vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

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
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
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);