[Perf] move quant before allgather in Allgather EP (#3420)

### What this PR does / why we need it?
move quant before allgather in Allgather EP, rely on
https://github.com/vllm-project/vllm-ascend/pull/3334

Deepseek R1 W8A8 performance on A2 with
`HCCL_ALGO="level0:NA;level1:pipeline"`:
| Seq length | Mean TTFT (ms) main | Mean TTFT (ms)  this PR |
|----------|----------|----------|
| 4k   |  375.21  | 364.99   |
| 16k  | 1465.23   | 1421.75  |
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.11.0
- vLLM main:
83f478bb19

---------

Signed-off-by: realliujiaxu <realliujiaxu@163.com>

vllm_ascend/ops/fused_moe/fused_moe.py

@@ -289,7 +289,7 @@ class AscendFusedMoE(FusedMoE):
 
         self.enable_shared_expert_dp = ascend_config.enable_shared_expert_dp
 
-        setup_moe_comm_method(self.moe_config)
+        setup_moe_comm_method(self.moe_config, self.quant_method)
 
     def update_expert_map(self, new_expert_map):
         self.expert_map = new_expert_map
@@ -336,11 +336,17 @@ class AscendFusedMoE(FusedMoE):
             replace_allreduce=forward_context.sp_enabled,
             enable_shared_expert_dp=self.enable_shared_expert_dp)
 
+        if isinstance(hidden_states, tuple):
+            hidden_states, pertoken_scale = hidden_states
+        else:
+            pertoken_scale = None
+
         # Matrix multiply.
         final_hidden_states = self.quant_method.apply(
             layer=self,
             x=hidden_states,
             router_logits=router_logits,
+            pertoken_scale=pertoken_scale,
             top_k=self.top_k,
             renormalize=self.renormalize,
             use_grouped_topk=self.use_grouped_topk,