Struct Fp8Weight 

pub struct Fp8Weight {
    pub bytes: CudaSlice<u8>,
    pub scale: f32,
    pub blk: Option<Fp8BlockScales>,
}

FP8-native prefill operand: raw checkpoint e4m3 codes [out_f, in_f] row-major (EXACT — the weight side of the FP8 GEMM does no re-quantization) + its weight scale(s). Per-tensor class: scale is the dequant scalar folded into the GEMM’s scale pointer together with the per-batch activation scale, blk == None. Block-128 class (Qwen official FP8): blk == Some and scale == 1.0 — see Fp8BlockScales for the resident layout contract.

Fields

bytes: CudaSlice<u8>

scale: f32

blk: Option<Fp8BlockScales>