Class emulator::inference::InferenceBackend

ClassList > emulator > inference > InferenceBackend

Abstract interface for inference backends. More...

• #include <inference_backend.hpp>

Inherited by the following classes: emulator::inference::LibTorchBackend, emulator::inference::StubBackend

Public Functions

Type	Name
virtual void	finalize () = 0 Release resources and finalize the backend.
virtual bool	infer (const double * inputs, double * outputs, int batch_size) = 0 Run inference on input data.
virtual bool	initialize (const InferenceConfig & config) = 0 Initialize the backend.
virtual bool	is_initialized () const = 0 Check if the backend is ready for inference.
virtual std::string	name () const = 0 Get the human-readable name of this backend.
virtual BackendType	type () const = 0 Get the backend type enumeration.
virtual ValidationResult	validate () const Validate configuration before running.
virtual	~InferenceBackend () = default

Detailed Description

Public Functions Documentation

function finalize

Release resources and finalize the backend.

virtual void emulator::inference::InferenceBackend::finalize () = 0

After calling this, the backend is no longer usable until initialize() is called again.

---

function infer

Run inference on input data.

virtual bool emulator::inference::InferenceBackend::infer (
    const double * inputs,
    double * outputs,
    int batch_size
) = 0

Executes the model on the provided input batch and writes results to the output buffer.

Parameters:

• inputs Input data array, size = batch_size * input_channels
• outputs Output data array, size = batch_size * output_channels
• batch_size Number of samples in the batch

Returns:

true if inference succeeded, false on error

Precondition:

initialize() must have been called successfully

Precondition:

outputs must be pre-allocated with sufficient size

---

function initialize

Initialize the backend.

virtual bool emulator::inference::InferenceBackend::initialize (
    const InferenceConfig & config
) = 0

Loads the model, allocates resources, and prepares for inference. Must be called before infer().

Parameters:

• config Configuration options

Returns:

true if initialization succeeded, false on error

---

function is_initialized

Check if the backend is ready for inference.

virtual bool emulator::inference::InferenceBackend::is_initialized () const = 0

Returns:

true if initialized and ready

---

function name

Get the human-readable name of this backend.

virtual std::string emulator::inference::InferenceBackend::name () const = 0

Returns:

Backend name (e.g., "LibTorch", "Stub")

---

function type

Get the backend type enumeration.

virtual BackendType emulator::inference::InferenceBackend::type () const = 0

Returns:

BackendType value

---

function validate

Validate configuration before running.

inline virtual ValidationResult emulator::inference::InferenceBackend::validate () const

Checks that the model file exists, dimensions match, device is available, etc. Call this after initialize() to detect configuration errors early.

Returns:

ValidationResult with errors/warnings if any

---

function ~InferenceBackend

virtual emulator::inference::InferenceBackend::~InferenceBackend () = default

---

---

The documentation for this class was generated from the following file components/emulator_comps/common/src/inference/inference_backend.hpp