{18, 15, 12, 18, 15, 12, 18, 15, 12},
                         {24, 24, 24, 15, 15, 15, 6, 6, 6},
                         {18, 18, 18, 15, 15, 15, 12, 12, 12}};
  float dB_vals[4][9] = {{12, 12, 12, 15, 15, 15, 18, 18, 18},
                         {12, 15, 18, 12, 15, 18, 12, 15, 18},
                         {6, 6, 6, 15, 15, 15, 24, 24, 24},

                 absl::Span<AbstractTensorHandle*> grad_inputs) override {
    /* Given upstream grad U and a matmul op A*B, the gradients are:
     *
     *    dA = U * B.T
     *    dB = A.T * U
     *
     *    where A.T means `transpose(A)`
     */
    AbstractTensorHandle* upstream_grad = grad_outputs[0];

    // Get transpose attrs
    bool t_a;