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

Function llama_model_size

llama.cpp:10079–10085  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

10077}
10078
10079uint64_t llama_model_size(const struct llama_model * model) {
10080 uint64_t size = 0;
10081 for (const auto & it : model->tensors_by_name) {
10082 size += ggml_nbytes(it.second);
10083 }
10084 return size;
10085}
10086
10087uint64_t llama_model_n_params(const struct llama_model * model) {
10088 uint64_t nparams = 0;

Callers 1

testMethod · 0.50

Calls 1

ggml_nbytesFunction · 0.70

Tested by

no test coverage detected