Enum PreparationStep 

pub enum PreparationStep {
    NormalizeQwen4Exp,
    QuantizeAffineQ4,
    PackExpertRecords,
    InterleaveNgramRows,
}

A transformation needed to produce the engine’s prepared representation.

Variants

NormalizeQwen4Exp

Normalize native Qwen4-exp tensor names and layout.

QuantizeAffineQ4

Convert supported dense weights to affine 4-bit storage.

PackExpertRecords

Group expert weights into records for streaming and residency.

InterleaveNgramRows

Interleave n-gram codes, scales, and biases by row.

Trait Implementations

impl Clone for PreparationStep

fn clone(&self) -> PreparationStep

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for PreparationStep

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for PreparationStep

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for PreparationStep

impl PartialEq for PreparationStep

fn eq(&self, other: &PreparationStep) -> 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 PreparationStep

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for PreparationStep