[Refactor][MoE] remove redundant code after refactoring fused_moe (#2612)

### What this PR does / why we need it?
There are a lot of redundant codes related to moe here, and the
structure is not very clear.
We did the following things：

we have placed the relatively independent code related to apply_mlp into
a separate file;
removed the environment variables of alltoall_buffer and alltoall_seq.
Remove the code related to alltoall_buffer and alltoall_seq, and retain
the sole TokenDispatcher inheritance class.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e&ut

- vLLM version: v0.10.1.1
- vLLM main:
4071c76cf3

---------

Signed-off-by: Pr0Wh1teGivee <calvin_zhu0210@outlook.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian0 <12153182+weijinqian0@users.noreply.github.com>

tests/e2e/multicard/test_offline_inference_distributed.py

@@ -108,14 +108,13 @@ def test_models_distributed_pangu():
     ]
     max_tokens = 5
 
-    with VllmRunner(
-            snapshot_download("vllm-ascend/pangu-pro-moe-pruing"),
-            max_model_len=8192,
-            enforce_eager=True,
-            dtype="auto",
-            tensor_parallel_size=2,
-            distributed_executor_backend="mp",
-    ) as vllm_model:
+    with VllmRunner(snapshot_download("vllm-ascend/pangu-pro-moe-pruing"),
+                    max_model_len=8192,
+                    enforce_eager=True,
+                    dtype="auto",
+                    tensor_parallel_size=2,
+                    distributed_executor_backend="mp",
+                    enable_expert_parallel=True) as vllm_model:
         vllm_model.generate_greedy(example_prompts, max_tokens)
 
 
@@ -141,28 +140,6 @@ def test_models_distributed_topk() -> None:
         vllm_model.generate(example_prompts, sampling_params)
 
 
-@patch.dict(os.environ, {"VLLM_ASCEND_ENABLE_MOE_ALL2ALL_SEQ": "1"})
-def test_models_distributed_alltoallv() -> None:
-    example_prompts = [
-        "vLLM is a high-throughput and memory-efficient inference and serving engine for LLMs.",
-        "Briefly describe the major milestones in the development of artificial intelligence from 1950 to 2020.",
-        "Compare and contrast artificial intelligence with human intelligence in terms of processing information.",
-    ]
-    dtype = "half"
-    sampling_params = SamplingParams(max_tokens=5,
-                                     temperature=0.0,
-                                     top_k=50,
-                                     top_p=0.9)
-
-    with VllmRunner(
-            "deepseek-ai/DeepSeek-V2-Lite",
-            dtype=dtype,
-            tensor_parallel_size=2,
-            distributed_executor_backend="mp",
-    ) as vllm_model:
-        vllm_model.generate(example_prompts, sampling_params)
-
-
 def test_models_distributed_Qwen3_W8A8():
     example_prompts = [
         "Hello, my name is",