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

Remove debug assert

This commit is contained in:
Colin Kealty 2025-04-02 22:52:13 -04:00
parent 105261d2ba
commit 502812b2b1
1 changed files with 0 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-quant.cpp
View File

@ -865,8 +865,6 @@ static void llama_model_quantize_impl(const std::string & fname_inp, const std::
is_clip_model |= name.rfind("mm.", 0) == 0; // check the "mm." prefix is_clip_model |= name.rfind("mm.", 0) == 0; // check the "mm." prefix
} }
GGML_ASSERT(qs.n_ffn_down_exp != 0);
qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)model.hparams.n_layer; qs.n_ffn_down = qs.n_ffn_gate = qs.n_ffn_up = (int)model.hparams.n_layer;
// sanity checks for models that have attention layers // sanity checks for models that have attention layers