ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-03 10:30:27 +00:00
Code Issues Packages Projects Releases Wiki Activity

NEON is not working yet, so still use Q8_K GEMM

Browse Source
This commit is contained in:
Iwan Kawrakow
2025-06-11 10:55:42 +03:00
parent bed683fd09
commit 415a7cf6c3
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
ggml/src/ggml.c
View File

@@ -1067,7 +1067,11 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = {
.from_float = quantize_row_iq2_xxs,
.from_float_ref = (ggml_from_float_t)quantize_row_iq2_xxs_ref,
.vec_dot = ggml_vec_dot_iq2_xxs_q8_K,
.vec_dot_type = GGML_TYPE_Q8_2_X4, //GGML_TYPE_Q8_K,
#ifdef __AVX2__
.vec_dot_type = GGML_TYPE_Q8_2_X4,
#else
.vec_dot_type = GGML_TYPE_Q8_K,
#endif
.nrows = 1,
.row_meta_size = 0,
},