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
@@ -52,7 +52,7 @@ llm_build_falcon_h1::llm_build_falcon_h1(const llama_model & model, const llm_gr
        cb(Vcur, "Vcur-post-rope", il);

        ggml_tensor * attn_out = build_attn(inp->get_attn(),
-                                    model.layers[il].wo, NULL,
+                                    model.layers[il].wo, NULL, model.layers[il].wo_s,
                                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
        cb(attn_out, "attn_out", il);