[EPLB][Nightly][Bugfix] Get expert from moe layer only (#5908)

### What this PR does / why we need it?
1. If the model has dense layers, the current code will attempt to
obtain the routing experts of the dense layers, which will cause an
error. This should be fixed by modifying the code to skip the dense
layers when obtaining the routing experts.
2. The global_expert_map that the function directly outputs a affects
the performance of dsv3.2.
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?

DeepSeek V3.1 conversation is normal.

#### aime precision test (dsv3.1)
baseline without eplb
| dataset | version | metric | mode | vllm-api-general-chat |
|----- | ----- | ----- | ----- | -----|
| aime2024 | 604a78 | accuracy | gen | 66.67 |

eplb
| dataset | version | metric | mode | vllm-api-general-chat |
|----- | ----- | ----- | ----- | -----|
| aime2024 | 604a78 | accuracy | gen | 70.00 |

- vLLM version: v0.13.0
- vLLM main:
11b6af5280

Signed-off-by: shenchuxiaofugui <1311027364@qq.com>

vllm_ascend/ops/fused_moe/fused_moe.py

@@ -202,10 +202,8 @@ class AscendFusedMoE(FusedMoE):
 
         # init moe
         eplb_config = ascend_config.eplb_config
-        self.global_expert_map, self.log2phy, self.global_redundant_expert_num = init_eplb_config(
+        self.global_expert_map, self._expert_map, self.log2phy, self.global_redundant_expert_num = init_eplb_config(
             eplb_config, self.moe_instance_id, self.moe_config)
-        if self.global_expert_map is not None:
-            self._expert_map = self.global_expert_map[self.ep_rank].npu()
         self.global_num_experts = num_experts + self.global_redundant_expert_num
         self.dynamic_eplb = eplb_config.dynamic_eplb and (self.log2phy
                                                           is not None)