Method synchronize

smallthinker/src/llama-context.cpp:350–378

}

void llama_context::synchronize() {
    ggml_backend_sched_synchronize(sched.get());

    // FIXME: if multiple single tokens are evaluated without a synchronization,
    // the stats will be added to the prompt evaluation stats
    // this should only happen when using batch size 1 to evaluate a batch

    // add the evaluation to the stats
    if (n_queued_tokens == 1) {
        if (!cparams.no_perf) {
            t_eval_us += ggml_time_us() - t_compute_start_us;
        }
        n_eval++;
    } else if (n_queued_tokens > 1) {
        if (!cparams.no_perf) {
            t_p_eval_us += ggml_time_us() - t_compute_start_us;
        }
        n_p_eval += n_queued_tokens;
    }

    // get a more accurate load time, upon first eval
    if (n_queued_tokens > 0 && !has_evaluated_once) {
        t_load_us = ggml_time_us() - t_start_us;
        has_evaluated_once = true;
    }

    n_queued_tokens = 0;
    t_compute_start_us = 0;
}

const llama_model & llama_context::get_model() const {
    return model;