PreferredBackend enum

Preferred hardware backend for model inference execution.

Specifies the computational backend to use for running AI models, allowing optimization based on device capabilities and performance requirements.

Example:

final config = ModelConfig(
  modelPath: 'model.task',
  maxTokens: 512,
  preferredBackend: PreferredBackend.gpu,
);

Inheritance

• Object
• Enum
• PreferredBackend

Available extensions

• EnumName

Values

unknown → const PreferredBackend

Unknown or unspecified backend.

The system will automatically select an appropriate backend.

const PreferredBackend(0)

cpu → const PreferredBackend

CPU-based inference.

Uses the device's CPU for model execution. This is more compatible but generally slower than GPU inference.

const PreferredBackend(1)

gpu → const PreferredBackend

GPU-based inference.

Uses the device's GPU for accelerated model execution. Provides better performance for supported models and devices.

const PreferredBackend(2)

Properties

hashCode → int

The hash code for this object.

no setter, inherited

index → int

A numeric identifier for the enumerated value.

no setter, inherited

name → String

Available on Enum, provided by the EnumName extension

The name of the enum value.

no setter

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

value → int

The numeric value representing this backend type.

final

Methods

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited

Constants

values → const List<PreferredBackend>

A constant List of the values in this enum, in order of their declaration.