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

comment ref #12557

This commit is contained in:
ddh0 2026-02-11 22:18:56 -06:00
parent b15bb3404c
commit 40528248fc
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-quant.cpp
View File

@ -484,7 +484,7 @@ static bool tensor_type_requires_imatrix(const llama_model_quantize_params * par
dst_type == GGML_TYPE_IQ2_XXS || dst_type == GGML_TYPE_IQ2_XS ||
dst_type == GGML_TYPE_IQ3_XXS || dst_type == GGML_TYPE_IQ1_S ||
dst_type == GGML_TYPE_IQ2_S || dst_type == GGML_TYPE_IQ1_M ||
dst_type == GGML_TYPE_TQ1_0 || dst_type == GGML_TYPE_TQ2_0 ||
// dst_type == GGML_TYPE_TQ1_0 || dst_type == GGML_TYPE_TQ2_0 || // uncomment if #12557 is merged
( // Q2_K is the worst k-quant type - only allow it without imatrix for token embeddings
dst_type == GGML_TYPE_Q2_K && strcmp(t->name, "token_embd.weight") != 0
)