From 334a835a1ccc8106a5fa355683a965efb1bfa24b Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Tue, 16 Jan 2024 19:51:26 +0200 Subject: ggml : importance matrix support for legacy quants (#4969) * imatrix: adding support for legacy quants * imatrix: guard Q4_0/Q5_0 against ffn_down craziness --------- Co-authored-by: Iwan Kawrakow --- ggml-quants.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'ggml-quants.h') diff --git a/ggml-quants.h b/ggml-quants.h index 99467936..d7fefdb5 100644 --- a/ggml-quants.h +++ b/ggml-quants.h @@ -253,3 +253,7 @@ size_t quantize_q3_K (const float * src, void * dst, int nrows, int n_per_row, 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); +size_t quantize_q4_0 (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); +size_t quantize_q4_1 (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); +size_t quantize_q5_0 (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); +size_t quantize_q5_1 (const float * src, void * dst, int nrows, int n_per_row, int64_t * hist, const float * imatrix); -- cgit v1.2.3