[Feature] Support moe multi-stream for aclgraph. (#2946)

This PR puts the calculation of shared experts into a separate stream,
overlaping with routing experts.

- vLLM version: v0.10.2
- vLLM main:
fbd6523ac0

---------

Signed-off-by: whx-sjtu <2952154980@qq.com>

tests/e2e/multicard/test_offline_inference_distributed.py

@@ -66,8 +66,8 @@ def test_models_distributed_DeepSeek_multistream_moe():
             additional_config={
                 "torchair_graph_config": {
                     "enabled": True,
-                    "enable_multistream_moe": True,
                 },
+                "enable_multistream_moe": True,
                 "ascend_scheduler_config": {
                     "enabled": True,
                 },