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
@@ -179,7 +179,7 @@ ggml_tensor * llm_build_qwen35moe ::build_layer_attn(
    const float kq_scale = hparams.f_attention_scale == 0.0f ? 1.0f / sqrtf(float(n_embd_head)) : hparams.f_attention_scale;

    cur = build_attn(inp,
-                nullptr, nullptr,
+                nullptr, nullptr, nullptr,
                Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);
    cb(cur, "attn_pregate", il);