Class server_slot

smallthinker/tools/server/server.cpp:1221–1497

};

struct server_slot {
    int id;
    int id_task = -1;

    // only used for completion/embedding/infill/rerank
    server_task_type task_type = SERVER_TASK_TYPE_COMPLETION;

    llama_batch batch_spec = {};

    llama_context * ctx = nullptr;
    llama_context * ctx_dft = nullptr;

    // multimodal
    mtmd_context * mctx = nullptr;

    common_speculative * spec = nullptr;

    std::vector<common_adapter_lora_info> lora;

    // the index relative to completion multi-task request
    size_t index = 0;

    struct slot_params params;

    slot_state state = SLOT_STATE_IDLE;

    // used to determine the slot that has been used the longest
    int64_t t_last_used = -1;

    // generation props
    int32_t n_ctx       = 0;  // context size per slot
    int32_t n_past      = 0;
    int32_t n_decoded   = 0;
    int32_t n_remaining = -1;
    int32_t i_batch     = -1;
    int32_t n_predict   = -1; // TODO: disambiguate from params.n_predict

    // n_prompt_tokens may not be equal to prompt_tokens.size(), because prompt maybe truncated
    int32_t n_prompt_tokens           = 0;
    int32_t n_prompt_tokens_processed = 0;

    // input prompt tokens
    server_tokens prompt_tokens;

    size_t last_nl_pos = 0;

    std::string  generated_text;
    llama_tokens generated_tokens;
    common_chat_msg chat_msg;

    server_tokens cache_tokens;

    std::vector<completion_token_output> generated_token_probs;

    bool has_next_token = true;
    bool has_new_line   = false;
    bool truncated      = false;
    stop_type stop;