// CHECK-SAME: f = @composite_conv2d_with_bias_and_relu6_fn_1}>
// CHECK-SAME: {_tfl_quant_trait = "fully_quantizable"
// CHECK: %[[PARTITIONEDCALL_1:.*]] = "tf.PartitionedCall"(%arg0, %arg1, %[[CONST_0]])
// CHECK-SAME: f = @composite_conv2d_with_bias_and_relu_fn_1}
// CHECK: %[[PARTITIONEDCALL_2:.*]] = "tf.PartitionedCall"(%arg0, %arg1, %[[CONST_0]])
// CHECK-SAME: f = @composite_conv2d_with_bias_fn_1}

  // CHECK: [[a:%.*]] = tf_mlrt.executeop([[input0]],
  // CHECK-SAME: AddV2
  // CHECK-SAME: op_key = 1
  // CHECK-NOT: __op_key
  %a = "tf.AddV2"(%input0, %const) {__op_key = 1: i32}: (tensor<i32>, tensor<i32>) -> tensor<i32>
  // CHECK: [[b:%.*]] = tf_mlrt.executeop([[a]])
  // CHECK-SAME: Abs
  // CHECK-SAME: op_key = 2
  // CHECK-NOT: __op_key

  }
}

// -----

module attributes {tf_saved_model.semantics} {
  // CHECK-LABEL: composite_and_select
  // CHECK-SAME: %[[ARG0:.*]]: tensor<1x2xf32>
  // CHECK-SAME: %[[ARG1:.*]]: tensor<2x3xf32>
  // CHECK-SAME: %[[ARG2:.*]]: tensor<1x3xi1>
  // CHECK-SAME: %[[ARG3:.*]]: tensor<1x3xf32>

            }
        }
    }

    @Test
    fun `same script different target type`() {

        // given: same init, settings & build files all applying same script
        val same = withFile("same.gradle.kts", """println("Same script on ${'$'}this")""")
        val sameApply = """apply(from = "same.gradle.kts")"""
        val initScriptFile = withFile("same.init.gradle.kts", sameApply)

// CHECK-SAME: proj_clip = 0.000000e+00 : f32,
// CHECK-SAME: time_major = false}> : (
// CHECK-SAME: tensor<1x2x3xf32>,
// CHECK-SAME: tensor<1x1xf32>, tensor<1x1xf32>, tensor<1x1xf32>, tensor<1x1xf32>,
// CHECK-SAME: tensor<1x1xf32>, tensor<1x1xf32>, tensor<1x1xf32>, tensor<1x1xf32>,
// CHECK-SAME: none, none, none,
// CHECK-SAME: tensor<3xf32>, tensor<3xf32>, tensor<3xf32>, tensor<3xf32>,

// CHECK-SAME: , asymmetric_quantize_inputs = true
// CHECK: return %[[mm:.*]]

// PerTensor: %[[w:.*]] = "tfl.pseudo_qconst"() <{qtype = tensor<512x12x!quant.uniform<i8<-127:127>:f32, 1.000000e+00>>,
// PerTensor: %[[mm:.*]] = "tfl.batch_matmul"(%arg0, %[[w]]) <{adj_x = false, adj_y = false
// PerTensor-SAME: , asymmetric_quantize_inputs = true
// PerTensor: return %[[mm:.*]]
}

  // CHECK: %[[CONST:.*]] = mhlo.constant()
  // CHECK-SAME{LITERAL} value = dense<127> : tensor<2x3x3x2xi8>
  // CHECK-SAME: tensor<2x3x3x2x!quant.uniform<i8:f32, 1.000000e+00:3>>
  // CHECK: mhlo.convolution(%arg0, %[[CONST]])
  // CHECK-SAME{LITERAL}: dim_numbers = [b, 0, 1, f]x[0, 1, i, o]->[b, 0, 1, f]
  // CHECK-SAME{LITERAL}: window = {stride = [1, 2], pad = [[0, 0], [0, 0]], lhs_dilate = [1, 1], rhs_dilate = [2, 2]}

  %0 = "tf_device.cluster"() ({
    // CHECK: "tf.Const"() <{value = dense<1> : tensor<i32>}>
    // CHECK-NOT: _xla_outside_compilation
    // CHECK: "tf.Const"
    // CHECK-SAME: _xla_outside_compilation
    // CHECK-SAME: tf_type.string
    // CHECK: "tf.Identity"
    // CHECK-NOT: _xla_outside_compilation
    %1 = "tf.Const"() {value = dense<1> : tensor<i32>} : () -> tensor<i32>

            }
        }
        createTar('test2.tar') {
            subdir1 {
                file ('file.txt').text = 'original text 1' // Same name in same dir
            }
            subdir3 {
                file('file3.txt').text = 'original text 3' // Same name in same different nested dir
                file ('file4.txt').text =  'original text 4'
            }
        }

But it's still part of the same **FastAPI** application/web API (it's part of the same "Python Package").

You can create the *path operations* for that module using `APIRouter`.

### Import `APIRouter`

You import it and create an "instance" the same way you would with the class `FastAPI`:

```Python hl_lines="1  3" title="app/routers/users.py"