Enum NemotronSsmQuant 

pub enum NemotronSsmQuant {
    Nvfp4,
    Fp8,
    Bf16,
}

SSM weight quantization format detected at load time.

Variants

Nvfp4

NVFP4: has weight_scale + weight_scale_2 (Nano NVFP4 model).

Fp8

FP8 E4M3: has weight_scale but no weight_scale_2 (Super 120B).

Bf16

BF16: no weight_scale at all (BF16 layers adjacent to attention).

Trait Implementations

impl Clone for NemotronSsmQuant

fn clone(&self) -> NemotronSsmQuant

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for NemotronSsmQuant

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

Formats the value using the given formatter.

impl PartialEq for NemotronSsmQuant

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

impl Eq for NemotronSsmQuant

impl StructuralPartialEq for NemotronSsmQuant