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

Method n_ff

subprojects/llama.cpp/src/llama-hparams.cpp:46–52  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

44}
45
46uint32_t llama_hparams::n_ff(uint32_t il) const {
47 if (il < n_layer) {
48 return n_ff_arr[il];
49 }
50
51 GGML_ABORT("fatal error");
52}
53
54uint32_t llama_hparams::n_gqa(uint32_t il) const {
55 const uint32_t n_head = this->n_head(il);

Callers 7

load_hparamsMethod · 0.80
load_tensorsMethod · 0.80
print_infoMethod · 0.80
create_memoryMethod · 0.80
llm_build_nemotron_hMethod · 0.80
llm_build_deciMethod · 0.80
llm_build_bertMethod · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected