diff options
Diffstat (limited to 'ggml-quants.h')
| -rw-r--r-- | ggml-quants.h | 9 |
1 files changed, 9 insertions, 0 deletions
diff --git a/ggml-quants.h b/ggml-quants.h index 4d436a8f..a66fe6d6 100644 --- a/ggml-quants.h +++ b/ggml-quants.h @@ -25,12 +25,14 @@ void quantize_row_q4_K_reference(const float * GGML_RESTRICT x, block_q4_K * GGM void quantize_row_q5_K_reference(const float * GGML_RESTRICT x, block_q5_K * GGML_RESTRICT y, int64_t k); void quantize_row_q6_K_reference(const float * GGML_RESTRICT x, block_q6_K * GGML_RESTRICT y, int64_t k); void quantize_row_q8_K_reference(const float * GGML_RESTRICT x, block_q8_K * GGML_RESTRICT y, int64_t k); +void quantize_row_q8_K64_reference(const float * GGML_RESTRICT x, block_q8_K64 * GGML_RESTRICT y, int64_t k); void quantize_row_iq3_xxs_reference(const float * GGML_RESTRICT x, block_iq3_xxs * GGML_RESTRICT y, int64_t k); void quantize_row_iq4_nl_reference (const float * GGML_RESTRICT x, block_iq4_nl * GGML_RESTRICT y, int64_t k); void quantize_row_iq4_xs_reference (const float * GGML_RESTRICT x, block_iq4_xs * GGML_RESTRICT y, int64_t k); void quantize_row_iq3_s_reference (const float * GGML_RESTRICT x, block_iq3_s * GGML_RESTRICT y, int64_t k); void quantize_row_iq2_s_reference (const float * GGML_RESTRICT x, block_iq2_s * GGML_RESTRICT y, int64_t k); +void quantize_row_iq1_bn_reference (const float * GGML_RESTRICT x, block_iq1_bn * GGML_RESTRICT y, int64_t k); void quantize_row_q4_0(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); void quantize_row_q4_1(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); @@ -45,12 +47,14 @@ void quantize_row_q4_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, in void quantize_row_q5_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); void quantize_row_q6_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); void quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); +void quantize_row_q8_K64(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); void quantize_row_iq3_xxs(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); void quantize_row_iq4_nl (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); void quantize_row_iq4_xs (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); void quantize_row_iq3_s (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); void quantize_row_iq2_s (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); +void quantize_row_iq1_bn (const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); // Dequantization void dequantize_row_q4_0(const block_q4_0 * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); @@ -76,6 +80,7 @@ void dequantize_row_iq1_m (const block_iq1_m * GGML_RESTRICT x, float * GGML_ void dequantize_row_iq4_nl (const block_iq4_nl * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); void dequantize_row_iq4_xs (const block_iq4_xs * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); void dequantize_row_iq3_s (const block_iq3_s * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); +void dequantize_row_iq1_bn (const block_iq1_bn * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); // Dot product void ggml_vec_dot_q4_0_q8_0(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); @@ -99,6 +104,8 @@ void ggml_vec_dot_iq1_m_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const void ggml_vec_dot_iq4_nl_q8_0 (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_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); +void ggml_vec_dot_iq1_bn_q8_0 (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_bn_q8_K64(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 * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); @@ -110,6 +117,7 @@ size_t quantize_iq1_m (const float * GGML_RESTRICT src, void * GGML_RESTRICT ds size_t quantize_iq4_nl (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); size_t quantize_iq4_xs (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); size_t quantize_iq3_s (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); +size_t quantize_iq1_bn (const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); size_t quantize_q2_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); size_t quantize_q3_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); @@ -126,6 +134,7 @@ void iq2xs_init_impl(enum ggml_type type); void iq2xs_free_impl(enum ggml_type type); void iq3xs_init_impl(int grid_size); void iq3xs_free_impl(int grid_size); +void iq1bn_init_impl(void); #ifdef __cplusplus } |