#include "models.h"

void llama_model_maple::load_arch_hparams(llama_model_loader & ml) {
    hparams.swa_type = LLAMA_SWA_TYPE_STANDARD;

    ml.get_key(LLM_KV_ATTENTION_LAYERNORM_RMS_EPS, hparams.f_norm_rms_eps);
    ml.get_key(LLM_KV_ATTENTION_SLIDING_WINDOW,    hparams.n_swa);
    ml.get_key_or_arr(LLM_KV_EXPERT_FEED_FORWARD_LENGTH, hparams.n_ff_exp_arr, hparams.n_layer_all);

    ml.get_arr(LLM_KV_ATTENTION_SLIDING_WINDOW_PATTERN, hparams.is_swa_impl);

    hparams.rope_freq_base_train_swa  = hparams.rope_freq_base_train;
    hparams.rope_freq_scale_train_swa = hparams.rope_freq_scale_train;
    ml.get_key(LLM_KV_ROPE_FREQ_BASE_SWA, hparams.rope_freq_base_train_swa, false);

    ml.get_key_or_arr(LLM_KV_SWIGLU_CLAMP_EXP, hparams.swiglu_clamp_exp, hparams.n_layer_all);

    switch (hparams.n_layer()) {
        case 24: type = LLM_TYPE_20B; break;
        default: type = LLM_TYPE_UNKNOWN;
    }
}

void llama_model_maple::load_arch_tensors(llama_model_loader &) {
    LLAMA_LOAD_LOCALS;

    const int64_t n_ff_exp = hparams.n_ff_exp();
    const int64_t head_dim = hparams.n_embd_head_k();

    tok_embd = create_tensor(tn(LLM_TENSOR_TOKEN_EMBD, "weight"), {n_embd, n_vocab}, 0);

    output_norm = create_tensor(tn(LLM_TENSOR_OUTPUT_NORM, "weight"), {n_embd}, 0);
    output      = create_tensor(tn(LLM_TENSOR_OUTPUT,      "weight"), {n_embd, n_vocab}, 0);

    if (n_expert == 0) {
        throw std::runtime_error("n_expert must be > 0 for Maple");
    }
    if (n_expert_used == 0) {
        throw std::runtime_error("n_expert_used must be > 0 for Maple");
    }

    for (int i = 0; i < n_layer; ++i) {
        auto & layer = layers[i];

        layer.attn_norm = create_tensor(tn(LLM_TENSOR_ATTN_NORM, "weight", i), {n_embd}, 0);

        create_tensor_qkv(layer, i, n_embd, n_head * head_dim, n_head_kv * head_dim, n_head_kv * head_dim, 0);
        layer.wo = create_tensor(tn(LLM_TENSOR_ATTN_OUT, "weight", i), {n_head * head_dim, n_embd}, 0);

        layer.attn_q_norm = create_tensor(tn(LLM_TENSOR_ATTN_Q_NORM, "weight", i), {head_dim}, 0);
        layer.attn_k_norm = create_tensor(tn(LLM_TENSOR_ATTN_K_NORM, "weight", i), {head_dim}, 0);
        layer.ffn_norm    = create_tensor(tn(LLM_TENSOR_FFN_NORM,    "weight", i), {n_embd}, 0);

        layer.ffn_gate_inp  = create_tensor(tn(LLM_TENSOR_FFN_GATE_INP,  "weight", i), {n_embd, n_expert}, 0);
        layer.ffn_gate_exps = create_tensor(tn(LLM_TENSOR_FFN_GATE_EXPS, "weight", i), {n_embd, n_ff_exp, n_expert}, 0);
        layer.ffn_down_exps = create_tensor(tn(LLM_TENSOR_FFN_DOWN_EXPS, "weight", i), {n_ff_exp, n_embd, n_expert}, 0);
        layer.ffn_up_exps   = create_tensor(tn(LLM_TENSOR_FFN_UP_EXPS,   "weight", i), {n_embd, n_ff_exp, n_expert}, 0);
    }
}

std::unique_ptr<llm_graph_context> llama_model_maple::build_arch_graph(const llm_graph_params & params) const {
    return std::make_unique<graph>(*this, params);
}

llama_model_maple::graph::graph(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_ASSERT(n_embd_head == hparams.n_embd_head_v());

    ggml_tensor * inpL = build_inp_embd(model.tok_embd);
    ggml_tensor * inp_pos = build_inp_pos();
    auto * inp_attn = build_attn_inp_kv_iswa();
    ggml_tensor * inp_out_ids = build_inp_out_ids();

    for (int il = 0; il < n_layer; ++il) {
        ggml_tensor * inpSA = inpL;

        ggml_tensor * cur = build_norm(inpL, model.layers[il].attn_norm, nullptr, LLM_NORM_RMS, il);
        cb(cur, "attn_norm", il);

        {
            auto [Qcur, Kcur, Vcur] = build_qkv(model.layers[il], cur, n_embd_head, n_head, n_head_kv, il);

            Qcur = build_norm(Qcur, model.layers[il].attn_q_norm, nullptr, LLM_NORM_RMS, il);
            Kcur = build_norm(Kcur, model.layers[il].attn_k_norm, nullptr, LLM_NORM_RMS, il);
            cb(Qcur, "Qcur_normed", il);
            cb(Kcur, "Kcur_normed", il);

            if (hparams.is_swa(il)) {
                const int64_t n_rot_l = hparams.n_rot(il);
                const float freq_base_l = model.get_rope_freq_base(cparams, il);
                const float freq_scale_l = model.get_rope_freq_scale(cparams, il);

                Qcur = ggml_rope_ext(ctx0, Qcur, inp_pos, nullptr, n_rot_l, rope_type, n_ctx_orig, freq_base_l,
                                     freq_scale_l, ext_factor, attn_factor, beta_fast, beta_slow);
                Kcur = ggml_rope_ext(ctx0, Kcur, inp_pos, nullptr, n_rot_l, rope_type, n_ctx_orig, freq_base_l,
                                     freq_scale_l, 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, nullptr, model.layers[il].wo_s,
                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), il);
            cb(cur, "attn_out", 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);
        }

        ggml_tensor * ffn_inp = ggml_add(ctx0, cur, inpSA);
        cb(ffn_inp, "ffn_inp", il);

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

        cur = build_moe_ffn(cur,
                model.layers[il].ffn_gate_inp,
                model.layers[il].ffn_up_exps,
                model.layers[il].ffn_gate_exps,
                model.layers[il].ffn_down_exps,
                nullptr,
                n_expert, n_expert_used,
                LLM_FFN_SILU, true,
                1.0f,
                LLAMA_EXPERT_GATING_FUNC_TYPE_SOFTMAX,
                il);
        cb(cur, "ffn_moe_out", il);

        cur = ggml_add(ctx0, cur, ffn_inp);
        cur = build_cvec(cur, il);
        cb(cur, "l_out", il);

        inpL = cur;
    }

    ggml_tensor * cur = build_norm(inpL, model.output_norm, nullptr, LLM_NORM_RMS, -1);
    cb(cur, "result_norm", -1);
    res->t_embd = cur;

    cur = build_lora_mm(model.output, cur, model.output_s);
    cb(cur, "result_output", -1);
    res->t_logits = cur;

    ggml_build_forward_expand(gf, cur);
}