[BugFix]Support redundant experts in EPLB (#3473)

This PR adds support for redundant experts in the EPLB. 

Key points: 
- Use global_num_experts = num_experts + num_redundant_experts
consistently.
- Backward compatible when num_redundant_experts=0. 

Tested 
On a 16-rank setup (W8A8) with static EPLB and expert_map_path,
verifying router logits shape and successful requests.

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

Signed-off-by: yechao237 <yechao20180411@gmail.com>

tests/ut/eplb/core/test_eplb_utils.py

@@ -34,8 +34,8 @@ def test_determine_default_expert_map_multiple_worlds_with_redundant():
         rank_id=0,
         global_redundant_expert_num=1)
 
-    assert count == 3
-    assert torch.all(expert_map[0:3] >= 0)
+    assert count == 2
+    assert torch.all(expert_map[0:2] >= 0)
 
 
 def test_generate_log2phy_map_single_rank_holding():

tests/ut/ops/test_fused_ops.py

@@ -257,7 +257,7 @@ class MockFusedMoEMethod(FusedMoEMethodBase):
 
 class TestExpertsSelector:
 
-    @pytest.mark.parametrize("global_num_experts", [[256], [128]])
+    @pytest.mark.parametrize("global_num_experts", [256, 128])
     def test_select_experts(self, mock_dist_env, mock_moe_env,
                             global_num_experts):
 

tests/ut/torchair/ops/test_torchair_fused_moe.py

@@ -22,6 +22,7 @@ import torch_npu
 from pytest_mock import MockerFixture
 from vllm.model_executor.layers.fused_moe import FusedMoEMethodBase
 
+from vllm_ascend.ascend_config import get_ascend_config
 from vllm_ascend.ascend_forward_context import _get_fused_moe_state
 from vllm_ascend.quantization.quant_config import AscendFusedMoEMethod
 from vllm_ascend.torchair.ops.torchair_fused_moe import (
@@ -355,7 +356,9 @@ class TestTorchairAscendUnquantizedFusedMoEMethod:
         """
         global_num_experts, ep_size = others_param
         is_prefill = False
-        is_deepseek_v3_r1 = global_num_experts == 256
+        global_redundant_expert_num = get_ascend_config(
+        ).init_redundancy_expert
+        is_deepseek_v3_r1 = global_num_experts - global_redundant_expert_num == 256
         forward_context = MagicMock(fused_moe_state=_get_fused_moe_state(
             ep_size, is_prefill, is_deepseek_v3_r1))
         with patch(