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

Method n_head

subprojects/llama.cpp/src/llama-hparams.cpp:30–36  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

28}
29
30uint32_t llama_hparams::n_head(uint32_t il) const {
31 if (il < n_layer) {
32 return n_head_arr[il];
33 }
34
35 GGML_ABORT("fatal error");
36}
37
38uint32_t llama_hparams::n_head_kv(uint32_t il) const {
39 if (il < n_layer) {

Callers 15

n_gqaMethod · 0.95
weight_buft_supportedFunction · 0.80
load_hparamsMethod · 0.80
load_tensorsMethod · 0.80
print_infoMethod · 0.80
llama_model_n_headFunction · 0.80
llm_graph_contextMethod · 0.80
build_attention_layerMethod · 0.80
build_attention_layerMethod · 0.80
llm_build_deciMethod · 0.80
llm_build_mimo2_iswaMethod · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected