[main] [refactor] refactor common_fused_moe.py (#2706)

### What this PR does / why we need it?
1. Move prepare/finalize operation from moe_comm_method to
/ops/moe/fused_moe_prepare_and_finalize
2. Adapt to token_dispatcher in moe_comm_method
3. Move
moe_comm_method/experts_selector/token_dispatcher/fused_moe_prepare_and_finalize
to /ops/moe
### Does this PR introduce _any_ user-facing change?
no
### How was this patch tested?
e2e & ut

- vLLM version: v0.10.1.1
- vLLM main:
f4962a6d55

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

vllm_ascend/quantization/w8a8_dynamic.py

@@ -27,10 +27,8 @@ import vllm_ascend.envs as envs_ascend
 from vllm_ascend.ascend_config import get_ascend_config
 from vllm_ascend.ascend_forward_context import FusedMoEState
 from vllm_ascend.distributed.parallel_state import get_mc2_group
-from vllm_ascend.ops.common_fused_moe import \
-    fused_experts as unified_fused_experts
 from vllm_ascend.ops.fused_moe import unified_fused_experts_eager
-from vllm_ascend.ops.layers.experts_selector import select_experts
+from vllm_ascend.ops.moe.experts_selector import select_experts
 from vllm_ascend.utils import ACL_FORMAT_FRACTAL_NZ
 
 
@@ -221,12 +219,14 @@ class AscendW8A8DynamicFusedMoEMethod:
             global_num_experts=global_num_experts)
 
         if self.use_aclgraph:
-            return unified_fused_experts(
+            moe_comm_method = get_forward_context().moe_comm_method
+            return moe_comm_method.fused_experts(
                 hidden_states=x,
                 w1=layer.w13_weight,
                 w2=layer.w2_weight,
                 topk_weights=topk_weights,
                 topk_ids=topk_ids,
+                row_idx=row_idx,
                 use_int8_w8a8=True,
                 w1_scale=layer.w13_weight_scale,
                 w2_scale=layer.w2_weight_scale,