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

Update src/llama.cpp

Browse source 
Co-authored-by: compilade <git@compilade.net>
This commit is contained in:
Yoshi Suhara 2024-08-09 02:06:04 -07:00 • committed by Yoshi Suhara
parent b841554d0c
commit 092382fee3
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama.cpp
View file

@ -13854,7 +13854,7 @@ struct llm_build_context {
// self-attention // self-attention
{ {
// compute Q and K and RoPE them // compute Q and K and RoPE them
struct ggml_tensor * Qcur = ggml_mul_mat(ctx0, model.layers[il].wq, cur); struct ggml_tensor * Qcur = llm_build_lora_mm(lctx, ctx0, model.layers[il].wq, cur);
cb(Qcur, "Qcur", il); cb(Qcur, "Qcur", il);
if (model.layers[il].bq) { if (model.layers[il].bq) {
Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq); Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);