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
@@ -66,7 +66,7 @@ llm_build_lfm2<iswa>::llm_build_lfm2(const llama_model & model, const llm_graph_
                          attn_factor, beta_fast, beta_slow);

        cur = build_attn(inp_attn,
-                model.layers[il].wo, NULL,
+                model.layers[il].wo, NULL, model.layers[il].wo_s,
                q, k, v, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), il);

        cb(cur, "model.layers.{}.self_attn.out_proj", il);