[0] | ((uint32_t) signs[1] << 16));
             aux256 = _mm256_and_si256(_mm256_shuffle_epi8(aux256,mask1), mask2);
             const __m256i s2_1 = _mm256_cmpeq_epi8(aux256, mask2);
             const __m256i q8s_1 = _mm256_sub_epi8(_mm256_xor_si256(s2_1, q8_1), s2_1);
 
-            aux256 = _mm256_set1_epi32(signs[2] | (signs[3] << 16));
+            aux256 = _mm256_set1_epi32(signs[2] | ((uint32_t) signs[3] << 16));
             aux256 = _mm256_and_si256(_mm256_shuffle_epi8(aux256,mask1), mask2);
             const __m256i s2_2 = _mm256_cmpeq_epi8(aux256, mask2);
             const __m256i q8s_2 = _mm256_sub_epi8(_mm256_xor_si256(s2_2, q8_2), s2_2);
@@ -10074,7 +9314,7 @@ void ggml_vec_dot_iq3_xxs_q8_K(int n, float * restrict s, size_t bs, const void
 #endif
 }
 
-void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) {
+void ggml_vec_dot_iq3_s_q8_K (int n, float * restrict s, size_t bs, const void * restrict vx, size_t bx, const void * restrict vy, size_t by, int nrc) {
     assert(n % QK_K == 0);
     assert(nrc == 1);
     UNUSED(nrc);
@@ -10089,18 +9329,35 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
 
 #if defined(__ARM_NEON)
 
+    typedef union {
+        uint16x8_t vec_index;
+        uint16_t   index[8];
+    } vec_index_t;
+
    static const uint8_t k_mask1[32] = {0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01, 0x01,
                                        0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x02, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03, 0x03
    };
 
     static const uint8_t k_mask2[16] = {0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80, 0x01, 0x02, 0x04, 0x08, 0x10, 0x20, 0x40, 0x80,};
 
-    const uint8x16x2_t mask1 = vld1q_u8_x2(k_mask1);
-    const uint8x16_t   mask2 = vld1q_u8(k_mask2);
+    static const int16_t k_shift[8] = {8, 7, 6, 5, 4, 3, 2, 1};
+
+    const ggml_uint8x16x2_t mask1 = ggml_vld1q_u8_x2(k_mask1);
+    const uint8x16_t        mask2 = vld1q_u8(k_mask2);
+
+    const int16x8_t  hshift = vld1q_s16(k_shift);
+    const uint16x8_t m256   = vdupq_n_u16(256);
+    const uint8x16_t m1     = vdupq_n_u8(1);
 
     uint8x16x2_t vs;
     ggml_int8x16x4_t q3s;
     ggml_int8x16x4_t q8b;
+    vec_index_t idx;
+
+#if QK_K == 256
+    uint32_t scales32[2];
+    const uint8_t * scales8 = (const uint8_t *)scales32;
+#endif
 
     float sumf = 0;
     for (int i = 0; i < nb; ++i) {
@@ -10109,47 +9366,63 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
         const uint8_t * restrict qh = x[i].qh;
         const uint16_t * restrict signs = (const uint16_t *)x[i].signs;
         const int8_t   * restrict q8 = y[i].qs;
+
+#if QK_K == 256
+        memcpy(scales32, x[i].scales, 4);
+        scales32[1] = (((scales32[0] >> 4) & 0x0f0f0f0f) << 1) | 0x01010101;
+        scales32[0] = ((scales32[0] & 0x0f0f0f0f) << 1) | 0x01010101;
+#endif
+
         int sumi1 = 0, sumi2 = 0;
         for (int ib32 = 0; ib32 < QK_K/32; ib32 += 2) {
             q8b = ggml_vld1q_s8_x4(q8); q8 += 64;
-            const uint32x4_t aux32x4_0 = {iq3xs_grid[qs[ 0] | ((qh[ib32+0] << 8) & 256)], iq3xs_grid[qs[ 1] | ((qh[ib32+0] << 7) & 256)],
-                                          iq3xs_grid[qs[ 2] | ((qh[ib32+0] << 6) & 256)], iq3xs_grid[qs[ 3] | ((qh[ib32+0] << 5) & 256)]};
-            const uint32x4_t aux32x4_1 = {iq3xs_grid[qs[ 4] | ((qh[ib32+0] << 4) & 256)], iq3xs_grid[qs[ 5] | ((qh[ib32+0] << 3) & 256)],
-                                          iq3xs_grid[qs[ 6] | ((qh[ib32+0] << 2) & 256)], iq3xs_grid[qs[ 7] | ((qh[ib32+0] << 1) & 256)]};
-            const uint32x4_t aux32x4_2 = {iq3xs_grid[qs[ 8] | ((qh[ib32+1] << 8) & 256)], iq3xs_grid[qs[ 9] | ((qh[ib32+1] << 7) & 256)],
-                                          iq3xs_grid[qs[10] | ((qh[ib32+1] << 6) & 256)], iq3xs_grid[qs[11] | ((qh[ib32+1] << 5) & 256)]};
-            const uint32x4_t aux32x4_3 = {iq3xs_grid[qs[12] | ((qh[ib32+1] << 4) & 256)], iq3xs_grid[qs[13] | ((qh[ib32+1] << 3) & 256)],
-                                          iq3xs_grid[qs[14] | ((qh[ib32+1] << 2) & 256)], iq3xs_grid[qs[15] | ((qh[ib32+1] << 1) & 256)]};
-            qs += 16;
 
-            vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | (signs[1] << 16)));
+            const uint8x16_t idx_l = vld1q_u8(qs); qs += 16;
+            idx.vec_index = vorrq_u16(vmovl_u8(vget_low_u8 (idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+0]), hshift), m256));
+            const uint32x4_t aux32x4_0 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
+                                                        iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]);
+            const uint32x4_t aux32x4_1 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
+                                                        iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]);
+            idx.vec_index = vorrq_u16(vmovl_u8(vget_high_u8(idx_l)), vandq_u16(vshlq_u16(vdupq_n_u16(qh[ib32+1]), hshift), m256));
+            const uint32x4_t aux32x4_2 = ggml_vld1q_u32(iq3s_grid[idx.index[0]], iq3s_grid[idx.index[1]],
+                                                        iq3s_grid[idx.index[2]], iq3s_grid[idx.index[3]]);
+            const uint32x4_t aux32x4_3 = ggml_vld1q_u32(iq3s_grid[idx.index[4]], iq3s_grid[idx.index[5]],
+                                                        iq3s_grid[idx.index[6]], iq3s_grid[idx.index[7]]);
+
+
+            vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[0] | ((uint32_t) signs[1] << 16)));
             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
             vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2);
-            vs.val[0] = vceqq_u8(vs.val[0], mask2);
-            vs.val[1] = vceqq_u8(vs.val[1], mask2);
+            vs.val[0] = vorrq_u8(vceqq_u8(vs.val[0], mask2), m1);
+            vs.val[1] = vorrq_u8(vceqq_u8(vs.val[1], mask2), m1);
 
-            q3s.val[0] = vsubq_s8(vreinterpretq_s8_u8(veorq_u8(vs.val[0], vreinterpretq_u8_u32(aux32x4_0))), vreinterpretq_s8_u8(vs.val[0]));
-            q3s.val[1] = vsubq_s8(vreinterpretq_s8_u8(veorq_u8(vs.val[1], vreinterpretq_u8_u32(aux32x4_1))), vreinterpretq_s8_u8(vs.val[1]));
+            q3s.val[0] = vmulq_s8(vreinterpretq_s8_u8(vs.val[0]), vreinterpretq_s8_u32(aux32x4_0));
+            q3s.val[1] = vmulq_s8(vreinterpretq_s8_u8(vs.val[1]), vreinterpretq_s8_u32(aux32x4_1));
 
-            vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[2] | (signs[3] << 16)));
+            vs.val[0] = vreinterpretq_u8_u32(vdupq_n_u32(signs[2] | ((uint32_t) signs[3] << 16)));
             vs.val[1] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[1]), mask2);
             vs.val[0] = vandq_u8(ggml_vqtbl1q_u8(vs.val[0], mask1.val[0]), mask2);
-            vs.val[0] = vceqq_u8(vs.val[0], mask2);
-            vs.val[1] = vceqq_u8(vs.val[1], mask2);
+            vs.val[0] = vorrq_u8(vceqq_u8(vs.val[0], mask2), m1);
+            vs.val[1] = vorrq_u8(vceqq_u8(vs.val[1], mask2), m1);
 
             signs += 4;
 
-            q3s.val[2] = vsubq_s8(vreinterpretq_s8_u8(veorq_u8(vs.val[0], vreinterpretq_u8_u32(aux32x4_2))), vreinterpretq_s8_u8(vs.val[0]));
-            q3s.val[3] = vsubq_s8(vreinterpretq_s8_u8(veorq_u8(vs.val[1], vreinterpretq_u8_u32(aux32x4_3))), vreinterpretq_s8_u8(vs.val[1]));
+            q3s.val[2] = vmulq_s8(vreinterpretq_s8_u8(vs.val[0]), vreinterpretq_s8_u32(aux32x4_2));
+            q3s.val[3] = vmulq_s8(vreinterpretq_s8_u8(vs.val[1]), vreinterpretq_s8_u32(aux32x4_3));
 
             const int32x4_t p1 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), q3s.val[0], q8b.val[0]), q3s.val[1], q8b.val[1]);
             const int32x4_t p2 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), q3s.val[2], q8b.val[2]), q3s.val[3], q8b.val[3]);
+#if QK_K == 256
+            sumi1 += vaddvq_s32(p1) * scales8[ib32/2+0];
+            sumi2 += vaddvq_s32(p2) * scales8[ib32/2+4];
+#else
             sumi1 += vaddvq_s32(p1) * (1 + 2*(x[i].scales[ib32/2] & 0xf));
             sumi2 += vaddvq_s32(p2) * (1 + 2*(x[i].scales[ib32/2] >>  4));
+#endif
         }
         sumf += d*(sumi1 + sumi2);
     }
-    *s = 0.25f * sumf;
+    *s = sumf;
 
 #elif defined(__AVX2__)
 
@@ -10164,6 +9437,16 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
     const __m256i mask1 = _mm256_loadu_si256((const __m256i*)k_mask1);
     const __m256i mask2 = _mm256_loadu_si256((const __m256i*)k_mask2);
 
