Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

model : load hparams.n_layer_nextn before n_layer() calls (#28159)

Browse Source 
* load hparams.n_layer_nextn before n_layer() calls

* remove duplicate loads
This commit is contained in:
Sigbjørn Skjæret
2026-09-01 13:55:45 +02:00
committed by GitHub
parent fe2120bc9d
commit 9d817213a0
21 changed files with 7 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/llama-model.cpp
+2
View File
@@ -1223,6 +1223,8 @@ void llama_model_base::load_hparams(llama_model_loader & ml) {
ml.get_key(LLM_KV_POOLING_TYPE, hparams.pooling_type, false);
ml.get_key(LLM_KV_BLOCK_COUNT, hparams.n_layer_all);
GGML_ASSERT(hparams.n_layer_all > 0 && hparams.n_layer_all <= LLAMA_MAX_LAYERS);
ml.get_key(LLM_KV_NEXTN_PREDICT_LAYERS, hparams.n_layer_nextn, false);
GGML_ASSERT(hparams.n_layer_nextn < hparams.n_layer_all);
ml.get_key(LLM_KV_EXPERT_COUNT, hparams.n_expert, false);
ml.get_key(LLM_KV_EXPERT_USED_COUNT, hparams.n_expert_used, false);
ml.get_key(LLM_KV_EXPERT_GROUP_COUNT, hparams.n_expert_groups, false);