LLM inference in C/C++
C++ ggml
wavtokenizer-dec : bound posnet/convnext block_count against n_layer_all (#26892)
Oğuzhan Akkaya55f453b92452
diff --git a/src/llama-model.cpp b/src/llama-model.cppindex 0e27cb4171..c810055050 100644--- a/src/llama-model.cpp+++ b/src/llama-model.cpp@@ -1122,6 +1122,9 @@ void llama_model_base::load_hparams(llama_model_loader & ml) {ml.get_key(LLM_KV_CONVNEXT_EMBEDDING_LENGTH, hparams.convnext.n_embd);ml.get_key(LLM_KV_CONVNEXT_BLOCK_COUNT, hparams.convnext.n_layer);++ GGML_ASSERT(hparams.posnet.n_layer <= hparams.n_layer_all);+ GGML_ASSERT(hparams.convnext.n_layer <= hparams.n_layer_all);}GGML_ASSERT(hparams.n_expert <= LLAMA_MAX_EXPERTS);