+    const __m256i idx_shift = _mm256_set_epi32(1, 2, 3, 4, 5, 6, 7, 8);
+    const __m256i idx_mask  = _mm256_set1_epi32(256);
+
+    typedef union {
+        __m256i  vec[2];
+        uint32_t index[16];
+    } index_t;
+
+    index_t idx;
+
     __m256 accumf = _mm256_setzero_ps();
     for (int i = 0; i < nb; ++i) {
         const float d = GGML_FP16_TO_FP32(x[i].d) * y[i].d;
@@ -10176,24 +9459,25 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
         for (int ib32 = 0; ib32 < QK_K/32; ib32 += 2) {
             const __m256i q8_1 = _mm256_loadu_si256((const __m256i *)q8); q8 += 32;
             const __m256i q8_2 = _mm256_loadu_si256((const __m256i *)q8); q8 += 32;
-            const __m256i q2_1 = _mm256_set_epi32(iq3xs_grid[qs[7] | ((qh[ib32+0] << 1) & 256)],
-                                                  iq3xs_grid[qs[6] | ((qh[ib32+0] << 2) & 256)],
-                                                  iq3xs_grid[qs[5] | ((qh[ib32+0] << 3) & 256)],
-                                                  iq3xs_grid[qs[4] | ((qh[ib32+0] << 4) & 256)],
-                                                  iq3xs_grid[qs[3] | ((qh[ib32+0] << 5) & 256)],
-                                                  iq3xs_grid[qs[2] | ((qh[ib32+0] << 6) & 256)],
-                                                  iq3xs_grid[qs[1] | ((qh[ib32+0] << 7) & 256)],
-                                                  iq3xs_grid[qs[0] | ((qh[ib32+0] << 8) & 256)]);
-            qs += 8;
-            const __m256i q2_2 = _mm256_set_epi32(iq3xs_grid[qs[7] | ((qh[ib32+1] << 1) & 256)],
-                                                  iq3xs_grid[qs[6] | ((qh[ib32+1] << 2) & 256)],
-                                                  iq3xs_grid[qs[5] | ((qh[ib32+1] << 3) & 256)],
-                                                  iq3xs_grid[qs[4] | ((qh[ib32+1] << 4) & 256)],
-                                                  iq3xs_grid[qs[3] | ((qh[ib32+1] << 5) & 256)],
-                                                  iq3xs_grid[qs[2] | ((qh[ib32+1] << 6) & 256)],
-                                                  iq3xs_grid[qs[1] | ((qh[ib32+1] << 7) & 256)],
-                                                  iq3xs_grid[qs[0] | ((qh[ib32+1] << 8) & 256)]);
-            qs += 8;
+            const __m256i idx_l = _mm256_cvtepu8_epi16(_mm_loadu_si128((const __m128i *)qs)); qs += 16;
+            idx.vec[0] = _mm256_set1_epi32(qh[ib32+0]);
+            idx.vec[1] = _mm256_set1_epi32(qh[ib32+1]);
+            idx.vec[0] = _mm256_and_si256(_mm256_sllv_epi32(idx.vec[0], idx_shift), idx_mask);
+            idx.vec[1] = _mm256_and_si256(_mm256_sllv_epi32(idx.vec[1], idx_shift), idx_mask);
+            idx.vec[0] = _mm256_or_si256(idx.vec[0], _mm256_cvtepi16_epi32(_mm256_castsi256_si128(idx_l)));
+            idx.vec[1] = _mm256_or_si256(idx.vec[1], _mm256_cvtepi16_epi32(_mm256_extractf128_si256(idx_l, 1)));
+
+            // At leat on my CPU (Ryzen 7950X), using _mm256_i32gather_epi32 is slower than _mm256_set_epi32. Strange.
+            //const __m256i q2_1 = _mm256_i32gather_epi32((const int *)iq3s_grid, idx.vec[0], 4);
+            //const __m256i q2_2 = _mm256_i32gather_epi32((const int *)iq3s_grid, idx.vec[1], 4);
+            const __m256i q2_1 = _mm256_set_epi32(
+                    iq3s_grid[idx.index[7]], iq3s_grid[idx.index[6]], iq3s_grid[idx.index[5]], iq3s_grid[idx.index[4]],
+                    iq3s_grid[idx.index[3]], iq3s_grid[idx.index[2]], iq3s_grid[idx.index[1]], iq3s_grid[idx.index[0]]
+            );
+            const __m256i q2_2 = _mm256_set_epi32(
+                    iq3s_grid[idx.index[15]], iq3s_grid[idx.index[14]], iq3s_grid[idx.index[13]], iq3s_grid[idx.index[12]],
+                    iq3s_grid[idx.index[11]], iq3s_grid[idx.index[10]], iq3s_grid[idx.index[ 9]], iq3s_grid[idx.index[ 8]]
+            );
 
             __m256i aux256 = _mm256_set1_epi32(signs[0] | (signs[1] << 16));
             aux256 = _mm256_and_si256(_mm256_shuffle_epi8(aux256,mask1), mask2);
@@ -10221,7 +9505,7 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
 
     }
 
-    *s = 0.25f * hsum_float_8(accumf);
+    *s = hsum_float_8(accumf);
 
 #else
 
@@ -10238,8 +9522,8 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
             const uint32_t ls2 = 2*(x[i].scales[ib32/2] >>  4) + 1;
             int32_t sumi = 0;
             for (int l = 0; l < 4; ++l) {
-                const uint8_t * grid1 = (const uint8_t *)(iq3xs_grid + (qs[2*l+0] | ((qh[ib32+0] << (8-2*l)) & 256)));
-                const uint8_t * grid2 = (const uint8_t *)(iq3xs_grid + (qs[2*l+1] | ((qh[ib32+0] << (7-2*l)) & 256)));
+                const uint8_t * grid1 = (const uint8_t *)(iq3s_grid + (qs[2*l+0] | ((qh[ib32+0] << (8-2*l)) & 256)));
+                const uint8_t * grid2 = (const uint8_t *)(iq3s_grid + (qs[2*l+1] | ((qh[ib32+0] << (7-2*l)) & 256)));
                 for (int j = 0; j < 4; ++j) {
                     sumi += grid1[j] * q8[j+0] * (signs[l] & kmask_iq2xs[j+0] ? -1 : 1);
                     sumi += grid2[j] * q8[j+4] * (signs[l] & kmask_iq2xs[j+4] ? -1 : 1);
@@ -10251,8 +9535,8 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
             bsum += sumi * ls1;
             sumi = 0;
             for (int l = 0; l < 4; ++l) {
-                const uint8_t * grid1 = (const uint8_t *)(iq3xs_grid + (qs[2*l+0] | ((qh[ib32+1] << (8-2*l)) & 256)));
-                const uint8_t * grid2 = (const uint8_t *)(iq3xs_grid + (qs[2*l+1] | ((qh[ib32+1] << (7-2*l)) & 256)));
+                const uint8_t * grid1 = (const uint8_t *)(iq3s_grid + (qs[2*l+0] | ((qh[ib32+1] << (8-2*l)) & 256)));
+                const uint8_t * grid2 = (const uint8_t *)(iq3s_grid + (qs[2*l+1] | ((qh[ib32+1] << (7-2*l)) & 256)));
                 for (int j = 0; j < 4; ++j) {
                     sumi += grid1[j] * q8[j+0] * (signs[l] & kmask_iq2xs[j+0] ? -1 : 1);
                     sumi += grid2[j] * q8[j+4] * (signs[l] & kmask_iq2xs[j+4] ? -1 : 1);
@@ -10265,7 +9549,7 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
         }
         sumf += d * bsum;
     }
-    *s = 0.25f * sumf;
+    *s = sumf;
 #endif
 }
 
@@ -10278,7 +9562,7 @@ static inline __m256i mul_add_epi8(const __m256i x, const __m256i y) {
 }
 #endif
 
-void ggml_vec_dot_iq1_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc) {
+void ggml_vec_dot_iq1_s_q8_K  (int n, float * restrict s, size_t bs, const void * restrict vx, size_t bx, const void * restrict vy, size_t by, int nrc) {
     assert(n % QK_K == 0);
     assert(nrc == 1);
     UNUSED(nrc);
@@ -10291,155 +9575,119 @@ void ggml_vec_dot_iq1_s_q8_K  (int n, float * GGML_RESTRICT s, size_t bs, const
 
     const int nb = n / QK_K;
 
-    // TODO: implement for QK_K = 64
-#if defined __ARM_NEON && QK_K == 256
-
-    const uint8x16_t m8 = vdupq_n_u8(0x08);
-    const uint8x16_t m7 = vdupq_n_u8(0x07);
-    const uint8x16_t m1 = vdupq_n_u8(0x01);
-    const int32x4_t vzero = vdupq_n_s32(0);
+#if defined __ARM_NEON
 
-    uint16_t gindex[8];
-    uint16x8x2_t vindex;
-    int8x16x4_t q1b;
+    ggml_int8x16x4_t q1b;
     ggml_int8x16x4_t q8b;
-    uint16x8x4_t scales;
-    int32x4x2_t sumi;
-    int32x4x2_t dotq;
 
     float sumf = 0;
     for (int i = 0; i < nb; ++i) {
 
-        const int8_t  * q8 = y[i].qs;
-        const uint8_t * qs = x[i].qs;
-        const uint8_t * sc = x[i].scales;
+        const int8_t   * q8 = y[i].qs;
+        const uint8_t  * qs = x[i].qs;
+        const uint16_t * qh = x[i].qh;
 
-        sumi.val[0] = sumi.val[1] = vzero;
+        int sumi1 = 0, sumi2 = 0, sumi3 = 0;
 
-        for (int i128 = 0; i128 < QK_K/128; ++i128) {
-            const uint8x16_t ql = vld1q_u8(qs); qs += 16;
-            const uint8x8_t tm1 = vld1_u8 (sc); sc +=  8;
-            const uint8x8_t tm2 = vshr_n_u8(tm1, 4);
-            const uint8x16_t qh = vcombine_u8(vzip1_u8(tm1, tm2), vzip2_u8(tm1, tm2));
-            const uint8x16_t hbit = vandq_u8(qh, m8);
-            vindex.val[0] = vorrq_u16(vmovl_u8(vget_low_u8 (ql)), vshlq_n_u16(vmovl_u8(vget_low_u8 (hbit)), 5));
-            vindex.val[1] = vorrq_u16(vmovl_u8(vget_high_u8(ql)), vshlq_n_u16(vmovl_u8(vget_high_u8(hbit)), 5));
-            const uint8x16_t scales8 = vorrq_u8(vshlq_n_u8(vandq_u8(qh, m7), 1), m1);
-            scales.val[0] = vmovl_u8(vget_low_u8 (scales8));
-            scales.val[1] = vmovl_u8(vget_high_u8 (scales8));
+        for (int ib = 0; ib < QK_K/32; ib += 2) {
 
