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

Function llama_backend_init

subprojects/llama.cpp/src/llama.cpp:796–805  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

794}
795
796void llama_backend_init(void) {
797 ggml_time_init();
798
799 // needed to initialize f16 tables
800 {
801 struct ggml_init_params params = { 0, NULL, false };
802 struct ggml_context * ctx = ggml_init(params);
803 ggml_free(ctx);
804 }
805}
806
807void llama_numa_init(enum ggml_numa_strategy numa) {
808 if (numa != GGML_NUMA_STRATEGY_DISABLED) {

Callers 15

mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85
mainFunction · 0.85

Calls 3

ggml_time_initFunction · 0.85
ggml_initFunction · 0.85
ggml_freeFunction · 0.85

Tested by 8

mainFunction · 0.68
mainFunction · 0.68
mainFunction · 0.68
mainFunction · 0.68
mainFunction · 0.68
mainFunction · 0.68
mainFunction · 0.68
mainFunction · 0.68