fix moe run error

vllm/model_executor/layers/fused_moe/fused_moe.py

@@ -5,7 +5,7 @@ import functools
 import json
 import os
 import math
-from typing import Any, Callable, Optional, List, Optional, Tuple
+from typing import Any, Callable, Dict, Optional, List, Optional, Tuple
 
 import torch
 

vllm/model_executor/layers/fused_moe/moe_align_block_size.py

 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
-from typing import Optional
+from typing import Optional, Tuple
 
 import torch
 
@@ -153,9 +153,9 @@ def moe_align_block_size(
     block_size: int,
     num_experts: int,
     expert_map: Optional[torch.Tensor] = None,
-    pad_sorted_ids: bool = False
+    pad_sorted_ids: bool = False,
     num_token: Optional[int] = None
-) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
+) -> Tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
     """
     Aligns the token distribution across experts to be compatible with block
     size for matrix multiplication.
@@ -253,4 +253,4 @@ def moe_align_block_size(
     if expert_map is not None:
         expert_ids = expert_map[expert_ids]
 
-    return sorted_ids, expert_ids, num_tokens_post_pad
+    return sorted_ids, expert_ids, num_tokens_post_pad
\ No newline at end of file