Function quantize_q4_K

subprojects/llama.cpp/ggml/src/ggml-quants.c:1449–1463

}

size_t quantize_q4_K(const float * GGML_RESTRICT src, void * GGML_RESTRICT dst, int64_t nrow, int64_t n_per_row, const float * quant_weights) {
    size_t row_size = ggml_row_size(GGML_TYPE_Q4_K, n_per_row);
    if (!quant_weights) {
        quantize_row_q4_K_ref(src, dst, (int64_t)nrow*n_per_row);
    }
    else {
        char * qrow = (char *)dst;
        for (int64_t row = 0; row < nrow; ++row) {
            quantize_row_q4_K_impl(src, (block_q4_K*)qrow, n_per_row, quant_weights);
            src += n_per_row;
            qrow += row_size;
        }
    }
    return nrow * row_size;
}

// ====================== 5-bit (de)-quantization