onnx-runtime-ep-api 0.1.0-dev.3

Execution Provider API for the ORT 2.0 runtime: ExecutionProvider and Kernel traits, OpRegistry, and the ORT graph ABI bridge
Documentation

onnx-runtime-ep-api

The Execution Provider (EP) interface for the ORT 2.0 runtime (see docs/ORT2.md §4). Every backend — CPU, CUDA, MLX, or a legacy ORT plugin loaded via dlopen — implements the same [ExecutionProvider] trait; only the loading mechanism differs.

This is a Phase 1 skeleton: trait and type signatures are real and reference the [onnx_runtime_ir] contract, but method bodies live in the concrete EP crates (e.g. onnx-runtime-ep-cpu). Zero-copy tensor views and the ORT ABI bridge require unsafe FFI and are stubbed here.

Modules

  • [provider] — [ExecutionProvider], [EpConfig], device buffers/fences.
  • [kernel] — [Kernel] trait, [KernelMatch], [Cost].
  • [registry] — [OpRegistry], [OpKey], [KernelFactory], [EpRegistry].
  • [epcontext] — [EpContext] runtime form + source-keyed [EpContextRegistry] (§55).
  • [tensor] — [TensorView] / [TensorMut] zero-copy device views.
  • [weight] — capability-negotiated lazy [WeightHandle] delivery.
  • [abi] — ORT graph ABI bridge for legacy plugin EPs (Phase 2).