#pragma once

#include "llama-batch.h"
#include "llama-graph.h"
#include "llama-kv-cells.h"
#include "llama-memory.h"

#include <unordered_map>
#include <vector>

struct llama_cparams;
struct llama_hparams;
struct llama_model;
struct llama_context;

//
// llama_kv_cache_unified
//

class llama_kv_cache_unified : public llama_memory_i {
public:
    static uint32_t get_padding(const llama_cparams & cparams);

    // this callback is used to filter out layers that should not be included in the cache
    using layer_filter_cb = std::function<bool(int32_t il)>;

    struct defrag_info {
        bool empty() const {
            return ids.empty();
        }

        // contains information about which cell moves where:
        //  - cell i moves to ids[i]
        //  - if ids[i] == i || ids[i] == ids.size(), then cell i is not moved
        std::vector<uint32_t> ids;
    };

    // for each ubatch, create a slot_info that contains information about where the ubatch should be inserted in the
    //   KV cells. for example, cell indices for each token, such that: token[i] -> goes to cells[idxs[i]]
    struct slot_info {
        // data for lm_ggml_set_rows
        using idx_vec_t = std::vector<uint32_t>;

        idx_vec_t idxs;

        uint32_t head() const {
            return idxs.at(0);
        }

        bool empty() const {
            return idxs.empty();
        }

        void clear() {
            idxs.clear();
        }

        // TODO: implement
        //std::vector<idx_vec_t> seq_idxs;
    };

    using slot_info_vec_t = std::vector<slot_info>;

    llama_kv_cache_unified(
            const llama_model &  model,
              layer_filter_cb && filter,
                    lm_ggml_type    type_k,
                    lm_ggml_type    type_v,
                         bool    v_trans,
                         bool    offload,
                     uint32_t    kv_size,
                     uint32_t    n_seq_max,
                     uint32_t    n_pad,
                     uint32_t    n_swa,
               llama_swa_type    swa_type);

    ~llama_kv_cache_unified() = default;

    //
    // llama_memory_i
    //

    llama_memory_context_ptr init_batch(
            llama_batch_allocr & balloc,
            uint32_t n_ubatch,
            bool embd_all) override;

    llama_memory_context_ptr init_full() override;

    llama_memory_context_ptr init_update(llama_context * lctx, bool optimize) override;

    bool get_can_shift() const override;

    void clear(bool data) override;

    bool seq_rm  (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1) override;
    void seq_cp  (llama_seq_id seq_id_src, llama_seq_id seq_id_dst, llama_pos p0, llama_pos p1) override;
    void seq_keep(llama_seq_id seq_id)                                                          override;
    void seq_add (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1, llama_pos shift) override;
    void seq_div (llama_seq_id seq_id,                              llama_pos p0, llama_pos p1, int d) override;

    llama_pos seq_pos_min(llama_seq_id seq_id) const override;
    llama_pos seq_pos_max(llama_seq_id seq_id) const override;

    // state write/load

    void state_write(llama_io_write_i & io, llama_seq_id seq_id = -1) const override;
    void state_read (llama_io_read_i  & io, llama_seq_id seq_id = -1)       override;

    //
    // llama_kv_cache_unified specific API
    //

    uint32_t get_size() const;

    bool get_has_shift() const;

    //
    // graph_build API
    //

    uint32_t get_n_kv() const;

    // get views of the current state of the cache
    lm_ggml_tensor * get_k(lm_ggml_context * ctx, int32_t il, uint32_t n_kv) const;
    lm_ggml_tensor * get_v(lm_ggml_context * ctx, int32_t il, uint32_t n_kv) const;

    // store k_cur and v_cur in the cache based on the provided head location
    lm_ggml_tensor * cpy_k(lm_ggml_context * ctx, lm_ggml_tensor * k_cur, lm_ggml_tensor * k_idxs, int32_t il, const slot_info & sinfo) const;
    lm_ggml_tensor * cpy_v(lm_ggml_context * ctx, lm_ggml_tensor * v_cur, lm_ggml_tensor * v_idxs, int32_t il, const slot_info & sinfo) const;