-            for (int l = 0; l < 2; ++l) {
-                vst1q_u16(gindex+0, vindex.val[l]);
-                q1b.val[0] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[0])), vld1_s8((const void *)(iq1s_grid+gindex[1])));
-                q1b.val[1] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[2])), vld1_s8((const void *)(iq1s_grid+gindex[3])));
-                q1b.val[2] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[4])), vld1_s8((const void *)(iq1s_grid+gindex[5])));
-                q1b.val[3] = vcombine_s8(vld1_s8((const void *)(iq1s_grid+gindex[6])), vld1_s8((const void *)(iq1s_grid+gindex[7])));
-                q8b = ggml_vld1q_s8_x4(q8); q8 += 64;
+            q1b.val[0] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[0] | ((qh[ib+0] << 8) & 0x700)))),
+                                     vld1_s8((const int8_t *)(iq1s_grid + (qs[1] | ((qh[ib+0] << 5) & 0x700)))));
+            q1b.val[1] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[2] | ((qh[ib+0] << 2) & 0x700)))),
+                                     vld1_s8((const int8_t *)(iq1s_grid + (qs[3] | ((qh[ib+0] >> 1) & 0x700)))));
+            q1b.val[2] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[4] | ((qh[ib+1] << 8) & 0x700)))),
+                                     vld1_s8((const int8_t *)(iq1s_grid + (qs[5] | ((qh[ib+1] << 5) & 0x700)))));
+            q1b.val[3] = vcombine_s8(vld1_s8((const int8_t *)(iq1s_grid + (qs[6] | ((qh[ib+1] << 2) & 0x700)))),
+                                     vld1_s8((const int8_t *)(iq1s_grid + (qs[7] | ((qh[ib+1] >> 1) & 0x700)))));
+            qs += 8;
 
-                dotq.val[0] = vpaddq_s32(ggml_vdotq_s32(vzero, q1b.val[0], q8b.val[0]), ggml_vdotq_s32(vzero, q1b.val[1], q8b.val[1]));
-                dotq.val[1] = vpaddq_s32(ggml_vdotq_s32(vzero, q1b.val[2], q8b.val[2]), ggml_vdotq_s32(vzero, q1b.val[3], q8b.val[3]));
+            q8b = ggml_vld1q_s8_x4(q8); q8 += 64;
+
+            const int32x4_t p1 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), q1b.val[0], q8b.val[0]), q1b.val[1], q8b.val[1]);
+            const int32x4_t p2 = ggml_vdotq_s32(ggml_vdotq_s32(vdupq_n_s32(0), q1b.val[2], q8b.val[2]), q1b.val[3], q8b.val[3]);
+
+            const int ls1 = 2*((qh[ib+0] >> 12) & 7) + 1;
+            const int ls2 = 2*((qh[ib+1] >> 12) & 7) + 1;
+            sumi1 += vaddvq_s32(p1) * ls1;
+            sumi2 += vaddvq_s32(p2) * ls2;
+            sumi3 += (y[i].bsums[2*ib+0] + y[i].bsums[2*ib+1]) * ls1 * (qh[ib+0] & 0x8000 ? -1 : 1)
+                   + (y[i].bsums[2*ib+2] + y[i].bsums[2*ib+3]) * ls2 * (qh[ib+1] & 0x8000 ? -1 : 1);
 
-                sumi.val[0] = vmlaq_s32(sumi.val[0], dotq.val[0], vreinterpretq_s32_u32(vmovl_u16(vget_low_u16 (scales.val[l]))));
-                sumi.val[1] = vmlaq_s32(sumi.val[1], dotq.val[1], vreinterpretq_s32_u32(vmovl_u16(vget_high_u16(scales.val[l]))));
-            }
         }
 
-        sumf += y[i].d * GGML_FP16_TO_FP32(x[i].d) * vaddvq_s32(vaddq_s32(sumi.val[0], sumi.val[1]));
+        sumf += y[i].d * GGML_FP16_TO_FP32(x[i].d) * (sumi1 + sumi2 + IQ1S_DELTA * sumi3);
     }
 
     *s = sumf;
 
-    // TODO: implement for QK_K = 64
-#elif defined __AVX2__ && QK_K == 256
-
-    const __m128i m8 = _mm_set1_epi8(0x08);
-    const __m128i m7 = _mm_set1_epi8(0x07);
-    const __m128i m1 = _mm_set1_epi8(0x01);
-    const __m128i shuffle_h = _mm_set_epi8(15, 7, 14, 6, 13, 5, 12, 4, 11, 3, 10, 2, 9, 1, 8, 0);
-    const __m128i shuffle_s[4] = {
-        _mm_set_epi32(0x03030303, 0x02020202, 0x01010101, 0x00000000),
-        _mm_set_epi32(0x07070707, 0x06060606, 0x05050505, 0x04040404),
-        _mm_set_epi32(0x0b0b0b0b, 0x0a0a0a0a, 0x09090909, 0x08080808),
-        _mm_set_epi32(0x0f0f0f0f, 0x0e0e0e0e, 0x0d0d0d0d, 0x0c0c0c0c)
-    };
-
-    uint64_t aux64;
-
-    typedef union m256i_uint16 {
-        __m256i reg;
-        uint16_t s[16];
-    } m256i_uint16_t;
-
-    m256i_uint16_t v_gindex;
+#elif defined __AVX2__
 
     __m256 accum = _mm256_setzero_ps();
+    float accum1 = 0;
     for (int i = 0; i < nb; ++i) {
 
-        const int8_t  * q8 = y[i].qs;
-        const uint8_t * qs = x[i].qs;
-        const uint8_t * sc = x[i].scales;
+        const int8_t   * q8 = y[i].qs;
+        const uint8_t  * qs = x[i].qs;
+        const uint16_t * qh = x[i].qh;
 
         __m256i sumi = _mm256_setzero_si256();
-        for (int i128 = 0; i128 < QK_K/128; ++i128) {
-            const __m128i ql = _mm_loadu_si128((const __m128i*)qs); qs += 16;
-            memcpy(&aux64, sc, 8); sc += 8;
-            const __m128i qh = _mm_shuffle_epi8(_mm_set_epi64x(aux64 >> 4, aux64), shuffle_h);
-            const __m256i hbit = _mm256_cvtepu8_epi16(_mm_and_si128(qh, m8));
-            v_gindex.reg = _mm256_or_si256(_mm256_cvtepu8_epi16(ql), _mm256_slli_epi16(hbit, 5));
-            const __m128i scales = _mm_or_si128(_mm_slli_epi16(_mm_and_si128(qh, m7), 1), m1);
+        int sumi1 = 0;
+        for (int ib = 0; ib < QK_K/32; ib += 2) {
+            const __m256i q1b_1 = _mm256_set_epi64x(iq1s_grid[qs[3] | ((qh[ib+0] >> 1) & 0x700)], iq1s_grid[qs[2] | ((qh[ib+0] << 2) & 0x700)],
+                                                    iq1s_grid[qs[1] | ((qh[ib+0] << 5) & 0x700)], iq1s_grid[qs[0] | ((qh[ib+0] << 8) & 0x700)]);
+            const __m256i q1b_2 = _mm256_set_epi64x(iq1s_grid[qs[7] | ((qh[ib+1] >> 1) & 0x700)], iq1s_grid[qs[6] | ((qh[ib+1] << 2) & 0x700)],
+                                                    iq1s_grid[qs[5] | ((qh[ib+1] << 5) & 0x700)], iq1s_grid[qs[4] | ((qh[ib+1] << 8) & 0x700)]);
+            qs += 8;
+            const __m256i q8b_1 = _mm256_loadu_si256((const __m256i*)q8); q8 += 32;
+            const __m256i q8b_2 = _mm256_loadu_si256((const __m256i*)q8); q8 += 32;
 
-            for (int i32 = 0; i32 < 4; ++i32) {
-                const __m256i q8b = _mm256_loadu_si256((const __m256i*)q8); q8 += 32;
-                const __m256i q1b = _mm256_set_epi64x(iq1s_grid[v_gindex.s[4*i32+3]], iq1s_grid[v_gindex.s[4*i32+2]],
-                                                      iq1s_grid[v_gindex.s[4*i32+1]], iq1s_grid[v_gindex.s[4*i32+0]]);
-                const __m256i dot = mul_add_epi8(q1b, q8b);
-                const __m256i s16 = _mm256_cvtepi8_epi16(_mm_shuffle_epi8(scales, shuffle_s[i32]));
-                const __m256i p   = _mm256_madd_epi16(s16, dot);
-                sumi = _mm256_add_epi32(sumi, p);
-            }
+            const __m256i dot1 = mul_add_epi8(q1b_1, q8b_1);
+            const __m256i dot2 = mul_add_epi8(q1b_2, q8b_2);
+            const int16_t ls1 = 2*((qh[ib+0] >> 12) & 7) + 1;
+            const int16_t ls2 = 2*((qh[ib+1] >> 12) & 7) + 1;
+            const __m256i p1 = _mm256_madd_epi16(dot1, _mm256_set1_epi16(ls1));
+            const __m256i p2 = _mm256_madd_epi16(dot2, _mm256_set1_epi16(ls2));
 
+            sumi = _mm256_add_epi32(sumi, _mm256_add_epi32(p1, p2));
+            sumi1 += (y[i].bsums[2*ib+0] + y[i].bsums[2*ib+1]) * (qh[ib+0] & 0x8000 ? -1 : 1) * ls1
+                   + (y[i].bsums[2*ib+2] + y[i].bsums[2*ib+3]) * (qh[ib+1] & 0x8000 ? -1 : 1) * ls2;
         }
 
-        accum = _mm256_fmadd_ps(_mm256_set1_ps(y[i].d * GGML_FP16_TO_FP32(x[i].d)), _mm256_cvtepi32_ps(sumi), accum);
+        const float d = y[i].d * GGML_FP16_TO_FP32(x[i].d);
+        accum = _mm256_fmadd_ps(_mm256_set1_ps(d), _mm256_cvtepi32_ps(sumi), accum);
+        accum1 += d * sumi1;
 
     }
 
-    *s = hsum_float_8(accum);
+    *s = hsum_float_8(accum) + IQ1S_DELTA * accum1;
 
 #else
 
-    int db[4];
-    uint16_t idx[4];
-
     float sumf = 0;
-    for (int i = 0; i < nb; ++i) {
+    for (int i = 0; i < nb; i++) {
 
-        const int8_t  * q8 = y[i].qs;
-        const uint8_t * qs = x[i].qs;
-        const uint8_t * sc = x[i].scales;
+        const int8_t   * q8 = y[i].qs;
+        const uint8_t  * qs = x[i].qs;
+        const uint16_t * qh = x[i].qh;
 
