OnnxBackendConfig#

class openstef_foundation_models.presets.forecasting_workflow.OnnxBackendConfig(*, kind: Literal['onnx'] = 'onnx', providers: list[CpuProvider | CudaProvider | TensorRTProvider | CoreMLProvider] | None = None, policy: DefaultProviderPolicy = DefaultProviderPolicy(kind='default'), session_options: SessionOptionsConfig | None = None)[source]

Bases: BaseConfig

Compute configuration for an ONNX Runtime inference backend.

Holds only how to run the model (execution providers, session options), not which weights: the checkpoint is supplied to build() by the caller, so the same compute settings can run different checkpoints.

Parameters:
kind: Literal['onnx']
providers: list[CpuProvider | CudaProvider | TensorRTProvider | CoreMLProvider] | None
policy: DefaultProviderPolicy
session_options: SessionOptionsConfig | None
build(checkpoint: LocalCheckpoint | HubCheckpoint) → InferenceBackend[source]

Resolve checkpoint and build the ONNX Runtime backend.

Importing the backend raises MissingExtraError if ONNX Runtime is not installed.

Parameters:

checkpoint (LocalCheckpoint | HubCheckpoint) – The checkpoint (weights + metadata) to load and run.

Return type:

InferenceBackend

Returns:

A ready-to-run backend wrapping the resolved checkpoint.

model_config: ClassVar[ConfigDict] = {'arbitrary_types_allowed': False, 'extra': 'ignore', 'protected_namespaces': ()}

Configuration for the model, should be a dictionary conforming to [ConfigDict][pydantic.config.ConfigDict].