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
@@ -141,7 +141,7 @@ ggml_tensor * llm_build_plamo2::build_plamo2_attn_layer(llm_graph_input_attn_kv
                             ext_factor, attn_factor, beta_fast, beta_slow);

        cur = build_attn(inp,
-            model.layers[il].wo, NULL,
+            model.layers[il].wo, NULL, model.layers[il].wo_s,
            Qcur, Kcur, Vcur, NULL, NULL, NULL, 1.0f / sqrtf(float(n_embd_head_v)), il);
    }