-        int sumi = 0;
-        for (int i32 = 0; i32 < QK_K/32; ++i32) {
-            idx[0] = qs[0] | ((sc[0] & 0x08) << 5);
-            idx[1] = qs[1] | ((sc[0] & 0x80) << 1);
-            idx[2] = qs[2] | ((sc[1] & 0x08) << 5);
-            idx[3] = qs[3] | ((sc[1] & 0x80) << 1);
-            db[0] = (2*(sc[0] & 7) + 1);
-            db[1] = (2*((sc[0] >> 4) & 7) + 1);
-            db[2] = (2*(sc[1] & 7) + 1);
-            db[3] = (2*((sc[1] >> 4) & 7) + 1);
+        int sumi = 0, sumi1 = 0;
+        for (int ib = 0; ib < QK_K/32; ++ib) {
+            const int ls = 2*((qh[ib] >> 12) & 7) + 1;
+            const int delta = qh[ib] & 0x8000 ? -1 : 1;
+            int lsum = 0;
             for (int l = 0; l < 4; ++l) {
-                const int8_t * grid = (const int8_t *)(iq1s_grid + idx[l]);
-                int suml = 0;
-                for (int j = 0; j < 8; ++j) suml += q8[j] * grid[j];
-                sumi += db[l] * suml;
+                const int8_t * grid = (const int8_t *)(iq1s_grid + (qs[l] | (((qh[ib] >> 3*l) & 7) << 8)));
+                for (int j = 0; j < 8; ++j) {
+                    lsum += q8[j] * grid[j];
+                }
                 q8 += 8;
             }
+            sumi  += ls * lsum;
+            sumi1 += ls * delta * (y[i].bsums[2*ib+0] + y[i].bsums[2*ib+1]);
             qs += 4;
-            sc += 2;
         }
 
-        sumf += GGML_FP16_TO_FP32(x[i].d) * y[i].d * sumi;
+        sumf += GGML_FP16_TO_FP32(x[i].d) * y[i].d * (sumi + IQ1S_DELTA * sumi1);
     }
 
     *s = sumf;
@@ -10508,10 +9756,10 @@ void ggml_vec_dot_iq4_nl_q8_0(int n, float * restrict s, size_t bs, const void *
         const __m128i q4bits_2 = _mm_loadu_si128((const __m128i*)x[1].qs);
         const __m256i q8b_1 = _mm256_loadu_si256((const __m256i *)y[0].qs);
         const __m256i q8b_2 = _mm256_loadu_si256((const __m256i *)y[1].qs);
-        const __m256i q4b_1 = _mm256_set_m128i(_mm_shuffle_epi8(values128, _mm_and_si128(_mm_srli_epi16(q4bits_1, 4), m4b)),
-                                               _mm_shuffle_epi8(values128, _mm_and_si128(q4bits_1, m4b)));
-        const __m256i q4b_2 = _mm256_set_m128i(_mm_shuffle_epi8(values128, _mm_and_si128(_mm_srli_epi16(q4bits_2, 4), m4b)),
-                                               _mm_shuffle_epi8(values128, _mm_and_si128(q4bits_2, m4b)));
+        const __m256i q4b_1 = MM256_SET_M128I(_mm_shuffle_epi8(values128, _mm_and_si128(_mm_srli_epi16(q4bits_1, 4), m4b)),
+                                              _mm_shuffle_epi8(values128, _mm_and_si128(q4bits_1, m4b)));
+        const __m256i q4b_2 = MM256_SET_M128I(_mm_shuffle_epi8(values128, _mm_and_si128(_mm_srli_epi16(q4bits_2, 4), m4b)),
+                                              _mm_shuffle_epi8(values128, _mm_and_si128(q4bits_2, m4b)));
         const __m256i p16_1 = mul_add_epi8(q4b_1, q8b_1);
         const __m256i p16_2 = mul_add_epi8(q4b_2, q8b_2);
         const __m256i p_1 = _mm256_madd_epi16(p16_1, mone);
@@ -10618,10 +9866,10 @@ void ggml_vec_dot_iq4_xs_q8_K(int n, float * restrict s, size_t bs, const void *
             const __m128i q4bits_2 = _mm_loadu_si128((const __m128i*)qs);  qs += 16;
             const __m256i q8b_1 = _mm256_loadu_si256((const __m256i *)q8); q8 += 32;
             const __m256i q8b_2 = _mm256_loadu_si256((const __m256i *)q8); q8 += 32;
-            const __m256i q4b_1 = _mm256_set_m128i(_mm_shuffle_epi8(values128, _mm_and_si128(_mm_srli_epi16(q4bits_1, 4), m4b)),
-                                                   _mm_shuffle_epi8(values128, _mm_and_si128(q4bits_1, m4b)));
-            const __m256i q4b_2 = _mm256_set_m128i(_mm_shuffle_epi8(values128, _mm_and_si128(_mm_srli_epi16(q4bits_2, 4), m4b)),
-                                                   _mm_shuffle_epi8(values128, _mm_and_si128(q4bits_2, m4b)));
+            const __m256i q4b_1 = MM256_SET_M128I(_mm_shuffle_epi8(values128, _mm_and_si128(_mm_srli_epi16(q4bits_1, 4), m4b)),
+                                                  _mm_shuffle_epi8(values128, _mm_and_si128(q4bits_1, m4b)));
+            const __m256i q4b_2 = MM256_SET_M128I(_mm_shuffle_epi8(values128, _mm_and_si128(_mm_srli_epi16(q4bits_2, 4), m4b)),
+                                                  _mm_shuffle_epi8(values128, _mm_and_si128(q4bits_2, m4b)));
             const __m256i p16_1 = mul_add_epi8(q4b_1, q8b_1);
             const __m256i p16_2 = mul_add_epi8(q4b_2, q8b_2);
             const int16_t ls1 = ((x[ibl].scales_l[ib/2] & 0xf) | ((sh << 4) & 0x30)) - 32;
@@ -10700,7 +9948,7 @@ static inline int iq2_grid_size(enum ggml_type type) {
     GGML_ASSERT(type == GGML_TYPE_IQ2_XXS || type == GGML_TYPE_IQ2_XS || type == GGML_TYPE_IQ1_S || type == GGML_TYPE_IQ2_S);
     return type == GGML_TYPE_IQ2_XXS ? 256 :
            type == GGML_TYPE_IQ2_XS  ? 512 :
-           type == GGML_TYPE_IQ1_S   ? 512 : 1024;
+           type == GGML_TYPE_IQ1_S   ? NGRID_IQ1S : 1024;
 }
 
