#include "models.h"

llm_build_gemma::llm_build_gemma(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_tensor * cur;

    ggml_tensor * inpL;

    inpL = build_inp_embd(model.tok_embd);

    inpL = ggml_scale(ctx0, inpL, sqrtf(n_embd));

    cb(inpL, "inp_scaled", -1);

    // inp_pos - contains the positions

    ggml_tensor * inp_pos = build_inp_pos();

    auto * inp_attn = build_attn_inp_kv();

    ggml_tensor * inp_out_ids = build_inp_out_ids();

    for (int il = 0; il < n_layer; ++il) {

        // 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);

            Qcur = ggml_rope_ext(

                    ctx0, Qcur, inp_pos, nullptr,

                    n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,

                    ext_factor, attn_factor, beta_fast, beta_slow);

            Kcur = ggml_rope_ext(

                    ctx0, Kcur, inp_pos, nullptr,

                    n_rot, rope_type, n_ctx_orig, freq_base, freq_scale,

                    ext_factor, attn_factor, beta_fast, beta_slow);

            cb(Qcur, "Qcur", il);

            cb(Kcur, "Kcur", il);

            cb(Vcur, "Vcur", il);

            Qcur = ggml_scale(ctx0, Qcur, 1.0f / sqrtf(float(n_embd_head)));

            cb(Qcur, "Qcur_scaled", il);

            cur = build_attn(inp_attn,

                    model.layers[il].wo, NULL,

                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f, il);

        }

        if (il == n_layer - 1 && inp_out_ids) {

            cur  = ggml_get_rows(ctx0,  cur, inp_out_ids);

            inpL = ggml_get_rows(ctx0, inpL, inp_out_ids);

        }

        ggml_tensor * sa_out = ggml_add(ctx0, cur, inpL);

        cb(sa_out, "sa_out", il);

        cur = build_norm(sa_out,

                model.layers[il].ffn_norm, NULL,

                LLM_NORM_RMS, il);

        cb(cur, "ffn_norm", il);

        // feed-forward network

        {

            cur = build_ffn(cur,

                    model.layers[il].ffn_up,   NULL, NULL,

                    model.layers[il].ffn_gate, NULL, NULL,

                    model.layers[il].ffn_down, NULL, NULL,

                    NULL,

                    LLM_FFN_GELU, LLM_FFN_PAR, il);

            cb(cur, "ffn_out", il);

        }

        cur = ggml_add(ctx0, cur, sa_out);

        cur = build_cvec(cur, il);

        cb(cur, "l_out", il);

        // input for next layer

        inpL = cur;

    }

    cur = inpL;

    cur = build_norm(cur,

            model.output_norm, NULL,

            LLM_NORM_RMS, -1);

    cb(cur, "result_norm", -1);

    res->t_embd = cur;

    // lm_head

    cur = build_lora_mm(model.output, cur);

    cb(cur, "result_output", -1);

    res->t_logits = cur;

    ggml_build_forward_expand(gf, cur);

}