Function moe_grouped_down_cutlass 

pub fn moe_grouped_down_cutlass(
    gpu: &dyn GpuBackend,
    eoff_cached: Option<&[i32]>,
    host: &MoeCutlassDownHostTables,
    a: DevicePtr,
    c: DevicePtr,
    expert_offsets: DevicePtr,
    hidden: u32,
    inter: u32,
    stream: u64,
) -> Result<()>

Single-launch CUTLASS grouped NVFP4 DOWN projection. a is the post-SiLU intermediate [total_expanded, inter] (already expert-contiguous — no gather). host is the down third of the load-time snapshot; expert_offsets is the device i32 [num_experts+1] prefix sum.