tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : deci : support ffn-free with attention (#13296)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-05-07 12:49:27 +02:00
committed by GitHub
parent 39e73ae0d6
commit bc4e1128f7
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-model.cpp
View File

@ -4792,7 +4792,7 @@ struct llm_build_deci : public llm_graph_context {
}
// FFN-free layer of Llama-3_1-Nemotron-Ultra-253B
if (n_head == 0 && n_ff == 0) {
if (n_ff == 0) {
continue;
}