pub fn w8a8_act_quant(
gpu: &dyn GpuBackend,
kernels: &W8a8Kernels,
scale: W8a8Scale,
x: DevicePtr,
ldx: u32,
rows: usize,
k: u32,
scratch: &W8a8Scratch,
stream: u64,
) -> Result<()>Expand description
2026-09-28: Quantize rows rows of the BF16 activation x ([rows, ldx],
the first k columns) into scratch for scale’s layout.