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

ggml : add IQ2 to test-backend-ops + refactoring

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-01-14 13:15:30 +02:00
parent bee938da74
commit bc0bb3009c
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
7 changed files with 99 additions and 64 deletions
Download patch file Download diff file Expand all files Collapse all files

3
ggml-quants.h
View file

@ -257,3 +257,6 @@ size_t quantize_q4_0 (const float * src, void * dst, int nrows, int n_per_row,
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);
void iq2xs_init_impl(int grid_size);
void iq2xs_free_impl(int grid_size);