Enum WeightQuantization 

pub enum WeightQuantization {
    Declared,
    Nvfp4,
}

2026-09-28: The --weight-quantization tiers.

Variants

Declared

2026-09-28: Each layer at the precision its checkpoint declares.

Nvfp4

2026-09-28: FP8-declared projections requantized to NVFP4 at load, as before the plan existed.

Implementations

impl WeightQuantization

pub const ALL: [Self; 2]

2026-09-28: Every tier, in the order the flag lists them.

pub fn name(self) -> &'static str

2026-09-28: The flag value, recipe value and gate-record value.

Trait Implementations

impl Clone for WeightQuantization

fn clone(&self) -> WeightQuantization

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for WeightQuantization

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

Formats the value using the given formatter.

impl Default for WeightQuantization

fn default() -> WeightQuantization

Returns the “default value” for a type.

impl PartialEq for WeightQuantization

fn eq(&self, other: &WeightQuantization) -> 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 Copy for WeightQuantization

impl Eq for WeightQuantization

impl StructuralPartialEq for WeightQuantization