LLM inference in C/C++
C++ ggml
model : register t_layer_inp for qwen3next (#25141)
Jürgen Schmied4f31eedb0ccf
diff --git a/src/models/qwen3next.cpp b/src/models/qwen3next.cppindex 97200a4407..09b66423d5 100644--- a/src/models/qwen3next.cpp+++ b/src/models/qwen3next.cpp@@ -121,6 +121,8 @@ llama_model_qwen3next::graph::graph(const llama_model & model, const llm_graph_pggml_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 = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il);