Commit 330f0189c for llama.cpp

commit 330f0189c9fc71ef631f40211660a87d99251cc1
Author: Daniel Bevenius <daniel.bevenius@gmail.com>
Date:   Wed Nov 4 21:29:50 2026 -0800

    qwen2 : add nvfp4 scales to build_ffn (#31657)

    This commit adds nvfp4 scales to qwen2's build_ffn call which are
    currently passed as NULL.

    The motivation for this is that a model converted to NVFP4 will
    currently crash because the scales are loaded but never applied in
    the FFN:
    ```console
    llama-completion: llama.cpp/src/llama-sampler.cpp:1218:
    void llama_sampler_dist_apply(llama_sampler*, llama_token_data_array*):
    Assertion `found' failed.
    ```
    The attention already applies its scales but ffn is missing them.

diff --git a/src/models/qwen2.cpp b/src/models/qwen2.cpp
index d2cd8e22d..8602c7831 100644
--- a/src/models/qwen2.cpp
+++ b/src/models/qwen2.cpp
@@ -117,9 +117,9 @@ llama_model_qwen2::graph::graph(const llama_model & model, const llm_graph_param
         cb(cur, "ffn_norm", il);

         cur = build_ffn(cur,
-                model.layers[il].ffn_up,   NULL, NULL,
-                model.layers[il].ffn_gate, NULL, NULL,
-                model.layers[il].ffn_down, NULL, NULL,
+                model.layers[il].ffn_up,   NULL, model.layers[il].ffn_up_s,
+                model.layers[il].ffn_gate, NULL, model.layers[il].ffn_gate_s,
+                model.layers[il].ffn_down, NULL, model.layers[il].ffn_down_s,
                 NULL,
                 LLM_FFN_SILU, LLM_FFN_PAR, il);
         cb(cur, "ffn_out", il);