pub fn bf16_concat(
gpu: &dyn GpuBackend,
kernel: KernelHandle,
a: DevicePtr,
b: DevicePtr,
output: DevicePtr,
n: u32,
stream: u64,
) -> Result<()>Expand description
2026-09-25: BF16 concatenation (kernel bf16_concat):
out[0..N] = a[0..N], out[N..2N] = b[0..N].