mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-28 12:25:03 +00:00
llama : deci : support ffn-free with attention (#13296)
This commit is contained in:
@ -4792,7 +4792,7 @@ struct llm_build_deci : public llm_graph_context {
|
|||||||
}
|
}
|
||||||
|
|
||||||
// FFN-free layer of Llama-3_1-Nemotron-Ultra-253B
|
// FFN-free layer of Llama-3_1-Nemotron-Ultra-253B
|
||||||
if (n_head == 0 && n_ff == 0) {
|
if (n_ff == 0) {
|
||||||
continue;
|
continue;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
Reference in New Issue
Block a user