tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-17 21:51:27 -04:00
Code Issues Packages Projects Releases Wiki Activity

ggml : importance matrix support for legacy quants (#4969)

Browse Source 
* imatrix: adding support for legacy quants

* imatrix: guard Q4_0/Q5_0 against ffn_down craziness

---------

Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>
This commit is contained in:
Kawrakow
2024-01-16 19:51:26 +02:00
committed by GitHub
parent 4feb4b33ee
commit 334a835a1c
4 changed files with 226 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml-quants.h
View File

@@ -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);