[main][Feature]Moe alltoallv communication optimization for unquantized RL training sence (#2088)

It comes from 0.9.1dev
[0.9.1][Feature]Moe alltoallv communication optimization for unquantized
RL training sence & alltoallv support dpo (#1547)

- vLLM version: v0.10.0
- vLLM main:
97608dc276

---------

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: curryliu <120010041@link.cuhk.edu.cn>
Signed-off-by: wangli <wangli858794774@gmail.com>
Signed-off-by: ChenTaoyu-SJTU <ctynb@qq.com>
Signed-off-by: taoxudonghaha <justsheldon@163.com>
Signed-off-by: shen-shanshan <467638484@qq.com>
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
Signed-off-by: leo-pony <nengjunma@outlook.com>
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Signed-off-by: MengqingCao <cmq0113@163.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: whx <56632993+whx-sjtu@users.noreply.github.com>
Co-authored-by: curryliu <99582471+Irving11-BKN@users.noreply.github.com>
Co-authored-by: Li Wang <wangli858794774@gmail.com>
Co-authored-by: TaoYu Chen <ctynb@qq.com>
Co-authored-by: taoxudonghaha <justsheldon@163.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>
Co-authored-by: leo-pony <nengjunma@outlook.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>

vllm_ascend/ascend_forward_context.py

@@ -18,6 +18,7 @@ class FusedMoEState(Enum):
     MC2 = 2
     AllGatherEP = 3
     NaiveMulticast = 4
+    All2AllSeq = 5
 
 
 # TODO(zzzzwwjj): add soc_version to choose branch
@@ -33,6 +34,10 @@ def get_fused_moe_state(ep_size: int, with_prefill: bool,
             return FusedMoEState.NaiveMulticast
         else:
             return FusedMoEState.AllGather
+    elif envs.VLLM_ASCEND_ENABLE_MOE_ALL2ALL_SEQ:
+        # MC2 Dispatch/Combine performs better than alltoall_seq in decoding stage.
+        return (FusedMoEState.All2AllSeq if
+                (ep_size < 16 or with_prefill) else FusedMoEState.MC2)
     # NOTE: mc2 need ep_size >= 16 & all2all can't use in torchair graph.
     elif ep_size < 16 or with_prefill:
         return FusedMoEState.All2All