[BUGFIX] main-sd-bugfix && [UT] add mtp UT (#593)

### What this PR does / why we need it?
The pr will fix some bug about spec decode / MTP
The pr add a mtp e2e UT `test_mtp_correctness.py`

**vllm_ascend/attention/attention.py**
1. add support `self.attn_mask_cache` only has 1 element to cover scene
in which both spec docode and chunked prefill are enabled.

**vllm_ascend/distributed/parallel_state.py**
1. remove 2 assert because spec decode worker would use init_worker
twice

**vllm_ascend/models/deepseek_mtp.py**
1. remove unused params;
2. add support w8a8 in `CustomDeepSeekMTP`

**vllm_ascend/quantization/quant_config.py**
1. use `AscendUnquantizedFusedMoEMethod` instead of
`UnquantizedFusedMoEMethod`

**other**
1. replace `from vllm.logger import init_logger` to `from vllm.logger
import logger` all of the vllm-ascend project



### Does this PR introduce _any_ user-facing change?


### How was this patch tested?

Signed-off-by: mengwei805 <mengwei25@huawei.com>

vllm_ascend/worker/draft_model_runner.py

@@ -19,7 +19,7 @@ from typing import List, Optional
 
 import torch
 from vllm.forward_context import set_forward_context
-from vllm.logger import init_logger
+from vllm.logger import logger
 from vllm.model_executor.layers.sampler import SamplerOutput
 from vllm.multimodal import MultiModalKwargs
 from vllm.sequence import ExecuteModelRequest, IntermediateTensors
@@ -29,8 +29,6 @@ from vllm.worker.model_runner_base import (ModelRunnerBase,
 
 from vllm_ascend.attention.attention import AscendMetadata
 
-logger = init_logger(__name__)
-
 # A flag to enable debug prints for the updated input tensors
 # before each step.
 debug_advance_input = False