Function ggml_quantize_q4_K

ggml-quants.c:1962–1971

}

size_t ggml_quantize_q4_K(const float * restrict src, void * restrict dst, int n, int k, int64_t * restrict hist) {
    assert(k % QK_K == 0);
    (void)hist; // TODO: collect histograms

    for (int j = 0; j < n; j += k) {
        block_q4_K * restrict y = (block_q4_K *)dst + j/QK_K;
        quantize_row_q4_K_reference(src + j, y, k);
    }
    return (n/QK_K*sizeof(block_q4_K));
}

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