#include "models.h"

template <bool iswa>

llm_build_smallthinker<iswa>::llm_build_smallthinker(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();

    using inp_attn_type = std::conditional_t<iswa, llm_graph_input_attn_kv_iswa, llm_graph_input_attn_kv>;

    inp_attn_type * inp_attn = nullptr;

    if constexpr (iswa) {

        inp_attn = build_attn_inp_kv_iswa();

    } else {

        inp_attn = build_attn_inp_kv();

    }

    ggml_tensor * inp_out_ids = build_inp_out_ids();

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

        ggml_tensor * inpSA  = inpL;

        // This overlaps with SWA layers in current models, so get_rope_freq_base/scale may be superfluous

        const bool use_rope = hparams.n_no_rope_layer_step == n_layer ||

                              il % hparams.n_no_rope_layer_step != 0;

        ggml_tensor * probs = build_lora_mm(model.layers[il].ffn_gate_inp, inpL);  // [n_expert, n_tokens]

        cb(probs, "ffn_moe_logits", 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

            struct ggml_tensor * Qcur = build_lora_mm(model.layers[il].wq, cur);

            cb(Qcur, "Qcur", il);

            struct ggml_tensor * Kcur = build_lora_mm(model.layers[il].wk, cur);

            cb(Kcur, "Kcur", il);

            struct 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);

            if (use_rope) {

                Qcur = ggml_rope_ext(ctx0, Qcur, inp_pos, nullptr, n_rot, 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, 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);

            cur = build_attn(inp_attn,

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

                    Qcur, Kcur, Vcur, nullptr, nullptr, nullptr, 1.0f / sqrtf(float(n_embd_head)), 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);

            probs = ggml_get_rows(ctx0, probs, inp_out_ids);

        }

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

        cb(ffn_inp, "ffn_inp", il);

        // MoE branch

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

        cb(cur, "ffn_norm", il);

        ggml_tensor * ffn_out =

            build_moe_ffn(cur,

                    nullptr,

                    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_RELU, true,

                    false, 0.0,

                    static_cast<llama_expert_gating_func_type>(hparams.expert_gating_func),

                    il, probs);

        cb(ffn_out, "ffn_out", il);

        cur = ffn_out;

        cur = ggml_add(ctx0, cur, ffn_inp);

        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);

}

Unexecuted instantiation: llm_build_smallthinker<false>::llm_build_smallthinker(llama_model const&, llm_graph_params const&)

Unexecuted instantiation: llm_build_smallthinker<true>::llm_build_smallthinker(llama_model const&, llm_graph_params const&)

// Explicit template instantiations

template struct llm_build_smallthinker<false>;

template struct llm_build_smallthinker<true>;