happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

guard ftype imatrix warning

This commit is contained in:
ddh0 2026-02-11 21:57:55 -06:00
parent 1658228d6a
commit b15bb3404c
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
tools/quantize/quantize.cpp
View File

@ -686,11 +686,12 @@ int main(int argc, char ** argv) {
}
}
if ((params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_S ||
params.ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_M) && imatrix_data.empty()) {
if (!params.dry_run &&
(
params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XS || params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_XXS ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ2_S || params.ftype == LLAMA_FTYPE_MOSTLY_Q2_K_S ||
params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_S || params.ftype == LLAMA_FTYPE_MOSTLY_IQ1_M
) && imatrix_data.empty()) {
fprintf(stderr, "\n==========================================================================================================\n");
fprintf(stderr, "Please do not use IQ1_S, IQ1_M, IQ2_S, IQ2_XXS, IQ2_XS or Q2_K_S quantization without an importance matrix\n");
fprintf(stderr, "==========================================================================================================\n\n\n");