diff --git a/ggml-quants.c b/ggml-quants.c index 6b5d26653..4ee4e0604 100644 --- a/ggml-quants.c +++ b/ggml-quants.c @@ -1956,7 +1956,7 @@ 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, const float * quant_weights) { +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); @@ -2264,7 +2264,7 @@ 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, const float * quant_weights) { +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); @@ -2512,7 +2512,7 @@ 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, const float * quant_weights) { +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); @@ -2821,7 +2821,7 @@ 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, const float * quant_weights) { +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); @@ -3063,7 +3063,7 @@ 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, const float * quant_weights) { +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); @@ -3107,7 +3107,7 @@ 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, 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) { quantize_row_q4_0_reference(src, dst, nrow*n_per_row); return nrow * ggml_row_size(GGML_TYPE_Q4_0, n_per_row); @@ -3152,7 +3152,7 @@ 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, 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) { quantize_row_q4_1_reference(src, dst, nrow*n_per_row); return nrow * ggml_row_size(GGML_TYPE_Q4_1, n_per_row); @@ -3206,7 +3206,7 @@ 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, 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) { quantize_row_q5_0_reference(src, dst, nrow*n_per_row); return nrow * ggml_row_size(GGML_TYPE_Q5_0, n_per_row); @@ -3259,7 +3259,7 @@ 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, 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) { quantize_row_q5_1_reference(src, dst, nrow*n_per_row); return nrow * ggml_row_size(GGML_TYPE_Q5_1, n_per_row); @@ -3274,7 +3274,7 @@ size_t quantize_q5_1(const float * src, void * dst, int nrow, int n_per_row, con return nrow * row_size; } -size_t quantize_q8_0(const float * src, void * dst, int nrow, int n_per_row, const float * quant_weights) { +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); @@ -9326,7 +9326,7 @@ 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); @@ -9573,7 +9573,7 @@ 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); @@ -10173,7 +10173,7 @@ void iq2xs_init_impl(enum ggml_type type) { 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); @@ -10228,7 +10228,7 @@ 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; @@ -10651,7 +10651,7 @@ 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, const float * quant_weights) { +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; @@ -10663,7 +10663,7 @@ 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, const float * quant_weights) { +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; @@ -10767,7 +10767,7 @@ 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); @@ -10822,7 +10822,7 @@ 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; @@ -11105,7 +11105,7 @@ 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, const float * quant_weights) { +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; @@ -11311,7 +11311,7 @@ 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, const float * quant_weights) { +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]; @@ -11536,7 +11536,7 @@ static void quantize_row_iq1_s_impl(const float * restrict x, void * restrict vy } } -size_t quantize_iq1_s(const float * src, void * dst, int nrow, int n_per_row, const float * quant_weights) { +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; @@ -11561,7 +11561,7 @@ 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, @@ -11669,7 +11669,7 @@ 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, const float * quant_weights) { +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; @@ -11702,7 +11702,7 @@ void quantize_row_iq4_nl_reference(const float * restrict x, block_iq4_nl * rest quantize_iq4_nl(x, y, 1, k, NULL); } -size_t quantize_iq4_xs(const float * src, void * dst, int nrow, int n_per_row, 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, quant_weights); #else @@ -11907,7 +11907,7 @@ 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, const float * quant_weights) { +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; diff --git a/ggml-quants.h b/ggml-quants.h index 266dec666..47dd52856 100644 --- a/ggml-quants.h +++ b/ggml-quants.h @@ -324,6 +324,7 @@ void ggml_vec_dot_q3_K_q8_K(int n, float * GGML_RESTRICT s, size_t bs, const voi void ggml_vec_dot_q4_K_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_q5_K_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_q6_K_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_iq2_xxs_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_iq2_xs_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_iq2_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); @@ -333,28 +334,26 @@ void ggml_vec_dot_iq4_nl_q8_0 (int n, float * GGML_RESTRICT s, size_t bs, const void ggml_vec_dot_iq4_xs_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 * GGML_RESTRICT s, size_t bs, const void * GGML_RESTRICT vx, size_t bx, const void * GGML_RESTRICT vy, size_t by, int nrc); -// // Quantization utilizing an importance matrix (a.k.a. "Activation aWare Quantization") -// -size_t quantize_iq2_xxs(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_iq2_xs (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_iq2_s (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_iq3_xxs(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_iq1_s (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_iq4_nl (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_iq4_xs (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_iq3_s (const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq2_xxs(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq2_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq2_s (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq3_xxs(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq1_s (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq4_nl (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq4_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_iq3_s (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q2_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q3_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q4_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q5_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q6_K(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q4_0(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q4_1(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q5_0(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q5_1(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); -size_t quantize_q8_0(const float * src, void * dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q2_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q3_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q4_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q5_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q6_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q4_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q4_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q5_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q5_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); +size_t quantize_q8_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int nrows, int n_per_row, const float * imatrix); void iq2xs_init_impl(enum ggml_type type); void iq2xs_free_impl(enum ggml_type type);