CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-15 11:17:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

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
9 changed files with 29 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
src/llama-hparams.h
View File

@@ -227,6 +227,9 @@ struct llama_hparams {
uint32_t n_gqa(uint32_t il = 0) const;
// dimension of main + auxiliary input embeddings
uint32_t n_embd_inp() const;
// dimension of key embeddings across all k-v heads
uint32_t n_embd_k_gqa(uint32_t il = 0) const;