Enum ScalingStrategy 

pub enum ScalingStrategy {
    PerTensor,
    PerChannel,
    PerToken,
    BlockWise {
        block_size: usize,
    },
}

Scaling strategy for FP8 quantization

Variants

PerTensor

Per-tensor scaling: single scale factor for entire tensor

PerChannel

Per-channel scaling: scale factor per output channel

PerToken

Per-token scaling: scale factor per token (for sequence models)

BlockWise

Block-wise scaling: scale factor per fixed-size block

Fields

block_size: usize

Trait Implementations

impl Clone for ScalingStrategy

fn clone(&self) -> ScalingStrategy

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ScalingStrategy

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ScalingStrategy

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ScalingStrategy

fn eq(&self, other: &ScalingStrategy) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for ScalingStrategy

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Copy for ScalingStrategy

impl Eq for ScalingStrategy

impl StructuralPartialEq for ScalingStrategy