clean code

Signed-off-by: shikang-hangzhou <459956190@qq.com>

Author: shikang-hangzhou

vllm_ascend/models/deepseek_dbo.py

@@ -33,17 +33,15 @@
 from torch import nn
 from transformers import PretrainedConfig
 from vllm.attention import AttentionMetadata
-from vllm.config import (CacheConfig, ModelConfig, VllmConfig,
-                         get_current_vllm_config)
+from vllm.config import (CacheConfig, ModelConfig, VllmConfig)
 from vllm.distributed import (get_ep_group, get_pp_group,
                               get_tensor_model_parallel_rank,
                               get_tensor_model_parallel_world_size,
                               get_tp_group, tensor_model_parallel_all_reduce)
 from vllm.distributed.parallel_state import get_dp_group
 from vllm.forward_context import get_forward_context
 from vllm.model_executor.layers.layernorm import RMSNorm
-from vllm.model_executor.layers.linear import (ReplicatedLinear,
-                                               UnquantizedLinearMethod)
+from vllm.model_executor.layers.linear import UnquantizedLinearMethod
 from vllm.model_executor.layers.logits_processor import LogitsProcessor
 from vllm.model_executor.layers.quantization import QuantizationConfig
 from vllm.model_executor.layers.sampler import get_sampler
@@ -57,10 +55,8 @@
 from vllm.sequence import IntermediateTensors
 
 import vllm_ascend.envs as envs_ascend
-from vllm_ascend.ascend_config import get_ascend_config
 from vllm_ascend.ascend_forward_context import FusedMoEState
 from vllm_ascend.models.deepseek_v2 import (CustomDeepseekV2DecoderLayer,
-                                            CustomDeepseekV2MLAAttention,
                                             CustomDeepseekV2MLP,
                                             CustomDeepseekV2MoE)
 from vllm_ascend.multistream.base import MSEventKey
@@ -72,7 +68,6 @@
 from vllm_ascend.multistream.metadata import (MultiStreamConfig,
                                               MultiStreamStepMetadata,
                                               make_multistream_metadata_ds)
-from vllm_ascend.ops.fused_moe import AscendFusedMoE
 from vllm_ascend.quantization.w8a8_dynamic import (
     AscendW8A8DynamicLinearMethod, apply_mlp)
 from vllm_ascend.utils import dispose_tensor