[Feature]EPLB:Adapt DispatchGmmCombineDecode operator to eplb tensor list and expert token numbers (#5552)

#### What this PR does / why we need it?
This PR adapt DispatchGmmCombineDecode operator to eplb tensor list and
expert token numbers.

This operator support gmm1, gmm2, gmm1Scale and gmm2Scale in format of
list.
This operator support couting how many token each local expert recieves
by expertTokensNum .


- vLLM version: v0.13.0
- vLLM main:
7157596103

More info about this operator, please refer to RFC: issue
https://github.com/vllm-project/vllm-ascend/issues/5476

vllm_ascend/envs.py

@@ -131,7 +131,7 @@ env_variables: Dict[str, Callable[[], Any]] = {
     # `dispatch_ffn_combine` can be used only for moe layer with W8A8, EP<=16, non-mtp, non-dynamic-eplb.
     # 2: MC2 might be replaced by `dispatch_gmm_combine_decode` operator.
     # `dispatch_gmm_combine_decode` can be used only for **decode node** moe layer
-    # with W8A8, non-dynamic-eplb. And MTP layer must be W8A8.
+    # with W8A8. And MTP layer must be W8A8.
     "VLLM_ASCEND_ENABLE_FUSED_MC2":
     lambda: int(os.getenv("VLLM_ASCEND_ENABLE_FUSED_MC2", '0')),
     # Whether to anbale balance scheduling