pub fn quantize_act_q8_1(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
input_bf16: DevicePtr,
out_q8: DevicePtr,
m: u32,
k: u32,
stream: u64,
) -> Result<()>Expand description
Quantize bf16 activations [m, k] -> q8_1_mmq (DS4 layout) into out_q8.