[Refactor][MOE] remove redundant code.

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>

Author: weijinqian_v1

tests/ut/ops/test_token_dispatcher.py

@@ -21,9 +21,9 @@
 
 from tests.ut.base import TestBase
 from vllm_ascend.ops.moe_dispatcher.token_dispatcher import (
-    AscendSocVersion, TokenDispatcherWithAll2AllV, TokenDispatcherWithAllGather,
-    TokenDispatcherWithMC2, _Dispatchers, _register_token_dispatcher,
-    get_token_dispatcher, setup_token_dispatchers)
+    AscendSocVersion, TokenDispatcherWithAll2AllV,
+    TokenDispatcherWithAllGather, TokenDispatcherWithMC2, _Dispatchers,
+    _register_token_dispatcher, get_token_dispatcher, setup_token_dispatchers)
 
 
 class TestTokenDispatcherWithMC2(TestBase):

vllm_ascend/ops/layers/moe_mlp.py

@@ -19,8 +19,9 @@
 import torch
 import torch_npu
 from vllm.forward_context import get_forward_context
+
 from vllm_ascend.ascend_forward_context import FusedMoEState
-from vllm_ascend.utils import (dispose_tensor, is_310p)
+from vllm_ascend.utils import dispose_tensor, is_310p
 
 
 def quant_apply_mlp(hidden_states: torch.Tensor,

vllm_ascend/ops/moe_dispatcher/token_dispatcher.py

@@ -29,11 +29,11 @@
 from vllm.distributed.parallel_state import get_ep_group
 
 from vllm_ascend.distributed.parallel_state import get_mc2_group
-from vllm_ascend.distributed.tensor_parallel import gather_from_sequence_parallel_region
+from vllm_ascend.distributed.tensor_parallel import \
+    gather_from_sequence_parallel_region
 from vllm_ascend.ops.comm_utils import async_all_to_all
 from vllm_ascend.utils import AscendSocVersion, get_ascend_soc_version
 
-
 _Dispatchers: Dict[str, Any] = {}