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

Fixed embd when offloading non-repeating layers

Browse source
This commit is contained in:
JohannesGaessler 2023-06-16 15:34:46 +02:00
parent a09f9195be
commit 1170a95732
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -1654,7 +1654,7 @@ static bool llama_eval_internal(
// cur = cur*norm(broadcasted) // cur = cur*norm(broadcasted)
cur = ggml_mul(ctx0, cur, model.norm); cur = ggml_mul(ctx0, cur, model.norm);
offload_func_nr(cur); // offload_func_nr(cur); // TODO CPU + GPU mirrored backend
ggml_set_name(cur, "result_norm"); ggml_set_name(cur, "result_norm");
embeddings = cur; embeddings = cur;