<!--
{
  "availability" : [
    "iOS: 26.0.0 -",
    "iPadOS: 26.0.0 -",
    "macCatalyst: 26.0.0 -",
    "macOS: 26.0.0 -",
    "tvOS: 26.0.0 -",
    "visionOS: 26.0.0 -"
  ],
  "documentType" : "symbol",
  "framework" : "Metal",
  "identifier" : "/documentation/Metal/MTL4MachineLearningCommandEncoder/dispatchNetwork(intermediatesHeap:)",
  "metadataVersion" : "0.1.0",
  "role" : "Instance Method",
  "symbol" : {
    "kind" : "Instance Method",
    "modules" : [
      "Metal"
    ],
    "preciseIdentifier" : "c:objc(pl)MTL4MachineLearningCommandEncoder(im)dispatchNetworkWithIntermediatesHeap:"
  },
  "title" : "dispatchNetwork(intermediatesHeap:)"
}
-->

# dispatchNetwork(intermediatesHeap:)

Dispatches a machine learning network using the current pipeline state and argument table.

```
func dispatchNetwork(intermediatesHeap heap: any MTLHeap)
```

## Parameters

`heap`

a heap that Metal can use to allocate intermediate tensors.

## Discussion

This method takes a parameter consisting of a `MTLHeap` that Metal can use to allocate intermediate tensors.
You can query the minimum size Metal requires for this heap by calling
[`intermediatesHeapSize`](/documentation/Metal/MTL4MachineLearningPipelineState/intermediatesHeapSize).

---

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)