[0.11.0][MTP][Aclgraph] Fix the support aclgraph with MTP (#3912)

### What this PR does / why we need it?
Fix 2 breaks of aclgraph with MTP:
1. deepseekmtp in vllm 0.11.0 does not support aclgraph and lack the
`support_torch_compile` decorator
2. There is a d2h synchornization in the original forward of mtp
predictor. The fix pr in vllm
https://github.com/vllm-project/vllm/pull/27643

As we'll fix it in vllm main, this fix pr is only needed in branch
v0.11.0-dev

The profling shows that MTP replays in aclgraph now:
<img width="1612" height="1866" alt="a7d7f04155df4ed454b7eb20a92b2e2a"
src="https://github.com/user-attachments/assets/eaa4b9ff-aeb0-416d-964f-5a06e497f155"
/>

### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->

---------

Signed-off-by: MengqingCao <cmq0113@163.com>

vllm_ascend/spec_decode/mtp_proposer.py

@@ -11,7 +11,6 @@ from vllm.forward_context import BatchDescriptor, get_forward_context
 from vllm.model_executor.model_loader import get_model_loader
 from vllm.model_executor.model_loader.utils import (
     process_weights_after_loading, set_default_torch_dtype)
-from vllm.model_executor.models.deepseek_mtp import DeepSeekMTP
 from vllm.v1.core.sched.output import SchedulerOutput
 from vllm.v1.sample.metadata import SamplingMetadata
 from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
@@ -19,6 +18,8 @@ from vllm.v1.spec_decode.metadata import SpecDecodeMetadata
 from vllm_ascend.ascend_config import get_ascend_config
 from vllm_ascend.ascend_forward_context import set_ascend_forward_context
 from vllm_ascend.attention.utils import AscendCommonAttentionMetadata
+from vllm_ascend.patch.worker.patch_deepseek_mtp import \
+    AscendDeepSeekMTP as DeepSeekMTP
 from vllm_ascend.spec_decode.interface import Proposer, SpecDcodeType
 from vllm_ascend.torchair.models.torchair_deepseek_mtp import \
     TorchairDeepSeekMTP