ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-03-13 15:30:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add command line option to merge experts up/gate

Browse Source
This commit is contained in:
Kawrakow
2026-01-12 12:49:18 +02:00
parent 80f2b090d5
commit 7671335ac9
8 changed files with 20 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-model-loader.cpp
View File

@@ -204,7 +204,7 @@ namespace GGUFMeta {
}
llama_model_loader::llama_model_loader(const std::string & fname, bool use_mmap, bool check_tensors,
bool repack_tensors, bool use_thp, bool merge_qkv,
bool repack_tensors, bool use_thp, bool merge_qkv, bool merge_up_gate_exps,
const llama_model_kv_override * param_overrides_p,
const llama_model_tensor_buft_override * param_tensor_buft_overrides_p) {
int trace = 0;
@@ -497,6 +497,7 @@ llama_model_loader::llama_model_loader(const std::string & fname, bool use_mmap,
this->repack_tensors = repack_tensors;
this->use_thp = use_thp;
this->merge_qkv = merge_qkv;
this->merge_up_gate_exps = merge_up_gate_exps;
}
llama_model_loader::~llama_model_loader() {