ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-28 09:04:10 +00:00
Code Issues Packages Projects Releases Wiki Activity

Minor

Browse Source
This commit is contained in:
Kawrakow
2024-09-19 11:14:53 +03:00
parent d373900e99
commit 15b231cb74
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama.cpp
View File

@@ -15690,7 +15690,7 @@ static ggml_type llama_tensor_get_type(quantize_state_internal & qs, ggml_type n
new_type = GGML_TYPE_Q4_K;
}
else if (ftype == LLAMA_FTYPE_MOSTLY_IQ3_XXS) {
new_type = qs.model.hparams.n_gqa() >= 4 ? GGML_TYPE_Q4_K : new_type = qs.model.hparams.n_gqa() >= 2 ? GGML_TYPE_IQ3_K
new_type = qs.model.hparams.n_gqa() >= 4 ? GGML_TYPE_Q4_K : qs.model.hparams.n_gqa() >= 2 ? GGML_TYPE_IQ3_K
: !qs.has_imatrix ? GGML_TYPE_IQ3_S : GGML_TYPE_IQ3_XXS;
}
else if ((ftype == LLAMA_FTYPE_MOSTLY_IQ3_XS || ftype == LLAMA_FTYPE_MOSTLY_IQ3_S || ftype == LLAMA_FTYPE_MOSTLY_IQ3_K) && qs.model.hparams.n_gqa() >= 2) {