 static int iq2_compare_func(const void * left, const void * right) {
@@ -10767,39 +10015,135 @@ void iq2xs_init_impl(enum ggml_type type) {
         40962, 40968, 40970, 40992, 41002, 41120, 41297, 41305, 41382, 41472, 41474, 41480, 41514, 41600, 41632, 42048,
         42133, 42597, 42648, 43018, 43040, 43042, 43048, 43168, 43176, 43268, 43396, 43398, 43560, 43562, 43665, 43690,
     };
-    static const uint16_t kgrid_1bit_512[512] = {
-           10,    33,    41,    85,   132,   134,   160,   162,   277,   337,   340,   345,   357,   405,   516,   545,
-          553,   598,   641,   650,   681,  1042,  1044,  1097,  1169,  1176,  1320,  1345,  1365,  1378,  1434,  1444,
-         1545,  1617,  1642,  1685,  2053,  2080,  2089,  2133,  2176,  2182,  2208,  2214,  2306,  2384,  2393,  2440,
-         2453,  2581,  2664,  2690,  2721,  4117,  4161,  4182,  4184,  4261,  4357,  4369,  4372,  4377,  4390,  4422,
-         4432,  4437,  4449,  4457,  4485,  4497,  4505,  4629,  4677,  4696,  4774,  5205,  5217,  5225,  5386,  5397,
-         5409,  5445,  5457,  5460,  5461,  5462,  5465,  5472,  5477,  5525,  5545,  5650,  5668,  5717,  5729,  5769,
-         5777,  6212,  6234,  6244,  6293,  6424,  6482,  6485,  6502,  6505,  6529,  6538,  6565,  6656,  6682,  6788,
-         6806,  6820,  8218,  8224,  8226,  8232,  8277,  8326,  8354,  8469,  8521,  8530,  8549,  8596,  8737,  8794,
-         9221,  9253,  9348,  9369,  9380,  9474,  9557,  9633,  9732,  9753,  9793,  9830,  9862,  9880, 10240, 10272,
-        10282, 10321, 10406, 10517, 10530, 10566, 10585, 10645, 10896, 16466, 16468, 16473, 16485, 16646, 16660, 16665,
-        16725, 16793, 16806, 16914, 16969, 16977, 16996, 17028, 17057, 17408, 17416, 17434, 17493, 17512, 17578, 17685,
-        17696, 17733, 17745, 17748, 17749, 17750, 17753, 17765, 17794, 17813, 17946, 17984, 18005, 18072, 18453, 18529,
-        18569, 18722, 18756, 18762, 18773, 18794, 18833, 18853, 18945, 19026, 19033, 19077, 20489, 20497, 20500, 20517,
-        20565, 20586, 20610, 20633, 20757, 20769, 20776, 20805, 20817, 20820, 20821, 20822, 20825, 20837, 20864, 20872,
-        20885, 20896, 21002, 21029, 21077, 21146, 21510, 21525, 21573, 21585, 21588, 21589, 21590, 21593, 21605, 21653,
-        21665, 21765, 21777, 21780, 21781, 21782, 21785, 21797, 21825, 21828, 21829, 21830, 21833, 21840, 21841, 21842,
-        21844, 21846, 21848, 21849, 21850, 21857, 21860, 21861, 21862, 21865, 21893, 21905, 21908, 21909, 21910, 21913,
-        21925, 22024, 22037, 22085, 22097, 22100, 22101, 22102, 22105, 22117, 22165, 22545, 22566, 22568, 22594, 22608,
-        22613, 22676, 22697, 22793, 22805, 22853, 22865, 22868, 22869, 22870, 22873, 22885, 22933, 22946, 23046, 23072,
-        23125, 23209, 24597, 24640, 24665, 24673, 24725, 24833, 24840, 24869, 24917, 24934, 24965, 25001, 25108, 25110,
-        25152, 25184, 25192, 25234, 25616, 25618, 25625, 25685, 25704, 25738, 25744, 25770, 25877, 25897, 25925, 25937,
-        25940, 25941, 25942, 25945, 25957, 25986, 26005, 26186, 26197, 26276, 26632, 26634, 26725, 26757, 26770, 26885,
-        26965, 26976, 26986, 27032, 27153, 27174, 27200, 27208, 27240, 27269, 27282, 27290, 32778, 32800, 32802, 32808,
-        32810, 32853, 32904, 32922, 32930, 32932, 33105, 33110, 33112, 33125, 33157, 33280, 33288, 33301, 33312, 33320,
-        33424, 33797, 33829, 33858, 34068, 34133, 34146, 34176, 34217, 34306, 34342, 34441, 34454, 34468, 34832, 34918,
-        34965, 34984, 35094, 35137, 35161, 35208, 35232, 35332, 35338, 35368, 35429, 36932, 36934, 36953, 37009, 37125,
-        37136, 37138, 37145, 37157, 37205, 37220, 37258, 37290, 37444, 37446, 37465, 37478, 37525, 37905, 37968, 37973,
-        38040, 38054, 38145, 38154, 38165, 38180, 38186, 38213, 38225, 38228, 38229, 38230, 38233, 38245, 38293, 38485,
-        38504, 38530, 38938, 38985, 38993, 39012, 39040, 39173, 39192, 39253, 39265, 39301, 39316, 39322, 39442, 39497,
-        39504, 39590, 40970, 40984, 40992, 41002, 41045, 41120, 41128, 41237, 41289, 41297, 41317, 41364, 41366, 41514,
-        41557, 41633, 41989, 42021, 42056, 42068, 42074, 42113, 42242, 42265, 42274, 42325, 42340, 42402, 42501, 42512,
-        42533, 42624, 42632, 42666, 43040, 43093, 43106, 43168, 43176, 43264, 43286, 43345, 43429, 43590, 43618, 43680,
+    static const uint16_t kgrid_1bit_2048[NGRID_IQ1S] = {
+            0,     2,     5,     8,    10,    17,    21,    32,    34,    40,    42,    69,    81,    84,    86,   101,
+          128,   130,   136,   138,   149,   160,   162,   168,   170,   260,   261,   273,   276,   278,   281,   282,
+          293,   321,   326,   329,   338,   341,   346,   353,   356,   358,   360,   389,   401,   404,   406,   421,
+          512,   514,   520,   522,   533,   544,   546,   552,   554,   581,   593,   601,   612,   617,   640,   642,
+          648,   650,   657,   661,   665,   672,   674,   680,   682,  1041,  1044,  1046,  1061,  1089,  1097,  1109,
+         1114,  1124,  1125,  1169,  1177,  1189,  1281,  1284,  1285,  1286,  1301,  1304,  1306,  1321,  1344,  1349,
+         1354,  1360,  1361,  1364,  1365,  1366,  1369,  1376,  1378,  1381,  1384,  1386,  1409,  1425,  1429,  1432,
+         1434,  1441,  1444,  1445,  1446,  1449,  1556,  1561,  1601,  1604,  1616,  1618,  1621,  1624,  1632,  1633,
+         1638,  1641,  1669,  1681,  1684,  1689,  2048,  2050,  2056,  2058,  2069,  2080,  2082,  2088,  2090,  2117,
+         2129,  2134,  2149,  2176,  2178,  2184,  2186,  2197,  2208,  2210,  2216,  2218,  2309,  2321,  2324,  2329,
+         2340,  2341,  2369,  2384,  2385,  2389,  2401,  2404,  2409,  2449,  2452,  2454,  2457,  2469,  2560,  2562,
+         2568,  2570,  2581,  2592,  2594,  2600,  2602,  2629,  2641,  2649,  2657,  2661,  2688,  2690,  2693,  2696,
+         2698,  2709,  2720,  2722,  2728,  2730,  4112,  4113,  4116,  4121,  4132,  4133,  4161,  4164,  4176,  4181,
+         4184,  4193,  4196,  4197,  4201,  4241,  4244,  4246,  4257,  4261,  4353,  4356,  4358,  4361,  4368,  4370,
+         4373,  4376,  4385,  4388,  4393,  4421,  4426,  4432,  4433,  4434,  4436,  4437,  4438,  4441,  4448,  4453,
+         4484,  4498,  4501,  4513,  4516,  4625,  4628,  4630,  4645,  4672,  4678,  4681,  4690,  4693,  4696,  4698,
+         4708,  4710,  4741,  4753,  4756,  4758,  4773,  5121,  5126,  5129,  5140,  5141,  5144,  5145,  5153,  5158,
+         5185,  5189,  5190,  5192,  5194,  5201,  5204,  5205,  5206,  5209,  5218,  5221,  5224,  5252,  5257,  5264,
+         5268,  5269,  5272,  5273,  5274,  5281,  5284,  5285,  5289,  5378,  5381,  5386,  5393,  5396,  5397,  5398,
+         5401,  5408,  5410,  5413,  5416,  5418,  5441,  5444,  5445,  5446,  5457,  5458,  5460,  5461,  5462,  5465,
+         5466,  5473,  5476,  5477,  5478,  5481,  5504,  5506,  5508,  5509,  5512,  5514,  5520,  5521,  5524,  5525,
+         5526,  5529,  5530,  5536,  5538,  5541,  5633,  5636,  5637,  5638,  5653,  5654,  5656,  5658,  5665,  5670,
+         5696,  5698,  5700,  5701,  5704,  5706,  5713,  5717,  5718,  5720,  5721,  5729,  5732,  5733,  5736,  5737,
+         5738,  5766,  5770,  5778,  5781,  5796,  5801,  6161,  6166,  6181,  6209,  6212,  6214,  6217,  6224,  6229,
+         6232,  6234,  6240,  6241,  6244,  6246,  6249,  6277,  6289,  6292,  6309,  6416,  6418,  6421,  6426,  6433,
+         6437,  6466,  6468,  6469,  6472,  6481,  6484,  6485,  6486,  6489,  6490,  6496,  6501,  6506,  6537,  6545,
+         6546,  6549,  6552,  6561,  6566,  6569,  6665,  6678,  6692,  6694,  6724,  6726,  6729,  6736,  6738,  6741,
+         6744,  6753,  6758,  6761,  6789,  6801,  6806,  6810,  8192,  8194,  8200,  8202,  8213,  8224,  8226,  8229,
+         8232,  8234,  8261,  8273,  8281,  8289,  8293,  8320,  8322,  8328,  8330,  8341,  8352,  8354,  8357,  8360,
+         8362,  8453,  8465,  8468,  8473,  8485,  8514,  8516,  8521,  8533,  8536,  8538,  8545,  8548,  8549,  8550,
+         8581,  8592,  8598,  8601,  8613,  8705,  8712,  8714,  8721,  8725,  8736,  8738,  8744,  8746,  8773,  8785,
+         8790,  8793,  8805,  8833,  8840,  8842,  8849,  8853,  8864,  8866,  8872,  8874,  9221,  9236,  9238,  9241,
+         9253,  9284,  9285,  9286,  9289,  9298,  9301,  9304,  9306,  9318,  9349,  9361,  9364,  9369,  9377,  9381,
+         9481,  9493,  9505,  9513,  9536,  9541,  9544,  9553,  9556,  9557,  9561,  9570,  9573,  9576,  9609,  9616,
+         9620,  9621,  9624,  9626,  9633,  9636,  9638,  9641,  9733,  9744,  9746,  9753,  9765,  9793,  9801,  9813,
+         9824,  9825,  9833,  9860,  9862,  9872,  9882, 10240, 10242, 10248, 10250, 10261, 10272, 10274, 10280, 10282,
+        10309, 10321, 10324, 10341, 10368, 10370, 10376, 10378, 10400, 10402, 10408, 10410, 10505, 10513, 10516, 10521,
+        10533, 10566, 10569, 10578, 10581, 10593, 10596, 10598, 10601, 10629, 10640, 10646, 10649, 10660, 10661, 10752,
+        10754, 10760, 10762, 10784, 10786, 10792, 10794, 10821, 10833, 10838, 10841, 10853, 10880, 10882, 10888, 10890,
+        10901, 10912, 10914, 10920, 10922, 16389, 16401, 16406, 16421, 16457, 16466, 16469, 16472, 16474, 16481, 16484,
+        16486, 16532, 16537, 16545, 16550, 16640, 16641, 16644, 16646, 16649, 16658, 16661, 16662, 16664, 16666, 16673,
+        16678, 16681, 16709, 16712, 16714, 16721, 16724, 16725, 16726, 16729, 16730, 16741, 16744, 16746, 16769, 16772,
+        16774, 16784, 16786, 16789, 16800, 16801, 16802, 16901, 16913, 16916, 16918, 16933, 16961, 16978, 16981, 16986,
+        16996, 17001, 17033, 17044, 17061, 17409, 17429, 17433, 17449, 17477, 17480, 17482, 17489, 17492, 17493, 17494,
+        17505, 17506, 17509, 17512, 17514, 17537, 17542, 17545, 17552, 17554, 17557, 17568, 17569, 17577, 17665, 17666,
+        17669, 17674, 17681, 17684, 17685, 17686, 17689, 17696, 17701, 17706, 17729, 17732, 17733, 17734, 17737, 17744,
+        17745, 17748, 17749, 17750, 17752, 17753, 17761, 17764, 17765, 17766, 17769, 17794, 17796, 17797, 17800, 17809,
+        17812, 17813, 17814, 17817, 17818, 17829, 17832, 17834, 17921, 17925, 17929, 17940, 17941, 17944, 17946, 17953,
+        17956, 17961, 17984, 17986, 17989, 17992, 18000, 18001, 18002, 18005, 18006, 18009, 18018, 18021, 18024, 18049,
