LiteRtLmBackendPreference enum
Preferred LiteRT-LM runtime backend for .litertlm models.
This is intentionally separate from GpuBackend, which mirrors llama.cpp backends. LiteRT-LM exposes a smaller runtime selector: CPU, GPU, or the Android NPU delegate.
Values
- auto → const LiteRtLmBackendPreference
-
Let llamadart choose a platform default.
const LiteRtLmBackendPreference(null) - cpu → const LiteRtLmBackendPreference
-
Run LiteRT-LM on CPU.
const LiteRtLmBackendPreference('cpu') - gpu → const LiteRtLmBackendPreference
-
Run LiteRT-LM on the platform GPU delegate when available.
const LiteRtLmBackendPreference('gpu') - npu → const LiteRtLmBackendPreference
-
Run LiteRT-LM on Android NPU delegate when available.
const LiteRtLmBackendPreference('npu')
Properties
- hashCode → int
-
The hash code for this object.
no setterinherited
- index → int
-
A numeric identifier for the enumerated value.
no setterinherited
- name → String
-
Available on Enum, provided by the EnumName extension
The name of the enum value.no setter - nativeName → String?
-
Native LiteRT-LM backend name, or null for automatic selection.
final
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
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<
LiteRtLmBackendPreference> - A constant List of the values in this enum, in order of their declaration.