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

Method n_head_kv

smallthinker/src/llama-hparams.cpp:35–41  ·  view source on GitHub ↗

Source from the content-addressed store, hash-verified

33}
34
35uint32_t llama_hparams::n_head_kv(uint32_t il) const {
36 if (il < n_layer) {
37 return n_head_kv_arr[il];
38 }
39
40 GGML_ABORT("fatal error");
41}
42
43uint32_t llama_hparams::n_ff(uint32_t il) const {
44 if (il < n_layer) {

Callers 14

n_gqaMethod · 0.95
n_embd_k_gqaMethod · 0.95
n_embd_v_gqaMethod · 0.95
load_hparamsMethod · 0.80
load_tensorsMethod · 0.80
print_infoMethod · 0.80
llm_build_deciMethod · 0.80
llm_build_openelmMethod · 0.80
build_rwkv6_time_mixMethod · 0.80
llama_model_n_head_kvFunction · 0.80
get_kMethod · 0.80
get_vMethod · 0.80

Calls

no outgoing calls

Tested by

no test coverage detected