+        18053, 18058, 18068, 18069, 18081, 18084, 18086, 18437, 18449, 18453, 18458, 18469, 18498, 18505, 18512, 18517,
+        18520, 18529, 18532, 18534, 18537, 18565, 18577, 18580, 18582, 18585, 18597, 18689, 18693, 18694, 18698, 18704,
+        18708, 18709, 18712, 18721, 18724, 18726, 18752, 18757, 18762, 18769, 18770, 18772, 18773, 18774, 18777, 18784,
+        18786, 18789, 18790, 18794, 18822, 18825, 18834, 18837, 18838, 18840, 18849, 18852, 18854, 18857, 18966, 19012,
+        19014, 19017, 19029, 19032, 19034, 19044, 19049, 19092, 19109, 20481, 20484, 20485, 20486, 20489, 20498, 20501,
+        20506, 20513, 20516, 20521, 20544, 20549, 20552, 20561, 20564, 20565, 20566, 20569, 20581, 20584, 20614, 20617,
+        20629, 20632, 20640, 20641, 20646, 20649, 20741, 20744, 20745, 20746, 20753, 20756, 20757, 20758, 20760, 20761,
+        20768, 20773, 20774, 20776, 20778, 20801, 20804, 20805, 20806, 20809, 20816, 20817, 20818, 20820, 20821, 20822,
+        20824, 20825, 20826, 20833, 20836, 20837, 20838, 20841, 20866, 20869, 20881, 20884, 20885, 20886, 20889, 20896,
+        20901, 20906, 20993, 20998, 21010, 21013, 21018, 21025, 21028, 21058, 21061, 21066, 21073, 21076, 21077, 21078,
+        21081, 21090, 21093, 21125, 21136, 21138, 21141, 21145, 21146, 21156, 21508, 21509, 21521, 21524, 21525, 21526,
+        21528, 21529, 21537, 21541, 21544, 21546, 21569, 21572, 21573, 21574, 21577, 21578, 21584, 21585, 21588, 21589,
+        21590, 21592, 21593, 21594, 21601, 21602, 21604, 21605, 21606, 21609, 21632, 21640, 21642, 21649, 21652, 21653,
+        21654, 21657, 21665, 21668, 21669, 21674, 21761, 21762, 21764, 21765, 21766, 21769, 21776, 21777, 21778, 21780,
+        21781, 21782, 21785, 21786, 21793, 21796, 21797, 21798, 21801, 21824, 21825, 21826, 21828, 21829, 21830, 21832,
+        21833, 21840, 21841, 21842, 21844, 21845, 21846, 21848, 21849, 21850, 21856, 21857, 21860, 21861, 21862, 21864,
+        21865, 21866, 21889, 21892, 21893, 21897, 21898, 21904, 21905, 21908, 21909, 21910, 21912, 21913, 21921, 21924,
+        21925, 21926, 21929, 22016, 22017, 22018, 22020, 22022, 22024, 22025, 22033, 22036, 22037, 22040, 22041, 22048,
+        22049, 22050, 22052, 22053, 22054, 22056, 22057, 22081, 22085, 22086, 22088, 22089, 22090, 22096, 22097, 22098,
+        22100, 22101, 22102, 22104, 22105, 22106, 22113, 22116, 22117, 22121, 22146, 22149, 22150, 22152, 22153, 22154,
+        22161, 22165, 22170, 22178, 22181, 22182, 22184, 22185, 22532, 22533, 22534, 22537, 22544, 22549, 22552, 22561,
+        22570, 22597, 22600, 22602, 22609, 22612, 22613, 22614, 22616, 22617, 22624, 22626, 22628, 22629, 22658, 22665,
+        22672, 22674, 22677, 22680, 22689, 22697, 22785, 22786, 22789, 22794, 22801, 22804, 22805, 22806, 22809, 22821,
+        22849, 22852, 22853, 22854, 22857, 22864, 22865, 22866, 22868, 22869, 22870, 22872, 22873, 22874, 22881, 22884,
+        22885, 22886, 22889, 22913, 22917, 22921, 22929, 22932, 22933, 22934, 22936, 22937, 22949, 23044, 23048, 23061,
+        23066, 23072, 23077, 23078, 23081, 23109, 23112, 23113, 23121, 23125, 23126, 23128, 23129, 23138, 23141, 23144,
+        23146, 23169, 23178, 23186, 23189, 23190, 23192, 23194, 23201, 24581, 24596, 24598, 24601, 24613, 24644, 24656,
+        24661, 24662, 24664, 24666, 24673, 24676, 24678, 24681, 24705, 24726, 24741, 24833, 24836, 24838, 24841, 24850,
+        24853, 24865, 24866, 24870, 24873, 24901, 24905, 24913, 24917, 24918, 24921, 24933, 24934, 24938, 24964, 24970,
+        24978, 24981, 24993, 24998, 25001, 25105, 25110, 25113, 25152, 25153, 25158, 25173, 25174, 25176, 25184, 25221,
+        25233, 25238, 25253, 25617, 25618, 25621, 25622, 25626, 25633, 25638, 25641, 25664, 25666, 25669, 25672, 25674,
+        25681, 25684, 25685, 25686, 25689, 25690, 25696, 25698, 25701, 25732, 25733, 25737, 25744, 25746, 25748, 25749,
+        25750, 25752, 25754, 25761, 25764, 25769, 25861, 25864, 25866, 25873, 25877, 25878, 25881, 25924, 25925, 25926,
+        25929, 25936, 25937, 25940, 25941, 25942, 25945, 25953, 25956, 25957, 25958, 25961, 25990, 25993, 25994, 26001,
+        26005, 26006, 26009, 26010, 26018, 26021, 26022, 26024, 26114, 26121, 26133, 26144, 26150, 26152, 26153, 26176,
+        26181, 26184, 26186, 26193, 26196, 26197, 26198, 26200, 26202, 26208, 26213, 26216, 26240, 26242, 26245, 26250,
+        26260, 26262, 26264, 26265, 26272, 26276, 26278, 26282, 26646, 26649, 26661, 26689, 26706, 26709, 26714, 26721,
+        26729, 26757, 26769, 26776, 26790, 26881, 26884, 26896, 26901, 26913, 26916, 26918, 26921, 26944, 26945, 26949,
+        26950, 26952, 26961, 26964, 26965, 26966, 26969, 26976, 26981, 26986, 27010, 27012, 27018, 27029, 27041, 27044,
+        27045, 27049, 27153, 27158, 27160, 27201, 27204, 27209, 27216, 27221, 27224, 27226, 27236, 27237, 27241, 27270,
+        27284, 27288, 27290, 27302, 32768, 32770, 32776, 32778, 32800, 32802, 32808, 32810, 32837, 32848, 32849, 32852,
+        32854, 32857, 32869, 32896, 32898, 32904, 32906, 32917, 32928, 32930, 32936, 32938, 33029, 33041, 33044, 33046,
+        33049, 33061, 33089, 33092, 33097, 33104, 33106, 33109, 33110, 33112, 33113, 33124, 33126, 33129, 33157, 33161,
+        33172, 33174, 33177, 33189, 33280, 33282, 33288, 33290, 33301, 33312, 33314, 33320, 33322, 33361, 33364, 33369,
+        33381, 33408, 33410, 33416, 33418, 33429, 33440, 33442, 33448, 33450, 33812, 33817, 33857, 33860, 33873, 33877,
+        33882, 33889, 33892, 33897, 33940, 33945, 34049, 34057, 34066, 34069, 34074, 34086, 34089, 34112, 34113, 34117,
+        34120, 34129, 34132, 34133, 34134, 34137, 34138, 34149, 34150, 34152, 34154, 34177, 34180, 34182, 34185, 34192,
+        34194, 34197, 34200, 34214, 34321, 34326, 34329, 34341, 34369, 34372, 34377, 34378, 34384, 34389, 34393, 34394,
+        34401, 34406, 34410, 34437, 34449, 34458, 34468, 34816, 34818, 34824, 34826, 34837, 34848, 34850, 34856, 34858,
+        34881, 34885, 34897, 34900, 34905, 34917, 34921, 34944, 34946, 34952, 34954, 34965, 34976, 34978, 34984, 34986,
+        35077, 35078, 35089, 35092, 35094, 35109, 35137, 35140, 35142, 35145, 35152, 35154, 35157, 35162, 35169, 35172,
+        35205, 35222, 35225, 35237, 35328, 35330, 35336, 35338, 35349, 35360, 35362, 35368, 35370, 35397, 35409, 35412,
+        35414, 35456, 35458, 35464, 35466, 35477, 35488, 35490, 35496, 35498, 36869, 36881, 36886, 36888, 36889, 36901,
+        36929, 36934, 36937, 36949, 36952, 36954, 36969, 36970, 36997, 37009, 37012, 37014, 37017, 37029, 37121, 37124,
+        37126, 37129, 37136, 37141, 37144, 37146, 37153, 37156, 37158, 37161, 37184, 37189, 37200, 37201, 37204, 37205,
+        37206, 37209, 37218, 37221, 37252, 37254, 37266, 37269, 37272, 37281, 37284, 37286, 37289, 37381, 37393, 37396,
+        37401, 37413, 37444, 37446, 37449, 37456, 37458, 37461, 37464, 37478, 37481, 37509, 37524, 37526, 37545, 37889,
+        37892, 37894, 37904, 37909, 37912, 37926, 37952, 37962, 37969, 37972, 37973, 37974, 37976, 37977, 37984, 37985,
+        37986, 37989, 38020, 38022, 38034, 38036, 38037, 38040, 38049, 38057, 38144, 38149, 38152, 38154, 38160, 38161,
+        38164, 38165, 38166, 38169, 38177, 38181, 38185, 38186, 38209, 38212, 38213, 38214, 38217, 38224, 38225, 38226,
+        38228, 38229, 38230, 38232, 38233, 38234, 38241, 38244, 38245, 38246, 38249, 38273, 38277, 38280, 38289, 38290,
+        38292, 38293, 38294, 38297, 38298, 38304, 38306, 38309, 38312, 38314, 38401, 38404, 38416, 38421, 38425, 38432,
+        38438, 38441, 38469, 38472, 38473, 38481, 38482, 38485, 38486, 38489, 38501, 38504, 38530, 38532, 38537, 38538,
+        38546, 38548, 38549, 38564, 38566, 38569, 38917, 38934, 38937, 38949, 38977, 38982, 38992, 38994, 38997, 38998,
+        39002, 39012, 39013, 39045, 39057, 39062, 39065, 39077, 39172, 39174, 39177, 39184, 39186, 39189, 39192, 39194,
+        39200, 39201, 39204, 39206, 39232, 39234, 39237, 39240, 39242, 39249, 39252, 39253, 39254, 39257, 39266, 39269,
+        39270, 39274, 39297, 39300, 39312, 39314, 39317, 39322, 39329, 39334, 39429, 39445, 39461, 39492, 39494, 39497,
+        39504, 39509, 39512, 39521, 39557, 39569, 39572, 39573, 39574, 40960, 40962, 40968, 40970, 40981, 40992, 40994,
+        41000, 41002, 41029, 41041, 41044, 41046, 41049, 41088, 41090, 41096, 41098, 41109, 41120, 41122, 41128, 41130,
+        41221, 41225, 41233, 41236, 41238, 41241, 41242, 41286, 41289, 41297, 41301, 41304, 41306, 41313, 41316, 41349,
+        41360, 41362, 41366, 41369, 41474, 41480, 41482, 41488, 41497, 41506, 41512, 41514, 41541, 41553, 41558, 41561,
+        41573, 41600, 41602, 41608, 41610, 41621, 41632, 41634, 41640, 41642, 42009, 42021, 42049, 42052, 42064, 42068,
+        42069, 42072, 42074, 42081, 42085, 42086, 42088, 42089, 42117, 42246, 42249, 42256, 42258, 42261, 42264, 42278,
+        42281, 42306, 42309, 42321, 42324, 42325, 42326, 42329, 42341, 42346, 42369, 42372, 42373, 42374, 42377, 42386,
+        42389, 42392, 42501, 42513, 42518, 42522, 42529, 42533, 42564, 42566, 42570, 42578, 42581, 42582, 42584, 42592,
+        42594, 42630, 42640, 42645, 42646, 42649, 42657, 42660, 42662, 43008, 43010, 43016, 43018, 43040, 43042, 43048,
+        43050, 43089, 43092, 43094, 43097, 43136, 43138, 43144, 43146, 43157, 43168, 43170, 43176, 43178, 43269, 43284,
+        43289, 43297, 43301, 43329, 43344, 43349, 43354, 43361, 43366, 43369, 43408, 43414, 43520, 43522, 43528, 43530,
+        43552, 43554, 43560, 43562, 43601, 43604, 43606, 43648, 43650, 43656, 43658, 43669, 43680, 43682, 43688, 43690,
     };
     static const uint16_t kgrid_2bit_1024[1024] = {
             0,     2,     5,     8,    10,    17,    20,    22,    25,    32,    34,    37,    40,    65,    68,    70,
@@ -10873,12 +10217,12 @@ void iq2xs_init_impl(enum ggml_type type) {
     const int nwant = type == GGML_TYPE_IQ1_S ? 3 : type == GGML_TYPE_IQ2_S ? 1 : 2;
     const uint16_t * kgrid = type == GGML_TYPE_IQ2_XXS ? kgrid_2bit_256 :
                              type == GGML_TYPE_IQ2_XS  ? kgrid_2bit_512 :
-                             type == GGML_TYPE_IQ1_S   ? kgrid_1bit_512 : kgrid_2bit_1024;
+                             type == GGML_TYPE_IQ1_S   ? kgrid_1bit_2048 : kgrid_2bit_1024;
     uint64_t * kgrid_q2xs;
     int      * kmap_q2xs;
     uint16_t * kneighbors_q2xs;
 
