pub fn moe_expert_down_act_fp8_grouped_tc_w8a8(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
act: (DevicePtr, DevicePtr),
down: (DevicePtr, DevicePtr),
output: DevicePtr,
rows: &Fp8GroupedW8a8Rows,
sh: (DevicePtr, DevicePtr),
sh_down: &Fp8Weight,
sh_down_out: DevicePtr,
n: u32,
k: u32,
stream: u64,
) -> Result<()>Expand description
2026-09-28: W8A8 down over the quantized SiLU products: routed rows into output by
sorted position, the shared rows into sh_down_out by token, both BF16.