#include "models.h"

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);

            cb(Vcur, "Vcur", il);

            if (model.layers[il].bv) {

                Vcur = ggml_add(ctx0, Vcur, model.layers[il].bv);

                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, rope_factors, 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, rope_factors, 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);

            cur = build_attn(inp_attn,

                    model.layers[il].wo, model.layers[il].bo,

                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, kq_scale, il);

        }

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

            cur   = ggml_get_rows(ctx0, cur, inp_out_ids);

            inpSA = ggml_get_rows(ctx0, inpSA, inp_out_ids);

        }

        // FFN-free layer of Llama-3_1-Nemotron-Ultra-253B

        if (n_ff == 0) {

            continue;

        }

        // modified to support attention-free layer of Llama-3_1-Nemotron-51B

        ggml_tensor * ffn_inp = cur;

        if (n_head > 0) {

            ffn_inp = ggml_add(ctx0, cur, inpSA);

            cb(ffn_inp, "ffn_inp", il);

        }

        // feed-forward network

        if (model.layers[il].ffn_gate_inp == nullptr) {

            cur = build_norm(ffn_inp, model.layers[il].ffn_norm, NULL, LLM_NORM_RMS, il);

            cb(cur, "ffn_norm", il);

            cur = build_ffn(cur,

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

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

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

                NULL, LLM_FFN_SILU, LLM_FFN_PAR, il);

            cb(cur, "ffn_out", il);

        }

        cur = ggml_add(ctx0, cur, ffn_inp);

        cb(cur, "ffn_out", il);

        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);

}