    //
    // preparation API
    //

    // find places for the provided ubatches in the cache, returns the slot infos
    // return empty vector on failure
    slot_info_vec_t prepare(const std::vector<llama_ubatch> & ubatches);

    bool update(llama_context * lctx, bool do_shift, const defrag_info & dinfo);

    // find a slot of kv cells that can hold the ubatch
    // if cont == true, then the slot must be continuous
    // return empty slot_info on failure
    slot_info find_slot(const llama_ubatch & ubatch, bool cont) const;

    // emplace the ubatch context into slot: [sinfo.idxs[0...ubatch.n_tokens - 1]]
    void apply_ubatch(const slot_info & sinfo, const llama_ubatch & ubatch);

    //
    // input API
    //

    lm_ggml_tensor * build_input_k_idxs(lm_ggml_context * ctx, const llama_ubatch & ubatch) const;
    lm_ggml_tensor * build_input_v_idxs(lm_ggml_context * ctx, const llama_ubatch & ubatch) const;

    void set_input_k_idxs(lm_ggml_tensor * dst, const llama_ubatch * ubatch, const slot_info & sinfo) const;
    void set_input_v_idxs(lm_ggml_tensor * dst, const llama_ubatch * ubatch, const slot_info & sinfo) const;

    void set_input_kq_mask   (lm_ggml_tensor * dst, const llama_ubatch * ubatch, bool causal_attn) const;
    void set_input_k_shift   (lm_ggml_tensor * dst) const;
    void set_input_pos_bucket(lm_ggml_tensor * dst, const llama_ubatch * ubatch) const;

private:
    const llama_model & model;
    const llama_hparams & hparams;

    struct kv_layer {
        // layer index in the model
        // note: can be different from the layer index in the KV cache
        uint32_t il;

        lm_ggml_tensor * k;
        lm_ggml_tensor * v;
    };

    bool v_trans = true;  // the value tensor is transposed

    // the current index from where we start searching for a free slot in the ring buffer of KV cells (see find_slot())
    // note: this is not part of the KV state and it's only used to speed-up the find_slot() method
    uint32_t head = 0;

    const uint32_t n_seq_max = 1;

    // required padding
    const uint32_t n_pad = 1;

    // SWA
    const uint32_t n_swa = 0;

    // env: LLAMA_KV_CACHE_DEBUG
    int debug = 0;

    // env: LLAMA_SET_ROWS (temporary)
    // ref: https://github.com/ggml-org/llama.cpp/pull/14285
    int supports_set_rows = false;

    const llama_swa_type swa_type = LLAMA_SWA_TYPE_NONE;

    std::vector<lm_ggml_context_ptr>        ctxs;
    std::vector<lm_ggml_backend_buffer_ptr> bufs;

    llama_kv_cells_unified cells;

    std::vector<kv_layer> layers;

    // model layer id -> KV cache layer id
    std::unordered_map<int32_t, int32_t> map_layer_ids;

    // return non-empty vector if cells have been moved
    defrag_info defrag_prepare(int32_t n_max_nodes) const;

    size_t total_size() const;

    size_t size_k_bytes() const;
    size_t size_v_bytes() const;

    bool is_masked_swa(llama_pos p0, llama_pos p1) const;

    lm_ggml_tensor * build_rope_shift(
            const llama_cparams & cparams,
                   lm_ggml_context * ctx,
                    lm_ggml_tensor * cur,
                    lm_ggml_tensor * shift,
                    lm_ggml_tensor * factors,
                          float   freq_base,
                          float   freq_scale) const;

    llm_graph_result_ptr build_graph_shift(
            const llama_cparams & cparams,
                   lm_ggml_context * ctx,
                    lm_ggml_cgraph * gf) const;

