model : support NVFP4 tensors for Gemma4 (#21971)

* support nvfp4 tensors for Gemma4 * add wo_s to build_attn * add wo_s to build_attn * fix glm4
2026-04-16 16:51:47 +02:00
parent b572d1ecd6
commit f772f6e434
105 changed files with 149 additions and 148 deletions
@@ -116,7 +116,7 @@ ggml_tensor * llm_build_granite_hybrid::build_attention_layer(ggml_tensor *
    const float kq_scale =
        hparams.f_attention_scale == 0.0f ? 1.0f / sqrtf(float(n_embd_head)) : hparams.f_attention_scale;
    cur = build_attn(inp_attn,
-            model.layers[il].wo, model.layers[il].bo,
+            model.layers[il].wo, model.layers[il].bo, model.layers[il].wo_s,
            Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
    cb(cur, "attn_out", il);
    return cur;