Function main

subprojects/llama.cpp/tools/perplexity/perplexity.cpp:1978–2070

}

int main(int argc, char ** argv) {
    common_params params;

    params.n_ctx = 512;
    params.escape = false;

    if (!common_params_parse(argc, argv, params, LLAMA_EXAMPLE_PERPLEXITY)) {
        return 1;
    }

    common_init();

    const int32_t n_ctx = params.n_ctx;

    if (n_ctx <= 0) {
        LOG_ERR("%s: perplexity tool requires '--ctx-size' > 0\n", __func__);
        return 1;
    }

    const bool ppl = !params.hellaswag && !params.winogrande && !params.multiple_choice && !params.kl_divergence;

    if (ppl) {
        const int32_t n_seq = std::max(1, params.n_batch / n_ctx);
        const int32_t n_kv = n_seq * n_ctx;

        params.n_parallel = n_seq;
        params.n_ctx      = n_kv;

        params.n_batch = std::min(params.n_batch, n_kv);
    } else {
        params.n_batch = std::min(params.n_batch, params.n_ctx);
        if (params.kl_divergence) {
            params.n_parallel = 1;
        } else {
            // ensure there's at least enough seq_ids for HellaSwag
            params.n_parallel = std::max(4, params.n_parallel);
        }
    }

    if (params.ppl_stride > 0) {
        LOG_INF("Will perform strided perplexity calculation -> adjusting context size from %d to %d\n",
                params.n_ctx, params.n_ctx + params.ppl_stride/2);
        params.n_ctx += params.ppl_stride/2;
    }

    llama_backend_init();
    llama_numa_init(params.numa);

    // load the model and apply lora adapter, if any
    auto llama_init = common_init_from_params(params);

    auto * model = llama_init->model();
    auto * ctx   = llama_init->context();

    if (model == NULL) {
        LOG_ERR("%s: unable to load model\n", __func__);
        return 1;
    }