Struct FP8Config 

pub struct FP8Config {
    pub format: FP8Format,
    pub scaling: ScalingStrategy,
    pub delayed_scaling: DelayedScalingConfig,
    pub stochastic_rounding: bool,
    pub clip_to_max: bool,
    pub use_hardware_ops: bool,
    pub calibration_samples: usize,
}

FP8 quantization configuration

Fields

format: FP8Format

FP8 format to use

scaling: ScalingStrategy

Scaling strategy

delayed_scaling: DelayedScalingConfig

Delayed scaling configuration

stochastic_rounding: bool

Enable stochastic rounding for better accuracy

clip_to_max: bool

Clipping strategy (clip to max or saturate)

use_hardware_ops: bool

Use hardware FP8 operations if available

calibration_samples: usize

Calibration samples for initial scale estimation

Trait Implementations

impl Clone for FP8Config

fn clone(&self) -> FP8Config

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for FP8Config

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

Formats the value using the given formatter.

impl Default for FP8Config

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for FP8Config

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for FP8Config

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.