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
@@ -89,7 +89,7 @@ llm_build_llama<embed>::llm_build_llama(const llama_model & model, const llm_gra
                cb(Kcur, "Kcur_normed", il);
            }
            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);
            if (model.layers[il].wo_s) {
                cur = ggml_mul(ctx0, cur, model.layers[il].wo_s);