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
@@ -61,7 +61,7 @@ llm_build_gemma2_iswa::llm_build_gemma2_iswa(const llama_model & model, const ll
            Qcur = ggml_scale(ctx0, Qcur, hparams.f_attention_scale);

            cur = build_attn(inp_attn,
-                    model.layers[il].wo, NULL,
+                    model.layers[il].wo, NULL, model.layers[il].wo_s,
                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f, il);
        }
        if (il == n_layer - 1 && inp_out_ids) {