[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/attention/attention.py

@@ -113,7 +113,8 @@ class AttentionMaskBuilder:
             self.update_attn_cache(max_seq_len, dtype, device)
             # FIXME: Currently the mask value of chunked-prefill situation and Prefill-Only situation
             # is not the same. Fix this in the future when kernel is ready.
-            if self.attn_mask_cache[0][1] > 0:
+            if self.attn_mask_cache.numel(
+            ) > 1 and self.attn_mask_cache[0][1] > 0:
                 attn_mask = self.get_attn_mask(  # type: ignore
                     max_seq_len, dtype, device)
                 attn_mask *= -10000

vllm_ascend/attention/mla_v1.py

@@ -6,7 +6,6 @@ import torch_npu
 from vllm.attention.backends.abstract import (AttentionBackend, AttentionLayer,
                                               AttentionMetadata,
                                               MLAAttentionImpl)
-from vllm.logger import init_logger
 from vllm.model_executor.layers.linear import (ColumnParallelLinear,
                                                LinearBase, RowParallelLinear,
                                                UnquantizedLinearMethod)
@@ -21,8 +20,6 @@ if TYPE_CHECKING:
     from vllm.v1.core.sched.output import SchedulerOutput
     from vllm.v1.worker.gpu_input_batch import InputBatch
 
-logger = init_logger(__name__)
-
 
 class AscendMLABackend(AttentionBackend):