[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/quantization/w8a8_dynamic.py

@@ -203,7 +203,7 @@ class AscendW8A8DynamicFusedMoEMethod:
         **kwargs,
     ) -> torch.Tensor:
         assert router_logits.shape[
-            1] == global_num_experts, "Number of global experts mismatch"
+            1] == global_num_experts - global_redundant_expert_num, "Number of global experts mismatch (excluding redundancy)"
 
         topk_weights, topk_ids = select_experts(
             hidden_states=x,