CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-31 08:51:55 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : fix incorrect Qwen2Moe ffn_moe_out graph callback (#12631)

Browse Source
This commit is contained in:
Sigbjørn Skjæret
2025-03-28 22:13:02 +01:00
committed by GitHub
parent b4ae50810e
commit 3714c3ee1a
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

@@ -6323,7 +6323,7 @@ struct llm_build_qwen2moe : public llm_graph_context {
false, 0.0, false, 0.0,
LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX, LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,
il); il);
cb(cur, "ffn_moe_out", il); cb(moe_out, "ffn_moe_out", il);
// FFN shared expert // FFN shared expert
{ {