Function llama_model_quantize

smallthinker/src/llama-quant.cpp:955–967

}

uint32_t llama_model_quantize(
        const char * fname_inp,
        const char * fname_out,
        const llama_model_quantize_params * params) {
    try {
        llama_model_quantize_impl(fname_inp, fname_out, params);
    } catch (const std::exception & err) {
        LLAMA_LOG_ERROR("%s: failed to quantize: %s\n", __func__, err.what());
        return 1;
    }

    return 0;
}