[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>

vllm_ascend/eplb/core/eplb_utils.py

@@ -40,14 +40,6 @@ def determine_default_expert_map(global_expert_num, world_size, rank_id,
         end = global_expert_num
         local_count = global_expert_num - rank_id * local_num_experts
 
-    if isinstance(global_redundant_expert_num,
-                  int) and rank_id < global_redundant_expert_num:
-        local_count += 1
-        if end < global_expert_num:
-            end += 1
-        else:
-            start -= 1
-
     if isinstance(local_count, int):
         local_ids = torch.arange(local_count, dtype=torch.int32)
         expert_map[start:end] = local_ids
@@ -118,14 +110,6 @@ def determine_default_log2phy_map(global_expert_num, world_size, rank_id,
             end = global_expert_num
             local_count = global_expert_num - r * local_num_experts
 
-        if isinstance(global_redundant_expert_num,
-                      int) and rank_id < global_redundant_expert_num:
-            local_count += 1
-            if end < global_expert_num:
-                end += 1
-            else:
-                start -= 1
-
         if isinstance(local_count, int):
             local_ids = torch.arange(local_count, dtype=torch.int32)
             expert_map_all[r, start:end] = local_ids