diff --git a/src/exo/worker/engines/mlx/auto_parallel.py b/src/exo/worker/engines/mlx/auto_parallel.py index 74681438..9dcf41c4 100644 --- a/src/exo/worker/engines/mlx/auto_parallel.py +++ b/src/exo/worker/engines/mlx/auto_parallel.py @@ -681,8 +681,8 @@ class MiniMaxShardingStrategy(TensorParallelShardingStrategy): def __call__( self, x: mx.array, - mask: Optional[mx.array] = None, - cache: Optional[Any] = None, + mask: mx.array | Any = None, + cache: Any | None = None, ) -> mx.array: B, L, D = x.shape