Method llm_build_gemma3

subprojects/llama.cpp/src/models/gemma3.cpp:4–152

template <bool iswa>
llm_build_gemma3<iswa>::llm_build_gemma3(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
    const int64_t n_embd_head = hparams.n_embd_head_k;

    ggml_tensor * cur;
    ggml_tensor * inpL;

    inpL = build_inp_embd(model.tok_embd);

    // important: do not normalize weights for raw embeddings input (i.e. encoded image emdeddings)
    inpL = ggml_scale(ctx0, inpL, ubatch.token ? sqrtf(n_embd) : 1.0f);
    cb(inpL, "inp_scaled", -1);

    // inp_pos - contains the positions
    ggml_tensor * inp_pos = build_inp_pos();

    // TODO: is causal == true correct? might need some changes
    using inp_attn_type = std::conditional_t<iswa, llm_graph_input_attn_kv_iswa, llm_graph_input_attn_kv>;
    inp_attn_type * inp_attn = nullptr;

    if constexpr (iswa) {
        inp_attn = build_attn_inp_kv_iswa();
    } else {
        inp_attn = build_attn_inp_kv();
    }

    ggml_tensor * inp_out_ids = build_inp_out_ids();

    for (int il = 0; il < n_layer; ++il) {
        float freq_base_l  = 0.0f;
        float freq_scale_l = 0.0f;

        if constexpr (iswa) {
            freq_base_l  = model.get_rope_freq_base (cparams, il);
            freq_scale_l = model.get_rope_freq_scale(cparams, il);
        } else {
            freq_base_l  = freq_base;
            freq_scale_l = freq_scale;
        }

        // norm
        cur = build_norm(inpL, model.layers[il].attn_norm, NULL, LLM_NORM_RMS, il);
        cb(cur, "attn_norm", il);

        // self-attention
        {
            // compute Q and K and RoPE them
            ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
            cb(Qcur, "Qcur", il);

            ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
            cb(Kcur, "Kcur", il);

            ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);
            cb(Vcur, "Vcur", il);

            Qcur = ggml_reshape_3d(ctx0, Qcur, n_embd_head, n_head,    n_tokens);
            Kcur = ggml_reshape_3d(ctx0, Kcur, n_embd_head, n_head_kv, n_tokens);
            Vcur = ggml_reshape_3d(ctx0, Vcur, n_embd_head, n_head_kv, n_tokens);