ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

llama : expose llama_model_n_head_kv in the API (#11997)

Browse source 
It's useful to be able to have this from the library layer as it's a key
parameter of the model (e.g. to figure out how much KV cache memory is
needed).
This commit is contained in:
Vitali Lovich 2025-02-25 01:29:33 -08:00 • committed by GitHub
parent 58d07a8043
commit 3e9a2860e9
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
include/llama.h
View file

@ -477,6 +477,7 @@ extern "C" {
LLAMA_API int32_t llama_model_n_embd (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_layer (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_head (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_head_kv (const struct llama_model * model);
// Get the model's RoPE frequency scaling factor
LLAMA_API float llama_model_rope_freq_scale_train(const struct llama_model * model);

4
src/llama-model.cpp
View file

@ -3838,6 +3838,10 @@ int32_t llama_model_n_head(const struct llama_model * model) {
return model->hparams.n_head();
}
int32_t llama_model_n_head_kv(const struct llama_model * model) {
return model->hparams.n_head_kv();
}
// deprecated
int32_t llama_n_ctx_train(const struct llama_model * model) {
return llama_model_n_ctx_train(model);