Function moe_expert_gate_up_act_fp8_grouped 

pub fn moe_expert_gate_up_act_fp8_grouped(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    geometry: Fp8GroupedGeometry,
    input: DevicePtr,
    gp_w: DevicePtr,
    gp_s: DevicePtr,
    up_w: DevicePtr,
    up_s: DevicePtr,
    act: DevicePtr,
    expert_offsets: DevicePtr,
    sorted_token_ids: DevicePtr,
    active_experts: DevicePtr,
    active_count: DevicePtr,
    sh_gate: &Fp8Weight,
    sh_up: &Fp8Weight,
    sh_act: DevicePtr,
    n: u32,
    k: u32,
    cap: u32,
    num_tokens: u32,
    stream: u64,
) -> Result<()>

2026-09-26: Grouped FP8 gate+up and SiLU. cap is fp8_grouped_active_cap; the first ceil(num_tokens / geometry.rows_per_pass) block rows are the shared expert. Writes the product silu(bf16(gate)) * bf16(up), [positions, n] for the routed experts into act and [num_tokens, n] for the shared expert into sh_act: FP32 from the scalar kernel (FP8_GROUPED_GATE_UP_SCALAR), BF16 from the tensor-core one (FP8_GROUPED_GATE_UP_TC, 2026-09-28).