MCPcopy Create free account
hub / github.com/Tiiny-AI/PowerInfer / llama_model_n_params

Function llama_model_n_params

llama.cpp:10087–10093  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

10085}
10086
10087uint64_t llama_model_n_params(const struct llama_model * model) {
10088 uint64_t nparams = 0;
10089 for (const auto & it : model->tensors_by_name) {
10090 nparams += ggml_nelements(it.second);
10091 }
10092 return nparams;
10093}
10094
10095struct ggml_tensor * llama_get_model_tensor(struct llama_model * model, const char * name) {
10096 return ggml_get_tensor(model->ctx, name);

Callers 1

testMethod · 0.50

Calls 1

ggml_nelementsFunction · 0.70

Tested by

no test coverage detected