adjusting the communication method in graph mode (#1194)

### What this PR does / why we need it?
Communication performance optimization: replace allreduce with
reduce_scatter+all_gather in MLA layer's TP group，to remove
stridedsliced and all_gather in MOE layer.
when tp > 1, It is enabled during the decode phase of the graph mode
when enable_multistream_moe、MLA, use_v1, and MC2 are used.
According to the end-to-end RL inference test results, this PR can bring
3% gain in the decode stage.

**Before Improvement**
Profiling kernel_details

![image](https://github.com/user-attachments/assets/1bb5dfa1-809b-410a-90c9-c5fd23cff003)
Evaluation

![image](https://github.com/user-attachments/assets/0b8ea0c7-88e7-410f-9ef4-f0cfe910cdc7)

![image](https://github.com/user-attachments/assets/94fde910-c125-4c2e-8de4-88fc3fafc057)

**After Improvement**
Profiling kernel_details

![image](https://github.com/user-attachments/assets/55fac0e0-11f2-4654-8fd4-287949e0b29e)
Evaluation

![image](https://github.com/user-attachments/assets/e923f74b-29c4-4171-9382-40a00cf05df0)

![image](https://github.com/user-attachments/assets/5dba7967-07ea-4926-a8be-804bfd34e3e4)

### Does this PR introduce _any_ user-facing change?
Users need to configure enable_multistream_moe=True

### How was this patch tested?
Add e2e test cases to cover code logic

Signed-off-by: sharonyunyun <zhangying134@huawei.com>

tests/e2e/multicard/test_offline_inference_distributed.py

@@ -47,6 +47,32 @@ def test_models_distributed_QwQ():
         vllm_model.generate_greedy(example_prompts, max_tokens)
 
 
+def test_models_distributed_DeepSeek_multistream_moe():
+    example_prompts = [
+        "Hello, my name is",
+    ]
+    dtype = "half"
+    max_tokens = 5
+    with VllmRunner(
+            "vllm-ascend/DeepSeek-V3-Pruning",
+            dtype=dtype,
+            tensor_parallel_size=2,
+            distributed_executor_backend="mp",
+            additional_config={
+                "torchair_graph_config": {
+                    "enabled": True,
+                    "enable_multistream_moe": True,
+                },
+                "ascend_scheduler_config": {
+                    "enabled": True,
+                },
+                "refresh": True,
+            },
+            enforce_eager=False,
+    ) as vllm_model:
+        vllm_model.generate_greedy(example_prompts, max_tokens)
+
+
 def test_models_distributed_DeepSeek():
     example_prompts = [
         "Hello, my name is",