<!--
{
  "availability" : [
    "iOS: 14.0.0 - 18.0.0",
    "iPadOS: 14.0.0 - 18.0.0",
    "macCatalyst: 14.0.0 - 18.0.0",
    "macOS: 11.0.0 - 15.0.0",
    "tvOS: 14.0.0 - 18.0.0",
    "visionOS: 1.0.0 - 2.0.0",
    "watchOS: 7.0.0 - 11.0.0"
  ],
  "documentType" : "symbol",
  "framework" : "Accelerate",
  "identifier" : "/documentation/Accelerate/BNNSLayerParametersMultiheadAttention",
  "metadataVersion" : "0.1.0",
  "role" : "Structure",
  "symbol" : {
    "kind" : "Structure",
    "modules" : [
      "Accelerate"
    ],
    "preciseIdentifier" : "c:@SA@BNNSLayerParametersMultiheadAttention"
  },
  "title" : "BNNSLayerParametersMultiheadAttention"
}
-->

# BNNSLayerParametersMultiheadAttention

A structure that contains the parameters of a multihead attention layer.

```
struct BNNSLayerParametersMultiheadAttention
```

## Topics

### Initializers

[`init(query:key:value:add_zero_attn:key_attn_bias:value_attn_bias:output:dropout:seed:)`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/init(query:key:value:add_zero_attn:key_attn_bias:value_attn_bias:output:dropout:seed:))

Returns a new multihead attention layer parameters structure from the specified parameters.

[`init()`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/init())

Returns a new multihead attention layer parameters structure.

### Instance Properties

[`query`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/query)

A projection parameter structure that describes the query-related input parameters and projection.

[`key`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/key)

A projection parameter structure that describes the key-related input parameters and projection.

[`value`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/value)

A projection parameter structure that describes the value-related input parameters and projection.

[`add_zero_attn`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/add_zero_attn)

A Boolean value that, if true, adds a row of zeroes to the projected *K* and *V* inputs to the calculation.

[`key_attn_bias`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/key_attn_bias)

A 2D tensor that’s added to the value as part of the attention calculation.

[`value_attn_bias`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/value_attn_bias)

An optional `d_value` x `num_heads` 2D tensor that’s added as part of the attention calculation.

[`output`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/output)

A projection parameter structure that describes the output tensor and associated projection.

[`dropout`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/dropout)

The seed for the dropout layer’s random number generator.

[`seed`](/documentation/Accelerate/BNNSLayerParametersMultiheadAttention/seed)

A random seed for the dropout layer.


---

Copyright &copy; 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)