Package apple.mlcompute.enums
Class MLCExecutionOptions
- java.lang.Object
-
- apple.mlcompute.enums.MLCExecutionOptions
-
public final class MLCExecutionOptions extends java.lang.Object[@enum] MLCExecutionOptions A bitmask that specifies the options you’ll use when executing a graph.
-
-
Field Summary
Fields Modifier and Type Field Description static longForwardForInferenceThe option to execute the forward pass for inference only.static longNonestatic longPerLayerProfilingThe option to enable additional per layer profiling information currently emitted using signposts.static longProfilingThe option to return profiling information in the callback before returning from execution.static longSkipWritingInputDataToDeviceThe option to skip writing input data to device memory.static longSynchronousThe option to execute the graph synchronously.
-
-
-
Field Detail
-
None
public static final long None
- See Also:
- Constant Field Values
-
SkipWritingInputDataToDevice
public static final long SkipWritingInputDataToDevice
The option to skip writing input data to device memory. this option to prevent writing the input tensors to device memory associated with these tensors when the framework executes the graph.- See Also:
- Constant Field Values
-
Synchronous
public static final long Synchronous
The option to execute the graph synchronously. Include this option to wait until execution of the graph on specified device finishes before returning from the \p execute method.- See Also:
- Constant Field Values
-
Profiling
public static final long Profiling
The option to return profiling information in the callback before returning from execution. Include this option to return profliling information in the graph execute completion handler callback, including device execution time.- See Also:
- Constant Field Values
-
ForwardForInference
public static final long ForwardForInference
The option to execute the forward pass for inference only. If you include this option and execute a training graph using one of the \p execute methods, such as \p -executeWithInputsData:lossLabelsData:lossLabelWeightsData:batchSize:options:completionHandler: , the framework only executes the forward pass of the training graph, and it executes that forward pass for inference only. If you include this option and execute a training graph using one of the executeForward methods, such as \p -executeForwardWithBatchSize:options:completionHandler:), the framework executes the forward pass for inference only.- See Also:
- Constant Field Values
-
PerLayerProfiling
public static final long PerLayerProfiling
The option to enable additional per layer profiling information currently emitted using signposts. The option to enable per layer profiling information emitted as signposts. The per layer information can be visualized using the Logging Instrument in Xcode's Instruments. This information may not be available for all MLCDevice. API-Since: 15.0- See Also:
- Constant Field Values
-
-