Method build_qkvz

subprojects/llama.cpp/src/models/qwen3next.cpp:536–616

}

std::pair<ggml_tensor *, ggml_tensor *> llm_build_qwen3next::build_qkvz(
                ggml_tensor * input,
                        int   il) {
    const int64_t d_inner      = hparams.ssm_d_inner;
    const int64_t n_seqs       = ubatch.n_seqs;
    const int64_t head_k_dim   = hparams.ssm_d_state;
    const int64_t num_k_heads  = hparams.ssm_n_group;
    const int64_t num_v_heads  = hparams.ssm_dt_rank;
    const int64_t head_v_dim   = d_inner / num_v_heads;
    const int64_t n_seq_tokens = ubatch.n_seq_tokens;

    if (model.layers[il].wqkv) {
        // optimized path
        ggml_tensor * qkv_mixed = build_lora_mm(model.layers[il].wqkv, input);
        qkv_mixed = ggml_reshape_3d(ctx0, qkv_mixed, qkv_mixed->ne[0], n_seq_tokens, n_seqs);
        cb(qkv_mixed, "linear_attn_qkv_mixed", il);

        ggml_tensor * z = build_lora_mm(model.layers[il].wqkv_gate, input);
        cb(z, "z", il);

        return { qkv_mixed, z };

    } else {
        // legacy (slower) path
        ggml_tensor * mixed_qkvz = build_lora_mm(model.layers[il].ssm_in, input);
        cb(mixed_qkvz, "linear_attn_mixed_qkvz", il);

        int64_t       qkvz_new_dim        = 2 * head_k_dim + 2 * head_v_dim * (num_v_heads / num_k_heads);
        ggml_tensor * mixed_qkvz_reshaped = ggml_reshape_4d(ctx0, mixed_qkvz, qkvz_new_dim, num_k_heads, n_seq_tokens, n_seqs);

        // Split mixed_qkvz into query, key, value, z
        int64_t split_sizes_qkvz[4] = {
            head_k_dim,                              // query size
            head_k_dim,                              // key size
            head_v_dim * num_v_heads / num_k_heads,  // value size
            head_v_dim * num_v_heads / num_k_heads   // z size
        };

        ggml_tensor * query =
            ggml_view_4d(ctx0, mixed_qkvz_reshaped, split_sizes_qkvz[0], num_k_heads, n_seq_tokens, n_seqs,
                        mixed_qkvz_reshaped->nb[1], mixed_qkvz_reshaped->nb[2], mixed_qkvz_reshaped->nb[3], 0);
        cb(query, "q", il);

        ggml_tensor * key = ggml_view_4d(ctx0, mixed_qkvz_reshaped, split_sizes_qkvz[1], num_k_heads, n_seq_tokens, n_seqs,
                                        mixed_qkvz_reshaped->nb[1], mixed_qkvz_reshaped->nb[2], mixed_qkvz_reshaped->nb[3],
                                        split_sizes_qkvz[0] * ggml_element_size(mixed_qkvz_reshaped));
        cb(key, "k", il);

        ggml_tensor * value =
            ggml_view_4d(ctx0, mixed_qkvz_reshaped, split_sizes_qkvz[2], num_k_heads, n_seq_tokens, n_seqs,
                        mixed_qkvz_reshaped->nb[1], mixed_qkvz_reshaped->nb[2], mixed_qkvz_reshaped->nb[3],
                        (split_sizes_qkvz[0] + split_sizes_qkvz[1]) * ggml_element_size(mixed_qkvz_reshaped));
        cb(value, "v", il);

        ggml_tensor * z = ggml_view_4d(ctx0, mixed_qkvz_reshaped, split_sizes_qkvz[3], num_k_heads, n_seq_tokens, n_seqs,
                                    mixed_qkvz_reshaped->nb[1], mixed_qkvz_reshaped->nb[2], mixed_qkvz_reshaped->nb[3],
                                    (split_sizes_qkvz[0] + split_sizes_qkvz[1] + split_sizes_qkvz[2]) * ggml_element_size(mixed_qkvz_reshaped));
        z = ggml_cont(ctx0, z);