[Refactor] [SP]The sequence parallelism characteristics in the MoE and Dense models are integrated into a single solution. (#3085)

What this PR does / why we need it?

there are two sets of sp implementations for moe and dense models. One
is called sequence_parallelism, and the other is flashcomm_v1.
We did the following things：

Merge two sets of code with the same implementation into one.
Remove the implementation of sequence_parallelism, as this solution
cannot support aclgraph.
Does this PR introduce any user-facing change?

No

How was this patch tested?

e2e&ut

- vLLM version: v0.10.2
- vLLM main:
f225ea7dd9

---------

Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
Co-authored-by: weijinqian_v1 <weijinqian@huawei.com>

vllm_ascend/utils.py

@@ -590,6 +590,14 @@ def dense_optim_enable() -> bool:
     return envs_ascend.VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE
 
 
+def enable_sp() -> bool:
+    from vllm.config import get_cached_compilation_config
+
+    return (
+        get_cached_compilation_config().pass_config.enable_sequence_parallelism
+        or envs_ascend.VLLM_ASCEND_ENABLE_FLASHCOMM)
+
+
 def is_moe_model(vllm_config: VllmConfig):
     config = vllm_config.model_config.hf_config
     return any('experts' in key.lower() for key in config.to_dict())