[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/ascend_forward_context.py

@@ -11,6 +11,7 @@ from vllm.forward_context import (BatchDescriptor, get_forward_context,
                                   set_forward_context)
 
 import vllm_ascend.envs as envs_ascend
+from vllm_ascend.utils import enable_sp
 
 
 class FusedMoEState(Enum):
@@ -101,21 +102,19 @@ def set_ascend_forward_context(
         # due to multiple warmups before actual capturing
         forward_context.capturing = False
 
-        # set for flashcomm_v1, 1000 is the batchsize concurrency threshold for enabling the flashcomm_v1 feature.
+        # set for sequence parallelism, 1000 is the batch size concurrency threshold for enabling the flashcomm_v1 or sequence_parallelism feature.
         # Currently, it is an empirical value. In normal scenarios, if the concurrency exceeds this threshold,
         # the performance benefits can be maximized. Conversely, if the concurrency is below the threshold,
         # the performance may degrade due to the switching of communication methods.
-        flashcomm_v1_enabled = envs_ascend.VLLM_ASCEND_ENABLE_DENSE_OPTIMIZE and \
-            envs_ascend.VLLM_ASCEND_ENABLE_FLASHCOMM and \
+        sp_enabled = enable_sp() and \
             tp_world_size > 1 and \
             num_tokens is not None and num_tokens > 1000
 
-        if flashcomm_v1_enabled:
+        if sp_enabled:
             pad_size = (tp_world_size -
                         (num_tokens % tp_world_size)) % tp_world_size
             forward_context.pad_size = pad_size
-
-        forward_context.flashcomm_v1_enabled = flashcomm_v1_enabled
+        forward_context.sp_enabled = sp_enabled
 
         # set this for rope forward_oot using
         forward_context.is_first_layer = True