diff options
author | Kawrakow <48489457+ikawrakow@users.noreply.github.com> | 2024-01-14 16:21:12 +0200 |
---|---|---|
committer | GitHub <noreply@github.com> | 2024-01-14 16:21:12 +0200 |
commit | 467a882fd2e5b6172897b49aa45aa29bd3f27685 (patch) | |
tree | 39f03df9b8418028c59380a8a4555395ba13f685 /ggml-quants.h | |
parent | bb0c1392479398f9aba86d9ec98db0b95ede6e6d (diff) |
Add ability to use importance matrix for all k-quants (#4930)
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
Diffstat (limited to 'ggml-quants.h')
-rw-r--r-- | ggml-quants.h | 5 |
1 files changed, 4 insertions, 1 deletions
diff --git a/ggml-quants.h b/ggml-quants.h index e5d11023..99467936 100644 --- a/ggml-quants.h +++ b/ggml-quants.h @@ -249,4 +249,7 @@ void ggml_vec_dot_iq2_xs_q8_K (int n, float * restrict s, const void * restrict size_t quantize_iq2_xxs(const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); size_t quantize_iq2_xs (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); size_t quantize_q2_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); - +size_t quantize_q3_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); +size_t quantize_q4_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); +size_t quantize_q5_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); +size_t quantize_q6_K (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); |