diff options
Diffstat (limited to 'ggml/src/iqk/iqk_quantize.h')
| -rw-r--r-- | ggml/src/iqk/iqk_quantize.h | 6 |
1 files changed, 6 insertions, 0 deletions
diff --git a/ggml/src/iqk/iqk_quantize.h b/ggml/src/iqk/iqk_quantize.h index 70918a65..3fc02a5e 100644 --- a/ggml/src/iqk/iqk_quantize.h +++ b/ggml/src/iqk/iqk_quantize.h @@ -31,6 +31,12 @@ size_t quantize_iq3_k(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, void dequantize_row_iq3_k(const block_iq3_k * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); void vec_dot_iq3_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 quantize_row_iq3_ks_ref(const float * GGML_RESTRICT x, block_iq3_ks * GGML_RESTRICT y, int64_t k); +void quantize_row_iq3_ks(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); +size_t quantize_iq3_ks(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); +void dequantize_row_iq3_ks(const block_iq3_ks * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); +void vec_dot_iq3_ks_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 quantize_row_iq4_k_ref(const float * GGML_RESTRICT x, block_iq4_k * GGML_RESTRICT y, int64_t k); void quantize_row_iq4_k(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); size_t quantize_iq4_k(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); |