Method init

smallthinker/tools/server/server.cpp:2030–2094

    }

    void init() {
        const int32_t n_ctx_slot = n_ctx / params_base.n_parallel;

        SRV_INF("initializing slots, n_slots = %d\n", params_base.n_parallel);

        for (int i = 0; i < params_base.n_parallel; i++) {
            server_slot slot;

            slot.id = i;
            slot.ctx = ctx;
            slot.n_ctx = n_ctx_slot;
            slot.n_predict = params_base.n_predict;
            slot.mctx = mctx;
            slot.cache_tokens.has_mtmd = mctx != nullptr;

            if (model_dft) {
                slot.batch_spec = llama_batch_init(params_base.speculative.n_max + 1, 0, 1);

                slot.ctx_dft = llama_init_from_model(model_dft, cparams_dft);
                if (slot.ctx_dft == nullptr) {
                    SRV_ERR("%s", "failed to create draft context\n");
                    return;
                }

                slot.spec = common_speculative_init(slot.ctx_dft);
                if (slot.spec == nullptr) {
                    SRV_ERR("%s", "failed to create speculator\n");
                    return;
                }
            }

            SLT_INF(slot, "new slot n_ctx_slot = %d\n", slot.n_ctx);

            slot.params.sampling = params_base.sampling;

            slot.callback_on_release = [this](int) {
                queue_tasks.pop_deferred_task();
            };

            slot.reset();

            slots.push_back(std::move(slot));
        }

        default_generation_settings_for_props = slots[0].to_json();

        // the update_slots() logic will always submit a maximum of n_batch or n_parallel tokens
        // note that n_batch can be > n_ctx (e.g. for non-causal attention models such as BERT where the KV cache is not used)
        {
            const int32_t n_batch = llama_n_batch(ctx);
            batch = llama_batch_init(std::max(n_batch, params_base.n_parallel), 0, 1);
        }

        metrics.init();

        oai_parser_opt = {
            /* use_jinja             */ params_base.use_jinja,
            /* prefill_assistant     */ params_base.prefill_assistant,