Compare commits

..

1 Commits

Author SHA1 Message Date
Jürgen Schmied 4f31eedb0c model : register t_layer_inp for qwen3next (#25141)
* Fix input assignment in layer processing loop

Fix DFLASH for qwen-coder-next

* add line break

Added tensor for attention normalization in Qwen3 model.
2026-06-30 17:57:14 +02:00
+2
View File
@@ -121,6 +121,8 @@ llama_model_qwen3next::graph::graph(const llama_model & model, const llm_graph_p
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 = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il);