Method llm_build_deci

subprojects/llama.cpp/src/models/deci.cpp:5–135

llm_build_deci::llm_build_deci(const llama_model & model, const llm_graph_params & params) : llm_graph_context(params) {
    const int64_t n_embd_head = hparams.n_embd_head_v;

    GGML_ASSERT(n_embd_head == hparams.n_embd_head_k);
    GGML_ASSERT(n_embd_head == hparams.n_rot);

    ggml_tensor * cur;
    ggml_tensor * inpL;

    inpL = build_inp_embd(model.tok_embd);

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

    auto * inp_attn = build_attn_inp_kv();

    const float kq_scale =
        hparams.f_attention_scale == 0.0f ? 1.0f / sqrtf(float(n_embd_head)) : hparams.f_attention_scale;

    ggml_tensor * inp_out_ids = build_inp_out_ids();

    for (int il = 0; il < n_layer; ++il) {
        ggml_tensor * inpSA     = inpL;
        const int64_t n_head_kv = hparams.n_head_kv(il);
        const int64_t n_head    = hparams.n_head(il);
        const int64_t n_ff      = hparams.n_ff(il);

        if (n_head == 0) {
            // attention-free layer of Llama-3_1-Nemotron-51B
            cur = inpL;
        } else {
            // norm
            cur = build_norm(inpL, model.layers[il].attn_norm, NULL, LLM_NORM_RMS, il);
            cb(cur, "attn_norm", il);
        }
        if (n_head > 0 && n_head_kv == 0) {
            // "linear attention" of Llama-3_1-Nemotron-51B
            cur = build_lora_mm(model.layers[il].wo, cur);
            cb(cur, "wo", il);
        } else if (n_head > 0) {
            // self-attention
            // rope freq factors for llama3; may return nullptr for llama2 and other models
            ggml_tensor * rope_factors = model.get_rope_factors(cparams, il);

            // compute Q and K and RoPE them
            ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);
            cb(Qcur, "Qcur", il);
            if (model.layers[il].bq) {
                Qcur = ggml_add(ctx0, Qcur, model.layers[il].bq);
                cb(Qcur, "Qcur", il);
            }
            ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);
            cb(Kcur, "Kcur", il);
            if (model.layers[il].bk) {
                Kcur = ggml_add(ctx0, Kcur, model.layers[il].bk);
                cb(Kcur, "Kcur", il);
            }
            ggml_tensor * Vcur = build_lora_mm(model.layers[il].wv, cur);