Function predequant_nvfp4_to_fp8 

pub fn predequant_nvfp4_to_fp8(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    b_packed: DevicePtr,
    b_scale: DevicePtr,
    scale2: f32,
    b_fp8: DevicePtr,
    n: u32,
    k: u32,
    stream: u64,
) -> Result<()>

2026-09-25: Dequantize an NVFP4 weight to FP8 E4M3: reads B_packed[N, K/2], B_scale[N, K/16] and scale2, writes B_fp8[N, K]. QuantizedWeight::predequant_to_fp8 calls it.