pub fn kquant_q8_1_rows(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
x_bf16: DevicePtr,
out_q8: DevicePtr,
m: u32,
k: u32,
stream: u64,
) -> Result<()>Expand description
bf16 [m, k] -> block_q8_1 [m, k/32] (kquant_q8_1_rows_bf16). k % 32 == 0.