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_bitnet::llm_build_bitnet(const llama_model & model, const llm_graph_pa
            cb(Vcur, "Vcur", il);

            cur = build_attn(inp_attn,
-                    NULL, NULL,
+                    NULL, NULL, NULL,
                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f/sqrtf(float(n_embd_head)), il);

            cur = build_norm(cur,