Struct Fp8Weight 

pub struct Fp8Weight {
    pub weight: DevicePtr,
    pub row_scale: DevicePtr,
    pub n: u32,
    pub k: u32,
    pub scale_format: WeightQuantFormat,
}

2026-09-25: FP8 E4M3 weight with its scale. The layout of row_scale depends on scale_format:

• WeightQuantFormat::Fp8PerRow: [N] f32;
• WeightQuantFormat::Fp8BlockScaled: [N/128, K/128] f32, rounded up;
• WeightQuantFormat::Fp8SingleScale: no scale buffer.

Check scale_format before reading row_scale.

Fields

weight: DevicePtr

2026-09-25: [N, K] FP8 E4M3 bytes.

row_scale: DevicePtr

2026-09-25: The scale buffer, laid out as scale_format says.

n: u32

k: u32

scale_format: WeightQuantFormat

Implementations

impl Fp8Weight

pub fn transpose_for_gemm( &self, gpu: &dyn GpuBackend, transpose_k: KernelHandle, transpose_scale_k: KernelHandle, stream: u64, ) -> Result<Fp8WeightTransposed>

2026-09-25: Transpose this weight into new buffers weight_t[K, N] and scale_t[K/128, N/128], and synchronize stream. row_scale is read as FP32 block scales; scale_format is not checked.

Trait Implementations

impl Clone for Fp8Weight

fn clone(&self) -> Fp8Weight

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Fp8Weight

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

Formats the value using the given formatter.

impl From<Fp8Weight> for QuantWeight

fn from(w: Fp8Weight) -> Self

Converts to this type from the input type.

impl Copy for Fp8Weight