Struct QuantConfig 

pub struct QuantConfig {
    pub weight_type: DType,
    pub scale_type: DType,
    pub group_size: usize,
    pub global_scale_type: DType,
}

Quantization configuration for a weight tensor.

Fields

weight_type: DType

Weight storage type (e.g., E2M1 for NVFP4)

scale_type: DType

Scale factor type (e.g., FP8E4M3 for NVFP4 block scales)

group_size: usize

Number of weights per scale factor (block size)

global_scale_type: DType

Global scale factor type (FP32 for NVFP4)

Implementations

impl QuantConfig

pub fn nvfp4() -> Self

NVFP4: E2M1 weights with FP8 block scales (group_size=16)

pub fn fp8() -> Self

FP8 per-tensor quantization

Trait Implementations

impl Clone for QuantConfig

fn clone(&self) -> QuantConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for QuantConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for QuantConfig

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for QuantConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.