MCPcopy Create free account
hub / github.com/appdevforall/CodeOnTheGo / llama_time_us

Function llama_time_us

subprojects/llama.cpp/src/llama.cpp:823–825  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

821}
822
823int64_t llama_time_us(void) {
824 return ggml_time_us();
825}
826
827// Returns 0 on success, -1 on error, and -2 on cancellation via llama_progress_callback
828static int llama_model_load(const std::string & fname, std::vector<std::string> & splits, llama_model & model, llama_model_params & params) {

Callers 2

mainFunction · 0.85
llama_params_fitFunction · 0.85

Calls 1

ggml_time_usFunction · 0.85

Tested by

no test coverage detected