-    printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size);
+    //printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size);
     uint64_t * the_grid = (uint64_t *)malloc(grid_size*sizeof(uint64_t));
     for (int k = 0; k < grid_size; ++k) {
         int8_t * pos = (int8_t *)(the_grid + k);
@@ -10933,7 +10277,7 @@ void iq2xs_init_impl(enum ggml_type type) {
         }
         num_neighbors += n;
     }
-    printf("%s: %d neighbours in total\n", __func__, num_neighbors);
+    //printf("%s: %d neighbours in total\n", __func__, num_neighbors);
     kneighbors_q2xs = (uint16_t *)malloc((num_neighbors + num_not_in_map)*sizeof(uint16_t));
     iq2_data[gindex].neighbours = kneighbors_q2xs;
     int counter = 0;
@@ -11356,8 +10700,7 @@ static void quantize_row_iq2_xs_impl(const float * restrict x, void * restrict v
     }
 }
 
-size_t quantize_iq2_xxs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq2_xxs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -11369,8 +10712,7 @@ size_t quantize_iq2_xxs(const float * src, void * dst, int nrow, int n_per_row,
     return nrow * nblock * sizeof(block_iq2_xxs);
 }
 
-size_t quantize_iq2_xs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq2_xs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -11474,7 +10816,7 @@ void iq3xs_init_impl(int grid_size) {
     int      * kmap_q3xs;
     uint16_t * kneighbors_q3xs;
 
-    printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size);
+    //printf("================================================================= %s(grid_size = %d)\n", __func__, grid_size);
     uint32_t * the_grid = (uint32_t *)malloc(grid_size*sizeof(uint32_t));
     for (int k = 0; k < grid_size; ++k) {
         int8_t * pos = (int8_t *)(the_grid + k);
@@ -11529,7 +10871,7 @@ void iq3xs_init_impl(int grid_size) {
         }
         num_neighbors += n;
     }
-    printf("%s: %d neighbours in total\n", __func__, num_neighbors);
+    //printf("%s: %d neighbours in total\n", __func__, num_neighbors);
     kneighbors_q3xs = (uint16_t *)malloc((num_neighbors + num_not_in_map)*sizeof(uint16_t));
     iq3_data[gindex].neighbours = kneighbors_q3xs;
     int counter = 0;
@@ -11812,8 +11154,7 @@ static void quantize_row_iq3_xxs_impl(int grid_size, const float * restrict x, v
     }
 }
 
-size_t quantize_iq3_xxs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq3_xxs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -11912,7 +11253,8 @@ static void quantize_row_iq3_s_impl(int block_size, const float * restrict x, vo
             }
             float best = 0;
             float scale = max/(2*kMaxQ-1);
-            for (int is = -15; is <= 15; ++is) {
+            for (int k = 0; k < bs4; ++k) is_on_grid[k] = false;
+            for (int is = -9; is <= 9; ++is) {
                 float id = (2*kMaxQ-1+is*0.2f)/max;
                 float this_scale = 1/id;
                 for (int k = 0; k < bs4; ++k) {
@@ -11948,7 +11290,7 @@ static void quantize_row_iq3_s_impl(int block_size, const float * restrict x, vo
             if (n_not_ongrid > 0 && scale > 0) {
                 float id = 1/scale;
                 for (int k = 0; k < bs4; ++k) {
-                    if (is_on_grid[k]) continue;
+                    //if (is_on_grid[k]) continue;
                     uint16_t u = 0;
                     for (int i = 0; i < 4; ++i) {
                         int l = nearest_int(0.5f*(id*xval[4*k+i]-1));
@@ -12004,7 +11346,7 @@ static void quantize_row_iq3_s_impl(int block_size, const float * restrict x, vo
         }
 
         float d = max_scale/31;
-        y[ibl].d = GGML_FP32_TO_FP16(d);
+        y[ibl].d = GGML_FP32_TO_FP16(d * 1.033f);
         float id = 1/d;
         for (int ib = 0; ib < QK_K/block_size; ib += 2) {
             int l1 = nearest_int(0.5f*(id*scales[ib+0]-1));
@@ -12018,8 +11360,7 @@ static void quantize_row_iq3_s_impl(int block_size, const float * restrict x, vo
 }
 
 #define IQ3S_BLOCK_SIZE 32
-size_t quantize_iq3_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq3_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     float scales[QK_K/IQ3S_BLOCK_SIZE];
@@ -12049,7 +11390,7 @@ void quantize_row_iq3_s(const float * restrict x, void * restrict vy, int k) {
 
 void quantize_row_iq3_s_reference(const float * restrict x, block_iq3_s * restrict y, int k) {
     assert(k % QK_K == 0);
-    quantize_iq3_s(x, y, 1, k, NULL, NULL);
+    quantize_iq3_s(x, y, 1, k, NULL);
 }
 
 
@@ -12115,12 +11456,70 @@ static int iq1_find_best_neighbour(const uint16_t * restrict neighbours, const u
     return grid_index;
 }
 
+static int iq1_find_best_neighbour2(const uint16_t * restrict neighbours, const uint64_t * restrict grid,
+        const float * restrict xval, const float * restrict weight, float scale, const float * restrict xg, int8_t * restrict L, int ngrid) {
+    int num_neighbors = neighbours[0];
+    GGML_ASSERT(num_neighbors > 0);
+    float best_score = FLT_MAX;
+    int grid_index = -1;
+    for (int j = 1; j <= num_neighbors; ++j) {
+        const int8_t * pg = (const int8_t *)(grid + neighbours[j]);
+        float d2 = 0;
+        for (int i = 0; i < 8; ++i) {
+            float q = xg[(pg[i] - 1)/2];
+            float w = weight[i];
+            float diff = scale*q - xval[i];
+            d2 += w*diff*diff;
+        }
+        if (d2 < best_score) {
+            best_score = d2;
+            grid_index = neighbours[j];
+        }
+    }
+    if (grid_index < 0) {
+        for (int i = 0; i < ngrid; ++i) {
+            const int8_t * grid_i = (const int8_t *)(grid + i);
+            float d2 = 0;
+            for (int j = 0; j < 8; ++j) {
+                float w = weight[j];
+                float q = xg[(grid_i[j] - 1)/2];
+                float diff = scale*q - xval[i];
+                d2 += w*diff*diff;
+            }
+            if (d2 < best_score) {
+                best_score = d2;
+                grid_index = i;
+            }
+        }
+    }
+    if (grid_index < 0) {
+        printf("Oops, did not find grid point\n");
+        printf("Have %d neighbours\n", num_neighbors);
+        for (int j = 1; j <= num_neighbors; ++j) {
+            const int8_t * pg = (const int8_t *)(grid + neighbours[j]);
+            float sumqx = 0, sumq2 = 0;
+            for (int i = 0; i < 8; ++i) {
+                float q = xg[(pg[i] - 1)/2];
+                float w = weight[i];
+                sumqx += w*q*xval[i];
+                sumq2 += w*q*q;
+            }
+            printf("    neighbour %d: sumqx = %g sumq2 = %g\n", j, (double)sumqx, (double)sumq2);
+        }
+    }
+    GGML_ASSERT(grid_index >= 0);
+    const int8_t * pg = (const int8_t *)(grid + grid_index);
+    for (int i = 0; i < 8; ++i) L[i] = (pg[i] - 1)/2;
+    return grid_index;
+}
+
 static int iq1_sort_helper(const void * left, const void * right) {
     const float * l = left;
     const float * r = right;
     return *l < *r ? -1 : *l > *r ? 1 : 0;
 }
 
+#define IQ1S_BLOCK_SIZE 32
 static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy, int n, const float * restrict quant_weights) {
 
     const int gindex = iq2_data_index(GGML_TYPE_IQ1_S);
@@ -12139,37 +11538,41 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
 
     block_iq1_s * y = vy;
 
-    float  scales[QK_K/8];
-    float  weight[8];
-    int8_t L[8];
-    float  sumx[9];
-    float  sumw[9];
-    float  pairs[16];
+    const float x_p[3] = {-1 + IQ1S_DELTA,  IQ1S_DELTA, 1 + IQ1S_DELTA};
+    const float x_m[3] = {-1 - IQ1S_DELTA, -IQ1S_DELTA, 1 - IQ1S_DELTA};
+
+    float  scales[QK_K/IQ1S_BLOCK_SIZE];
+    float  weight[IQ1S_BLOCK_SIZE];
+    int8_t L[IQ1S_BLOCK_SIZE];
+    float  sumx[IQ1S_BLOCK_SIZE+1];
+    float  sumw[IQ1S_BLOCK_SIZE+1];
+    float  pairs[2*IQ1S_BLOCK_SIZE];
     int * idx = (int *)(pairs + 1);
-    uint8_t hbit[QK_K/8];
+    uint16_t index[IQ1S_BLOCK_SIZE/8];
+    int8_t shifts[QK_K/IQ1S_BLOCK_SIZE];
 
     for (int ibl = 0; ibl < nbl; ++ibl) {
 
         y[ibl].d = GGML_FP32_TO_FP16(0.f);
         memset(y[ibl].qs, 0, QK_K/8);
-        memset(y[ibl].scales, 0, QK_K/16);
+        memset(y[ibl].qh, 0, QK_K/16);
 
         float max_scale = 0;
 
         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 = sumx2/QK_K;
+        float sigma2 = 2*sumx2/QK_K;
 
