Struct InferenceConfig 

pub struct InferenceConfig {
    pub device: DeviceType,
    pub max_batch_size: usize,
    pub quantize_weights: bool,
    pub cache_activations: bool,
}

Configuration for inference engine.

Fields

device: DeviceType

Preferred device.

max_batch_size: usize

Maximum batch size for batched operations.

quantize_weights: bool

Enable weight quantization.

cache_activations: bool

Enable activation caching.

Implementations

impl InferenceConfig

pub fn with_device(self, device: DeviceType) -> InferenceConfig

Set device type.

pub fn with_max_batch_size(self, size: usize) -> InferenceConfig

Set max batch size.

pub fn with_quantization(self, enabled: bool) -> InferenceConfig

Enable weight quantization.

Trait Implementations

impl Clone for InferenceConfig

fn clone(&self) -> InferenceConfig

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for InferenceConfig

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Default for InferenceConfig

fn default() -> InferenceConfig

Returns the “default value” for a type.