executorch_dart_shared library
The dart:ffi-free subset of package:executorch_dart.
Application code should not import this library — import
package:executorch_dart/executorch_dart.dart instead. This one exists
for a single consumer: the web branch of package:executorch_flutter.
The reason it has to exist is that export '...' hide Name still compiles
the library it hides names from. executorch_flutter re-exports this
package wholesale and routes the handful of native-only names to web
implementations of its own, but hiding those names is not enough — on web,
the blanket re-export would still drag executorch_dart.dart, and with it
dart:ffi, into the dart2js compile and fail the build. Pointing the web
branch of that re-export here keeps dart:ffi out of the graph entirely.
So this library carries everything in the package that does not need
dart:ffi: the tensor and model types, the error hierarchy, the processor
base classes, the manager interface and its shared base implementation, and
the version constant. The four native-only pieces — ExecuTorchLLM,
BackendQuery, ExecuTorchVersion, and setNativeDebugLogging — are
exported only from executorch_dart.dart.
When adding a new export to this package, add it here unless it needs
dart:ffi; executorch_dart.dart re-exports this library in full.
Classes
- ExecutorchManager
- High-level manager for ExecuTorch inference operations
- ExecutorchManagerBase
- Base implementation of ExecutorchManager with shared logic
- ExecuTorchModel
- High-level wrapper for an ExecuTorch model instance
-
ExecuTorchPostprocessor<
R> - Abstract base class for output postprocessing
-
ExecuTorchPreprocessor<
T> - Abstract base class for input preprocessing
-
ExecuTorchProcessor<
T, R> - Abstract base class combining preprocessing and postprocessing
- GenConfig
-
Generation parameters for
ExecuTorchLLM.generate. - ModelLoadResult
- Model loading result.
- ProcessorTensorUtils
- Utility class for tensor operations in processors
- TensorData
- Tensor data for input/output.
- TensorUtils
- Utility class for working with ExecuTorch tensors
Enums
- Backend
- Hardware acceleration backends supported by ExecuTorch.
- TensorType
- Tensor data type enumeration.
Extensions
- TensorTypeExtension on TensorType
- Deprecated extension providing backward compatibility for ExtendedTensorType.
Constants
- executorchVersion → const String
- ExecuTorch version this plugin is built against.
Typedefs
- ExtendedTensorType = TensorType
- Deprecated alias for TensorType.
Exceptions / Errors
- ExecuTorchException
- Base exception class for all ExecuTorch-related errors.
- ExecuTorchInferenceException
- Inference execution errors.
- ExecuTorchIOException
- Network and file I/O errors.
- ExecuTorchMemoryException
- Memory and resource errors.
- ExecuTorchModelException
- Model loading and lifecycle errors.
- ExecuTorchPlatformException
- Platform-specific integration errors.
- ExecuTorchValidationException
- Tensor validation and data errors.
- GenericProcessorException
- Generic processor exception implementation.
- InvalidInputException
- Exception thrown for invalid processor input.
- InvalidOutputException
- Exception thrown for invalid processor output.
- PostprocessingException
- Exception thrown during postprocessing operations.
- PreprocessingException
- Exception thrown during preprocessing operations.
- ProcessorException
- Base exception class for processor-related errors.