vart_runner_factory.hpp File Reference

Runner interface, async job types, quantization parameters, and RunnerFactory for VART ML. More...

#include <any>
#include <chrono>
#include <cstdint>
#include <functional>
#include <memory>
#include <string>
#include <unordered_map>
#include <vector>
#include "vart_npu_tensor.hpp"

Include dependency graph for vart_runner_factory.hpp:

Go to the source code of this file.

Classes
struct	vart::QuantParameters
	Struct representing quantization parameters for a tensor. More...
struct	vart::JobHandle
	Struct representing a job handle for asynchronous execution. More...
class	vart::Runner
	Abstract base class for executing model inference operations. More...
class	vart::RunnerFactory
	Factory class for creating Runner instances. More...

Namespaces
	vart
	VART (Vitis AI Runtime) ML inference API namespace.

Enumerations
enum class	vart::RunnerType { vart::VAIML }
	Enumerates the types of runner implementations supported. More...
enum class	vart::RoundingMode { vart::UNKNOWN , vart::ROUND_TO_NEAREST_EVEN , vart::ROUND_TOWARD_ZERO }
	Enumerates the rounding modes used in quantization. More...
enum class	vart::StatusCode {   vart::SUCCESS = 0 , vart::FAILURE , vart::INVALID_INPUT , vart::INVALID_OUTPUT ,   vart::OUT_OF_MEMORY , vart::RUNTIME_ERROR , vart::JOB_PENDING , vart::INVALID_JOB_ID ,   vart::RESOURCE_UNAVAILABLE }
	Enumerates the status codes used in the VART. More...

Detailed Description

Runner interface, async job types, quantization parameters, and RunnerFactory for VART ML.

Defines the types and classes used for model inference in VART ML:

• RunnerType, RoundingMode, StatusCode enums
• QuantParameters and JobHandle structs
• Runner abstract base class (sync/async inference, tensor allocation)
• RunnerFactory for creating Runner instances
• ExecuteAsyncCallback type alias

This is the primary header for VART ML applications. It includes vart_npu_tensor.hpp internally, so all tensor types and enums are available through this single include.