[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>

tests/ut/torchair/ops/test_torchair_fused_moe.py

@@ -23,7 +23,7 @@ from pytest_mock import MockerFixture
 from vllm.model_executor.layers.fused_moe import FusedMoEMethodBase
 
 import vllm_ascend
-from vllm_ascend.ascend_forward_context import _get_fused_moe_state
+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 (
     TorchairAscendFusedMoE, TorchairAscendUnquantizedFusedMoEMethod)
@@ -360,7 +360,7 @@ class TestTorchairAscendUnquantizedFusedMoEMethod:
         global_redundant_expert_num = vllm_ascend.torchair.ops.torchair_fused_moe.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(
+        forward_context = MagicMock(fused_moe_state=get_fused_moe_state(
             ep_size, is_prefill, is_deepseek_v3_r1))
         with patch(
                 "vllm_ascend.torchair.ops.torchair_fused_moe.get_forward_context",
@@ -396,7 +396,7 @@ class TestTorchairAscendUnquantizedFusedMoEMethod:
         ep_size = others_param
         is_prefill = False
         forward_context = MagicMock(
-            fused_moe_state=_get_fused_moe_state(ep_size, is_prefill, True))
+            fused_moe_state=get_fused_moe_state(ep_size, is_prefill, True))
         with patch("vllm_ascend.torchair.ops.torchair_fused_moe.get_forward_context", return_value=forward_context), \
              patch("vllm_ascend.torchair.ops.torchair_fused_moe.get_ascend_soc_version", return_value=AscendSocVersion.A3):
             expert_map = torch.tensor([0, 1, 2, -1, -1, -1, -1, -1])