diff options
| author | Kawrakow <iwankawrakow@gmail.com> | 2024-12-08 09:34:42 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-12-08 09:34:42 +0100 |
| commit | fc701cedd146152fb270482a7eef5aba23b20575 (patch) | |
| tree | 2628241f10a4fd3e501d17f13059df0039dd344a /ggml/src/iqk/iqk_quantize.h | |
| parent | ef95b81733599429fdd63e4c2fb32c74645046be (diff) | |
Rename iq4_nl_x4 to iq4_nl_r4 (#126)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml/src/iqk/iqk_quantize.h')
| -rw-r--r-- | ggml/src/iqk/iqk_quantize.h | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/ggml/src/iqk/iqk_quantize.h b/ggml/src/iqk/iqk_quantize.h index fb436e57..f5bbd3dc 100644 --- a/ggml/src/iqk/iqk_quantize.h +++ b/ggml/src/iqk/iqk_quantize.h @@ -63,16 +63,16 @@ void vec_dot_iq2_ks_q8_k(int n, float * GGML_RESTRICT s, size_t bs, const void void iqk_quantize_row_q8_K(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k); -void quantize_row_iq4_nl_x4_ref(const float * GGML_RESTRICT x, block_iq4_nl_x4 * GGML_RESTRICT y, int64_t k); -void quantize_row_iq4_nl_x4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); -size_t quantize_iq4_nl_x4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); -void dequantize_row_iq4_nl_x4(const block_iq4_nl_x4 * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); -void vec_dot_iq4_nl_x4_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 quantize_row_iq4_nl_r4_ref(const float * GGML_RESTRICT x, block_iq4_nl_r4 * GGML_RESTRICT y, int64_t k); +void quantize_row_iq4_nl_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); +size_t quantize_iq4_nl_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); +void dequantize_row_iq4_nl_r4(const block_iq4_nl_r4 * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); +void vec_dot_iq4_nl_r4_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 quantize_row_q4_0_r4_ref(const float * GGML_RESTRICT x, block_iq4_nl_x4 * GGML_RESTRICT y, int64_t k); +void quantize_row_q4_0_r4_ref(const float * GGML_RESTRICT x, block_iq4_nl_r4 * GGML_RESTRICT y, int64_t k); void quantize_row_q4_0_r4(const float * GGML_RESTRICT x, void * GGML_RESTRICT y, int64_t k); size_t quantize_q4_0_r4(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix); -void dequantize_row_q4_0_r4(const block_iq4_nl_x4 * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); +void dequantize_row_q4_0_r4(const block_iq4_nl_r4 * GGML_RESTRICT x, float * GGML_RESTRICT y, int64_t k); void vec_dot_q4_0_r4_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 quantize_row_q8_0_r4_ref(const float * GGML_RESTRICT x, block_q8_0_x4 * GGML_RESTRICT y, int64_t k); |