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
@@ -73,7 +73,7 @@ llm_build_plamo3<iswa>::llm_build_plamo3(const llama_model & model, const llm_gr
        const float attn_scale = 1.0f / sqrtf(float(head_dim_q));

        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, attn_scale, il);
        cb(cur, "attn_out", il);