Struct DenseWeight 

pub struct DenseWeight {
    pub weight: DevicePtr,
}

2026-09-25: Device pointer to an unquantized weight: BF16 unless the loader that built it says otherwise (for example dense_keep_f32).

Fields

weight: DevicePtr

Implementations

impl DenseWeight

pub fn quantize_to_fp8( &self, gpu: &dyn GpuBackend, quantize_kernel: KernelHandle, n: usize, k: usize, stream: u64, ) -> Result<Fp8DenseWeight>

2026-09-25: Quantize a BF16 weight [N, K] to FP8 E4M3 [N, K] with one f32 scale per row, in new buffers, with the quantize_bf16_to_fp8 kernel. It synchronizes stream before returning.

Trait Implementations

impl Clone for DenseWeight

fn clone(&self) -> DenseWeight

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for DenseWeight

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

Formats the value using the given formatter.

impl From<DenseWeight> for QuantWeight

fn from(w: DenseWeight) -> Self

Converts to this type from the input type.

impl Copy for DenseWeight