Method build_falcon

llama.cpp:5326–5468

    }

    struct ggml_cgraph * build_falcon() {
        struct ggml_cgraph * gf = ggml_new_graph_custom(ctx0, LLAMA_MAX_NODES, false);

        struct ggml_tensor * cur;
        struct ggml_tensor * inpL;

        inpL = llm_build_inp_embd(ctx0, hparams, batch, model.tok_embd, cb);
        cb(inpL, "inp_embd", -1);

        // inp_pos - contains the positions
        struct ggml_tensor * inp_pos = ggml_new_tensor_1d(ctx0, GGML_TYPE_I32, n_tokens);
        cb(inp_pos, "inp_pos", -1);

        // KQ_scale
        struct ggml_tensor * KQ_scale = ggml_new_tensor_1d(ctx0, GGML_TYPE_F32, 1);
        cb(KQ_scale, "KQ_scale", -1);

        // KQ_mask (mask for 1 head, it will be broadcasted to all heads)
        struct ggml_tensor * KQ_mask = ggml_new_tensor_3d(ctx0, GGML_TYPE_F32, n_kv, n_tokens, 1);
        cb(KQ_mask, "KQ_mask", -1);

        // shift the entire K-cache if needed
        if (do_rope_shift) {
            llm_build_k_shift(ctx0, hparams, cparams, kv_self, gf, LLM_ROPE_NEOX, n_ctx, n_embd_head, freq_base, freq_scale, cb);
        }

        for (int il = 0; il < n_layer; ++il) {
            struct ggml_tensor * attn_norm;

            attn_norm = llm_build_norm(ctx0, inpL, hparams,
                    model.layers[il].attn_norm,
                    model.layers[il].attn_norm_b,
                    LLM_NORM, cb, il);

            // self-attention
            {
                if (model.layers[il].attn_norm_2) {
                    // Falcon-40B
                    cur = llm_build_norm(ctx0, inpL, hparams,
                            model.layers[il].attn_norm_2,
                            model.layers[il].attn_norm_2_b,
                            LLM_NORM, cb, il);
                    cb(cur, "attn_norm_2", il);
                } else {
                    cur = attn_norm;
                }

                cur = ggml_mul_mat(ctx0, model.layers[il].wqkv, cur);
                cb(cur, "wqkv", il);

                struct ggml_tensor * Qcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd,     n_tokens, cur->nb[1], 0*sizeof(float)*(n_embd)));
                struct ggml_tensor * Kcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd)));
                struct ggml_tensor * Vcur = ggml_cont(ctx0, ggml_view_2d(ctx0, cur, n_embd_gqa, n_tokens, cur->nb[1], 1*sizeof(float)*(n_embd + n_embd_gqa)));

                cb(Qcur, "Qcur", il);
                cb(Kcur, "Kcur", il);
                cb(Vcur, "Vcur", il);