aditya/llama.cpp
1
0
Fork 0
mirror of https://git.adityakumar.xyz/llama.cpp.git synced 2024-11-09 15:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

llama : fix embd when offloading non-repeating layers (#1891)

Browse source
This commit is contained in:
Johannes Gäßler 2023-06-16 20:25:51 +02:00 committed by GitHub
parent 5b9ccaf104
commit ac3b886953
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
llama.cpp
View file

@ -1658,7 +1658,7 @@ 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;