tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-27 02:28:19 -04:00
Code Issues Packages Projects Releases Wiki Activity

Add ability to use importance matrix for all k-quants (#4930)

Browse Source 
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-01-14 16:21:12 +02:00
committed by GitHub
parent bb0c139247
commit 467a882fd2
4 changed files with 462 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
ggml-quants.h
View File

@@ -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);