providers

Typed ONNX Runtime execution-provider configuration.

Each provider is a small pydantic config that compiles to an ONNX Runtime (name, options) tuple via ExecutionProviderConfig.to_ort(). Keeping providers as typed configs (rather than raw strings) lets users opt into hardware acceleration — CUDA, TensorRT FP16, CoreML/ANE — without touching model code, and keeps the options validated and discoverable.

Classes

CoreMLProvider(**data)	The CoreML execution provider (Apple, GPU/Neural Engine).
CpuProvider(**data)	The default CPU execution provider.
CudaProvider(**data)	The CUDA (NVIDIA GPU) execution provider.
SessionOptionsConfig(**data)	A subset of ONNX Runtime SessionOptions exposed as typed config.
TensorRTProvider(**data)	The TensorRT execution provider (NVIDIA, ahead-of-time engine build).