Matrix dot product operation is not transposed in function ggml compute_forward_mul_mat_one_chunk

[velonica0]

In the function ggml compute_forward_mul_mat_one_chunk, why can src1.qs directly perform dot product operations and where is it transposed?

for (int j = 0; j < qk/2; ++j) {
    const int v0 = (x[ib].qs[j] & 0x0F) - 8;
    const int v1 = (x[ib].qs[j] >>   4) - 8;
  
    sumi0 += (v0 * y[ib].qs[j]);
    sumi1 += (v1 * y[ib].qs[j + qk/2]);
}