Runtime API Reference

The ExecuTorch C++ API provides an on-device execution framework for exported PyTorch models.

For a tutorial style introduction to the runtime API, check out the runtime tutorial and its simplified version.

For detailed information on how APIs evolve and the deprecation process, please refer to the ExecuTorch API Life Cycle and Deprecation Policy.

Model Loading and Execution

.. doxygenclass:: executorch::runtime::Program
  :members:

.. doxygenclass:: executorch::runtime::Method
  :members:

.. doxygenclass:: executorch::runtime::MethodMeta
  :members:

.. doxygenclass:: executorch::runtime::DataLoader
  :members:

.. doxygenclass:: executorch::runtime::MemoryAllocator
  :members:

.. doxygenclass:: executorch::runtime::HierarchicalAllocator
  :members:

.. doxygenclass:: executorch::runtime::MemoryManager
  :members:

.. doxygenstruct:: executorch::runtime::EValue
  :members:

.. doxygenclass:: executorch::runtime::etensor::Tensor
  :members: