CUDA `copy_strided_src` 会在偏移源视图的末尾复制数据,从而无声地损坏 `slice_scatter`(CPU 会出现不一致的情况)。

// candle-core/src/cpu_backend/mod.rs:902 -- copies exactly the view's length
StridedBlocks::SingleBlock { start_offset, len } =>
    dst[dst_offset..dst_offset + len]
        .copy_from_slice(&src[start_offset..start_offset + len])

// candle-core/src/cuda_backend/mod.rs:1208 -- derives the length from storage
fn slice_src_and_dst<'a, T>(
    src: &'a CudaSlice<T>,
    src_l: &Layout,
    dst: &'a mut CudaSlice<T>,
    dst_offset: usize,
) -> (cudarc::driver::CudaView<'a, T>, cudarc::driver::CudaViewMut<'a, T>) {
    let src_offset = src_l.start_offset();
    let to_copy = dst
        .len()
        .saturating_sub(dst_offset)
        .min(src.len().saturating_sub(src_offset));
    let src = src.slice(src_offset..src_offset + to_copy);
    let dst = dst.slice_mut(dst_offset..dst_offset + to_copy);
    (src, dst)
}