Skip to content

LLM inference in C/C++

C++ ggml

spec: add Minimax2 eagle3 support

Adrian259ae1df8b52
diff --git a/src/models/minimax-m2.cpp b/src/models/minimax-m2.cpp
index b25435e4d9..86a8ae2b1d 100644
--- a/src/models/minimax-m2.cpp
+++ b/src/models/minimax-m2.cpp
@@ -60,6 +60,8 @@ llama_model_minimax_m2::graph::graph(const llama_model & model, const llm_graph_
ggml_tensor * inp_out_ids = build_inp_out_ids();
for (int il = 0; il < n_layer; ++il) {
+ res->t_layer_inp[il] = inpL;
+
ggml_tensor * inpSA = inpL;
cur = inpL;