thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

hparams : add n_embd_inp() to support extended embed (#16928)

Browse source 
* add n_embd_full to support extended embed

* don't change output

* rename to n_embd_inp

* restore n_embd where applicable
This commit is contained in:
Sigbjørn Skjæret 2025-11-07 19:27:58 +01:00 • committed by GitHub
parent 16bcc1259d
commit 9008027aa3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 29 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

1
include/llama.h
View file

@ -486,6 +486,7 @@ extern "C" {
LLAMA_API int32_t llama_model_n_ctx_train(const struct llama_model * model);
LLAMA_API int32_t llama_model_n_embd (const struct llama_model * model);
LLAMA_API int32_t llama_model_n_embd_inp (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);