Commit 4df3f2959 for llama.cpp
commit 4df3f2959c159d1899d47dc521799f060b724552
Author: cherry77-cloud <1615405@qq.com>
Date: Tue Nov 17 18:32:30 2026 +0800
qwen3next : apply output projection weight scale (#32393)
Assisted-by: Codex
diff --git a/src/models/qwen3next.cpp b/src/models/qwen3next.cpp
index 110581bae..9546fba58 100644
--- a/src/models/qwen3next.cpp
+++ b/src/models/qwen3next.cpp
@@ -540,7 +540,7 @@ ggml_tensor * llama_model_qwen3next::graph::build_layer_attn_linear(
cb(final_output, "final_output", il);
// Output projection
- cur = build_lora_mm(model.layers[il].ssm_out, final_output);
+ cur = build_lora_mm(model.layers[il].ssm_out, final_output, model.layers[il].ssm_out_s);
cb(cur, "linear_attn_out", il);
return cur;