moe_act_quant_e4m3

Function moe_act_quant_e4m3 

Source
pub fn moe_act_quant_e4m3(
    gpu: &dyn GpuBackend,
    kernel: KernelHandle,
    x: DevicePtr,
    q: DevicePtr,
    s: DevicePtr,
    rows: u32,
    k: u32,
    stream: u64,
) -> Result<()>
Expand description

2026-09-28: E4M3 per (row, 128-K group) of x [rows, k] BF16 into q / s.