[Refactor] remove moe type of multicast. (#4224)

The main purposes of this PR are as follows: 
1. Remove the multicast-related code; 

Reason:
1. In the scenario like a2 Dual-System Back-to-Back Networking，the
performance is worse than all_gather. Before the modification, in e2e
test, it was 3 tps; after the modification, it is 10 tps.
2. At the same time, we usually enable the SP feature，it is consistent
with the current logic.
3. The advantage of broadcast communication lies in the fact that it
does not suffer from uneven DP load and does not require the prefill ACL
graph to be enabled. But we support prefill Acl graph recently.

So we think there is no need to maintain the multicast as one choice in
moe communication.

Performance benefits are as follows:
When not enable_flashcomm1, TTFT remains relatively stable at around
43000ms, which is approximately 15000ms faster than before the
modification.

When enable_flashcomm1, there is no diffenence, TTFT remains relatively
stable at around 29000ms.


- vLLM version: v0.11.0
- vLLM main:
2918c1b49c

---------

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: weijinqian0 <1184188277@qq.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>

vllm_ascend/ascend_forward_context.py

@@ -29,16 +29,8 @@ class FusedMoEState(Enum):
     All2AllSeq = 5
 
 
-class MoECommType(Enum):
-    ALLGATHER = 0
-    MC2 = 1
-    ALLTOALL = 2
-    NAIVE_MULTICAST = 3
-
-
-# TODO(zzzzwwjj): add soc_version to choose branch
-def _get_fused_moe_state(ep_size: int, with_prefill: bool,
-                         is_deepseek_v3_r1: bool):
+def get_fused_moe_state(ep_size: int, with_prefill: bool,
+                        is_deepseek_v3_r1: bool):
     # the fusion operator torch_npu.npu_grouped_matmul_finalize_routing called by allgather ep
     # only supports deepseek v3/r1
     if (envs_ascend.VLLM_ENABLE_FUSED_EXPERTS_ALLGATHER_EP and ep_size > 1
@@ -56,6 +48,12 @@ def _get_fused_moe_state(ep_size: int, with_prefill: bool,
         return FusedMoEState.MC2
 
 
+class MoECommType(Enum):
+    ALLGATHER = 0
+    MC2 = 1
+    ALLTOALL = 2
+
+
 @contextmanager
 def set_ascend_forward_context(
         attn_metadata: Any,
@@ -103,8 +101,8 @@ def set_ascend_forward_context(
         is_deepseek_v3_r1 = hasattr(
             vllm_config.model_config.hf_config, 'n_routed_experts'
         ) and vllm_config.model_config.hf_config.n_routed_experts == 256
-        fused_moe_state = _get_fused_moe_state(ep_size, with_prefill,
-                                               is_deepseek_v3_r1)
+        fused_moe_state = get_fused_moe_state(ep_size, with_prefill,
+                                              is_deepseek_v3_r1)
         forward_context.fused_moe_state = fused_moe_state
         forward_context.in_profile_run = in_profile_run