support async mtp (#4511)

### What this PR does / why we need it?
this pr aims to support async_scheduling for mtp, which refer to vllm pr
https://github.com/vllm-project/vllm/pull/24799.
and this pr fix some synchronize problem in vllm-ascend.
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?


- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

---------

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Co-authored-by: wangxiyuan <wangxiyuan1007@gmail.com>

tests/ut/attention/test_attention_v1.py

@@ -87,6 +87,7 @@ class TestAscendAttentionMetadataBuilder(TestBase):
         self.mock_vllm_config.scheduler_config.decode_max_num_seqs = 10
         self.mock_vllm_config.scheduler_config.chunked_prefill_enabled = False
         self.mock_device = 'cpu:0'
+        torch.Tensor.pin_memory = lambda x: x  # noqa
         self.builder = AscendAttentionMetadataBuilder(None, None,
                                                       self.mock_vllm_config,
                                                       self.mock_device)