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

move i2s to quantize v1

Browse source
This commit is contained in:
Eddie-Wang 2024-06-09 02:43:38 +00:00
parent 4e1ab50628
commit ca09085593
6 changed files with 46 additions and 14 deletions
Download patch file Download diff file Expand all files Collapse all files

1
ggml-quants.h
View file

@ -122,6 +122,7 @@ size_t quantize_q4_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst,
size_t quantize_q5_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
size_t quantize_q5_1(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
size_t quantize_q8_0(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
size_t quantize_i2_s(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrows, int64_t n_per_row, const float * imatrix);
void iq2xs_init_impl(enum ggml_type type);
void iq2xs_free_impl(enum ggml_type type);