-        for (int ib = 0; ib < QK_K/8; ++ib) {
-            const float * xb = xbl + 8*ib;
-            const float * qw = quant_weights + QK_K*ibl + 8*ib;
-            for (int i = 0; i < 8; ++i) weight[i] = qw[i] * sqrtf(sigma2 + xb[i]*xb[i]);
+        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]);
             float max = fabsf(xb[0]);
-            for (int i = 1; i < 8; ++i) max = MAX(max, fabsf(xb[i]));
+            for (int i = 1; i < IQ1S_BLOCK_SIZE; ++i) max = MAX(max, fabsf(xb[i]));
             if (!max) {
                 scales[ib] = 0;
-                memset(L, 1, 8);
+                memset(L, 1, IQ1S_BLOCK_SIZE);
                 continue;
             }
             // Here we solve exactly the sum of squared difference (SSD) weighted minimization problem.
@@ -12178,52 +11581,81 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
             // in ascending order, compute Si = sum[weight[j] xb[j], j = 0...i] and
             // Wi = sum[weight[j], j = 0...i], and use these to quckly get get the optimum scale
             // for each possible and score for each split.
-            for (int j = 0; j < 8; ++j) {
+            for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) {
                 pairs[2*j] = xb[j];
                 idx[2*j] = j;
             }
-            qsort(pairs, 8, 2*sizeof(float), iq1_sort_helper);
+            qsort(pairs, IQ1S_BLOCK_SIZE, 2*sizeof(float), iq1_sort_helper);
             {
                 sumx[0] = sumw[0] = 0;
-                for (int j = 0; j < 8; ++j) {
+                for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) {
                     int i = idx[2*j];
                     sumx[j+1] = sumx[j] + weight[i]*xb[i];
                     sumw[j+1] = sumw[j] + weight[i];
                 }
             }
             float best_score = 0, scale = max;
-            int besti1 = 0, besti2 = 0;
-            for (int i1 = 0; i1 <= 8; ++i1) {
-                for (int i2 = i1; i2 <= 8; ++i2) {
-                    float sumqx = -(sumx[i1] - sumx[0]) + (sumx[8] - sumx[i2]);
-                    float sumq2 =  (sumw[i1] - sumw[0]) + (sumw[8] - sumw[i2]);
+            int besti1 = -1, besti2 = -1, best_shift = 0;
+            for (int i1 = 0; i1 <= IQ1S_BLOCK_SIZE; ++i1) {
+                for (int i2 = i1; i2 <= IQ1S_BLOCK_SIZE; ++i2) {
+                    float sumqx = (sumx[i1] - sumx[0])*x_p[0] + (sumx[i2] - sumx[i1])*x_p[1] + (sumx[IQ1S_BLOCK_SIZE] - sumx[i2])*x_p[2];
+                    float sumq2 = (sumw[i1] - sumw[0])*x_p[0]*x_p[0] + (sumw[i2] - sumw[i1])*x_p[1]*x_p[1] + (sumw[IQ1S_BLOCK_SIZE] - sumw[i2])*x_p[2]*x_p[2];
                     if (sumq2 > 0 && sumqx*sumqx > best_score*sumq2) {
                         scale = sumqx/sumq2; best_score = scale*sumqx;
-                        besti1 = i1; besti2 = i2;
+                        besti1 = i1; besti2 = i2; best_shift = 1;
+                    }
+                    sumqx = (sumx[i1] - sumx[0])*x_m[0] + (sumx[i2] - sumx[i1])*x_m[1] + (sumx[IQ1S_BLOCK_SIZE] - sumx[i2])*x_m[2];
+                    sumq2 = (sumw[i1] - sumw[0])*x_m[0]*x_m[0] + (sumw[i2] - sumw[i1])*x_m[1]*x_m[1] + (sumw[IQ1S_BLOCK_SIZE] - sumw[i2])*x_m[2]*x_m[2];
+                    if (sumq2 > 0 && sumqx*sumqx > best_score*sumq2) {
+                        scale = sumqx/sumq2; best_score = scale*sumqx;
+                        besti1 = i1; besti2 = i2; best_shift = -1;
                     }
                 }
             }
+            GGML_ASSERT(besti1 >= 0 && besti2 >= 0 && best_shift != 0);
             for (int j =      0; j < besti1; ++j) L[idx[2*j]] = 0;
             for (int j = besti1; j < besti2; ++j) L[idx[2*j]] = 1;
-            for (int j = besti2; j <      8; ++j) L[idx[2*j]] = 2;
+            for (int j = besti2; j < IQ1S_BLOCK_SIZE; ++j) L[idx[2*j]] = 2;
             if (scale < 0) {
-                for (int j = 0; j < 8; ++j) L[j] = 2 - L[j];
-                scale = -scale;
+                for (int j = 0; j < IQ1S_BLOCK_SIZE; ++j) L[j] = 2 - L[j];
+                scale = -scale; best_shift = -best_shift;
+            }
+            bool all_on_grid = true;
+            const float * xx = best_shift == 1 ? x_p : x_m;
+            for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) {
+                uint16_t u = 0;
+                for (int j = 0; j < 8; ++j) u |= (L[8*k+j] << 2*j);
+                int grid_index = kmap_q2xs[u];
+                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);
+                    GGML_ASSERT(grid_index >= 0);
+                }
+                index[k] = grid_index;
+            }
+            if (!all_on_grid) {
+                float sumqx = 0, sumq2 = 0;
+                for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) {
+                    const int8_t * pg = (const int8_t *)(kgrid_q2xs + index[k]);
+                    for (int j = 0; j < 8; ++j) {
+                        float w = weight[8*k + j];
+                        float q = xx[(pg[j] - 1)/2];
+                        sumqx += w*q*xb[8*k+j];
+                        sumq2 += w*q*q;
+                    }
+                }
+                if (sumqx > 0 && sumq2 > 0) scale = sumqx/sumq2;
+            }
+            uint16_t h = 0;
+            for (int k = 0; k < IQ1S_BLOCK_SIZE/8; ++k) {
+                y[ibl].qs[(IQ1S_BLOCK_SIZE/8)*ib + k] = index[k] & 255;
+                h |= (index[k] >> 8) << 3*k;
             }
-            // Now we check if the solution found above corresponds to a grid point and, if not, use a neighbouring
-            // grid point that minimizes SSD.
-            uint16_t u = 0;
-            for (int j = 0; j < 8; ++j) u |= (L[j] << 2*j);
-            int grid_index = kmap_q2xs[u];
-            if (grid_index < 0) {
-                const uint16_t * neighbours = kneighbors_q2xs - kmap_q2xs[u] - 1;
-                grid_index = iq1_find_best_neighbour(neighbours, kgrid_q2xs, xb, weight, &scale, L, NGRID_IQ2XXS);
-                GGML_ASSERT(grid_index >= 0);
-            }
-            y[ibl].qs[ib] = grid_index & 255;
-            hbit[ib] = grid_index >> 8;
+            y[ibl].qh[ib] = h;
             GGML_ASSERT(scale >= 0);
             scales[ib] = scale;
+            shifts[ib] = best_shift;
             max_scale = MAX(max_scale, scale);
         }
 
@@ -12233,19 +11665,18 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy
         }
 
         float d = max_scale/15;
-        y[ibl].d = GGML_FP32_TO_FP16(d*1.085f); // 1.085f is another fudge factor. Don't ask me why it is needed.
+        y[ibl].d = GGML_FP32_TO_FP16(d*1.125f); // 1.085f is another fudge factor. Don't ask me why it is needed.
         float id = 1/d;
-        for (int ib = 0; ib < QK_K/8; ++ib) {
+        for (int ib = 0; ib < QK_K/IQ1S_BLOCK_SIZE; ++ib) {
             int l = nearest_int(0.5f*(id*scales[ib]-1));
             l = MAX(0, MIN(7, l));
-            if (hbit[ib]) l |= 8;
-            y[ibl].scales[ib/2] |= (l << 4*(ib%2));
+            if (shifts[ib] == -1) l |= 8;
+            y[ibl].qh[ib] |= (l << 12);
         }
     }
 }
 
-size_t quantize_iq1_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq1_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -12270,7 +11701,7 @@ static inline int best_index_int8(int n, const int8_t * val, float x) {
     return x - val[mu-1] < val[mu] - x ? mu-1 : mu;
 }
 
-static void quantize_row_iq4_nl_impl(const int super_block_size, const int block_size, const float * GGML_RESTRICT x,
+static void quantize_row_iq4_nl_impl(const int super_block_size, const int block_size, const float * restrict x,
         ggml_fp16_t * dh, uint8_t * q4, uint16_t * scales_h, uint8_t * scales_l,
         float * scales, float * weight, uint8_t * L,
         const int8_t * values,
@@ -12378,8 +11809,7 @@ static void quantize_row_iq4_nl_impl(const int super_block_size, const int block
     }
 }
 
-size_t quantize_iq4_nl(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq4_nl(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK4_NL == 0);
     int nblock = n_per_row/QK4_NL;
     char * qrow = (char *)dst;
@@ -12409,14 +11839,13 @@ void quantize_row_iq4_nl(const float * restrict x, void * restrict vy, int k) {
 
 void quantize_row_iq4_nl_reference(const float * restrict x, block_iq4_nl * restrict y, int k) {
     assert(k % QK4_NL == 0);
-    quantize_iq4_nl(x, y, 1, k, NULL, NULL);
+    quantize_iq4_nl(x, y, 1, k, NULL);
 }
 
-size_t quantize_iq4_xs(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
+size_t quantize_iq4_xs(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
 #if QK_K == 64
-    return quantize_iq4_nl(src, dst, nrow, n_per_row, hist, quant_weights);
+    return quantize_iq4_nl(src, dst, nrow, n_per_row, quant_weights);
 #else
-    (void)hist;
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -12445,7 +11874,7 @@ void quantize_row_iq4_xs(const float * restrict x, void * restrict vy, int k) {
 
 void quantize_row_iq4_xs_reference(const float * restrict x, block_iq4_xs * restrict y, int k) {
     assert(k % QK_K == 0);
-    quantize_iq4_xs(x, y, 1, k, NULL, NULL);
+    quantize_iq4_xs(x, y, 1, k, NULL);
 }
 
 // =============================== 2.5625 bpw
@@ -12618,8 +12047,7 @@ static void quantize_row_iq2_s_impl(const float * restrict x, void * restrict vy
     }
 }
 
-size_t quantize_iq2_s(const float * src, void * dst, int nrow, int n_per_row, int64_t * hist, const float * quant_weights) {
-    (void)hist;
+size_t quantize_iq2_s(const float * restrict src, void * restrict dst, int nrow, int n_per_row, const float * quant_weights) {
     GGML_ASSERT(n_per_row%QK_K == 0);
     int nblock = n_per_row/QK_K;
     char * qrow = (char *)dst;
@@ -12633,7 +12061,7 @@ size_t quantize_iq2_s(const float * src, void * dst, int nrow, int n_per_row, in
 
 void quantize_row_iq2_s_reference(const float * restrict x, block_iq2_s * restrict y, int k) {
     assert(k % QK_K == 0);
-    quantize_iq2_s(x, y, 1, k, NULL, NULL);
+    quantize_iq2_s(x, y, 1, k, NULL);
 }
 
 void quantize_row_iq2_s(const float * restrict x, void * restrict vy, int k) {