[v0.18.0][BugFix] Fix Qwen3.5 MoE flash comm v1 shared expert shape error of mtp layer on A2 (#8004)

### What this PR does / why we need it?
Fix Qwen3.5 MoE MTP layer shared expert shape error when flash comm v1
is enabled.

### Does this PR introduce _any_ user-facing change?
No.

### How was this patch tested?

- vLLM version: v0.18.0
- vLLM main:
35141a7eed

Signed-off-by: Wangbingjie <wangbj1207@126.com>

vllm_ascend/spec_decode/eagle_proposer.py

@@ -1595,10 +1595,8 @@ class SpecDecodeBaseProposer(EagleProposer):
         hidden_states: torch.Tensor,
         positions: torch.Tensor,
     ) -> tuple[torch.Tensor, torch.Tensor]:
-        if self.is_multimodal_model and _EXTRA_CTX.flash_comm_v1_enabled:
-            return hidden_states, positions
         if self.method == "mtp":
-            if _EXTRA_CTX.flash_comm_v1_enabled:
+            if _EXTRA_CTX.flash_comm_v1_enabled and not self.is_multimodal_model:
                 hidden_states = torch.ops.vllm.maybe_pad_and_reduce(hidden_states)
                 positions = positions.unsqueeze(-1)
                 positions = torch.ops.vllm.maybe_pad_and_reduce(positions)