// CHECK: %[[ADD:.+]] = mhlo.add %[[CONV]], %[[DYNAMIC_BCAST]] : tensor<?x256x256x2xf32>
  %filter = mhlo.constant dense<[[[[1.0, 2.0], [3.0, 4.0], [5.0, 6.0]]]]> : tensor<1x1x3x2xf32>
  %cst_0 = mhlo.constant dense<[0.1, 0.2]> : tensor<2xf32>
  %cst_1 = mhlo.constant dense<[0.3, 0.4]> : tensor<2xf32>

  %input_scales = "tf.Const"() { value = dense<2.0> : tensor<f32> } : () -> tensor<f32>
  %input_zps = "tf.Const"() { value = dense<4> : tensor<i32> } : () -> tensor<i32>
  %bias_scales = "tf.Const"() { value = dense<2.0> : tensor<f32> } : () -> tensor<f32>
  %bias_zps = "tf.Const"() { value = dense<4> : tensor<i32> } : () -> tensor<i32>
  %output_scales = "tf.Const"() { value = dense<2.0> : tensor<f32> } : () -> tensor<f32>

func.func @dense_tensor() -> tensor<4xui64> {
  // CHECK: tfrt_fallback_async.const_dense_tensor dense<[1, 2, 3, 4]> : tensor<4xui64>
  %0 = "tf.Const"() {value = dense<[1, 2, 3, 4]> : tensor<4xui64>} : () -> tensor<4xui64>
  // CHECK: tfrt_fallback_async.const_dense_tensor  dense<1.000000e+00> : tensor<1xbf16>
  %1 = "tf.Const"() {device = "/device:CPU:0", value = dense<[1.0]> : tensor<1xbf16>} : () -> tensor<4xbf16>

{{- define "name" -}}
    istio-cni
{{- end }}


{{- define "istio-tag" -}}
    {{ .Values.cni.tag | default .Values.global.tag }}{{with (.Values.cni.variant | default .Values.global.variant)}}-{{.}}{{end}}

You can import it directly from `fastapi`:

```python
from fastapi import Request
```

!!! tip
    When you want to define dependencies that should be compatible with both HTTP and WebSockets, you can define a parameter that takes an `HTTPConnection` instead of a `Request` or a `WebSocket`.

        return generatedTypeName;
    }

    public Type getGeneratedType() {
        return generatedType;
    }

    public <T> Class<T> define() {
        return define(targetType.getClassLoader());
    }

    public <T> Class<T> define(ClassLoader targetClassLoader) {
        return ClassLoaderUtils.defineDecorator(targetType, targetClassLoader, generatedTypeName, visitor.toByteArray());
    }

  addTypes<TFTensorType, TFDeviceType>();
  addInterfaces<TensorflowMlrtInlinerInterface>();

  addOperations<
#define GET_OP_LIST
#include "tensorflow/compiler/mlir/tfrt/ir/mlrt/tf_mlrt_ops.cpp.inc"
      >();

  addOperations<
#define GET_OP_LIST
#include "tensorflow/compiler/mlir/tfrt/ir/mlrt/tf_ops.cpp.inc"
      >();
}

// Parse a type registered to this dialect.

# `HTTPConnection` class

When you want to define dependencies that should be compatible with both HTTP and WebSockets, you can define a parameter that takes an `HTTPConnection` instead of a `Request` or a `WebSocket`.

You can import it from `fastapi.requests`:

```python
from fastapi.requests import HTTPConnection
```

play.http.secret.key="dxbAjiDdqlIV83LY<:;hSxql?tG`CPNgXEXt2asjk>lYQ<xfR`GsdeFJ@uuYBH=0"

# Global object class
# ~~~~~
# Define the Global object class for this application.
# Default to Global in the root package.
# application.global=Global

# Router
# ~~~~~
# Define the Router object to use for this application.
# This router will be looked up first when the application is starting up,

func.func @unfold_splat_constant_float() -> tensor<1x750xf32> {
  %cst = mhlo.constant dense<7.680000e+02> : tensor<1x750xf32>
  func.return %cst : tensor<1x750xf32>

  // CHECK-DAG: %0 = mhlo.constant dense<7.680000e+02> : tensor<f32>
  // CHECK: %1 = "mhlo.broadcast_in_dim"(%0) <{broadcast_dimensions = dense<> : tensor<0xi64>}> : (tensor<f32>) -> tensor<1x750xf32>
  // CHECK: return %1 : tensor<1x750xf32>
}