Crate ronn_api 

Re-exports

pub use async_session::AsyncBatchProcessor;

pub use async_session::AsyncSession;

pub use batch::BatchConfig;

pub use batch::BatchProcessor;

pub use batch::BatchRequest;

pub use batch::BatchStats;

pub use batch::BatchStrategy;

Modules

async_session

Async inference API for non-blocking, high-throughput inference.

batch

Batch processing for high-throughput inference

prelude

Prelude module for convenient imports

Structs

InferenceSession

An inference session for running a model

Model

Represents a loaded ML model

SessionBuilder

Builder for creating inference sessions

SessionOptions

Options for configuring an inference session

Tensor

Enhanced Tensor implementation with Candle backend.

Enums

DataType

Supported data types for tensors and operations.

Error

OptimizationLevel

Optimization levels similar to compiler optimization levels

Traits

ExecutionProvider

Core execution provider interface.

Type Aliases

ProviderType

Alias for provider types (same as ProviderId)

Result