Method _shared_load_model

src/common/AutoModel/automodel.cpp:114–145

void AutoModel::_shared_load_model(std::string model_path, json model_info, int default_context_length, bool enable_preemption) {
    if (this->is_model_loaded && this->model_path == model_path) {
        header_print("FLM", "Model already loaded: " << this->model_path);
        return;
    }

    this->model_path = model_path;
    header_print("FLM", "Loading model: " << this->model_path);
    this->lm_config = std::make_unique<LM_Config>();
    this->lm_config->from_pretrained(this->model_path);
    if (this->npu_device_inst == nullptr) {
        header_print("ERROR", "NPU device instance is nullptr");
        exit(1);
    }
    this->npu = std::make_unique<npu_xclbin_manager>(npu_device::device_npu2, this->npu_device_inst, enable_preemption);
    this->enable_preemption = enable_preemption;
    // Set context length: use provided value if not -1, otherwise use model default
    if (default_context_length != -1) {
        this->MAX_L = default_context_length;
    } else {
        this->MAX_L = model_info["default_context_length"];
    }
    
    this->is_model_loaded = true;

    this->token_history.clear();
    this->token_history.reserve(this->MAX_L);
    this->tokenizer = std::make_unique<Tokenizer>(this->model_path);

    this->last_token = -1;
    this->total_tokens = 0;
}

bool AutoModel::_shared_insert(chat_meta_info_t& meta_info, std::vector<int>& tokens, std::function<bool()> is_cancelled, void* payload, int first_len_run) {