    llm_graph_result_ptr build_graph_defrag(
            const llama_cparams & cparams,
                   lm_ggml_context * ctx,
                    lm_ggml_cgraph * gf,
              const defrag_info & dinfo) const;

    void state_write_meta(llama_io_write_i & io, const std::vector<std::pair<uint32_t, uint32_t>> & cell_ranges, llama_seq_id seq_id = -1) const;
    void state_write_data(llama_io_write_i & io, const std::vector<std::pair<uint32_t, uint32_t>> & cell_ranges) const;

    bool state_read_meta(llama_io_read_i & io, uint32_t cell_count, llama_seq_id dest_seq_id = -1);
    bool state_read_data(llama_io_read_i & io, uint32_t cell_count);
};

class llama_kv_cache_unified_context : public llama_memory_context_i {
public:
    // some shorthands
    using slot_info_vec_t = llama_kv_cache_unified::slot_info_vec_t;
    using defrag_info     = llama_kv_cache_unified::defrag_info;

    // used for errors
    llama_kv_cache_unified_context(llama_memory_status status);

    // used to create a full-cache context
    llama_kv_cache_unified_context(
            llama_kv_cache_unified * kv);

    // used to create an update context
    llama_kv_cache_unified_context(
            llama_kv_cache_unified * kv,
            llama_context * lctx,
            bool do_shift,
            defrag_info dinfo);

    // used to create a batch procesing context from a batch
    llama_kv_cache_unified_context(
            llama_kv_cache_unified * kv,
            slot_info_vec_t sinfos,
            std::vector<llama_ubatch> ubatches);

    virtual ~llama_kv_cache_unified_context();

    //
    // llama_memory_context_i
    //

    bool next()  override;
    bool apply() override;

    llama_memory_status  get_status() const override;
    const llama_ubatch & get_ubatch() const override;

    //
    // llama_kv_cache_unified_context specific API
    //

    uint32_t get_n_kv() const;

    // get views of the current state of the cache
    lm_ggml_tensor * get_k(lm_ggml_context * ctx, int32_t il) const;
    lm_ggml_tensor * get_v(lm_ggml_context * ctx, int32_t il) const;

    // store k_cur and v_cur in the cache based on the provided head location
    lm_ggml_tensor * cpy_k(lm_ggml_context * ctx, lm_ggml_tensor * k_cur, lm_ggml_tensor * k_idxs, int32_t il) const;
    lm_ggml_tensor * cpy_v(lm_ggml_context * ctx, lm_ggml_tensor * v_cur, lm_ggml_tensor * v_idxs, int32_t il) const;

    lm_ggml_tensor * build_input_k_idxs(lm_ggml_context * ctx, const llama_ubatch & ubatch) const;
    lm_ggml_tensor * build_input_v_idxs(lm_ggml_context * ctx, const llama_ubatch & ubatch) const;

    void set_input_k_idxs(lm_ggml_tensor * dst, const llama_ubatch * ubatch) const;
    void set_input_v_idxs(lm_ggml_tensor * dst, const llama_ubatch * ubatch) const;

    void set_input_k_shift   (lm_ggml_tensor * dst) const;
    void set_input_kq_mask   (lm_ggml_tensor * dst, const llama_ubatch * ubatch, bool causal_attn) const;
    void set_input_pos_bucket(lm_ggml_tensor * dst, const llama_ubatch * ubatch) const;

private:
    llama_memory_status status;

    llama_kv_cache_unified * kv;
    llama_context * lctx;

    //
    // update context
    //

    bool do_shift = false;

    defrag_info dinfo;

    //
    // batch processing context
    //

    // the index of the cur ubatch to process
    size_t i_cur = 0;

    slot_info_vec_t sinfos;

    std::vector<llama_ubatch> ubatches;

    //
    // data needed for building the compute graph for the current ubatch:
    //

    // a heuristic, to avoid attending the full cache if it is not yet utilized
    // as the cache gets filled, the benefit from this heuristic disappears
    int32_t n_kv;
};