}},
		}, valid: true},
		{name: "no destination", route: &networking.HTTPRoute{
			Route: []*networking.HTTPRouteDestination{{
				Destination: nil,
			}},
		}, valid: false},
		{name: "weighted", route: &networking.HTTPRoute{
			Route: []*networking.HTTPRouteDestination{{
				Destination: &networking.Destination{Host: "foo.baz.south"},
				Weight:      25,
			}, {

  let description = [{
The 4-D `input` tensor is treated as a 3-D array of 1-D vectors (along the last
dimension), and each vector is normalized independently.  Within a given vector,
each component is divided by the weighted, squared sum of inputs within
`depth_radius`.  In detail,

    sqr_sum[a, b, c, d] =
        sum(input[a, b, c, d - depth_radius : d + depth_radius + 1] ** 2)
    output = input / (bias + alpha * sqr_sum) ** beta