[Feature] model_runner refactor (#4764)

### What this PR does / why we need it?
refactor npu_modelrunner， we should be close to gpu_modelrunner 

### Does this PR introduce _any_ user-facing change?
NO

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

---------

Signed-off-by: zhenwenqi2024 <zhenwenqi_2022@qq.com>
Signed-off-by: zhenwenqi2024 <155598497+zhenwenqi2024@users.noreply.github.com>

vllm_ascend/attention/mla_v1.py

@@ -25,6 +25,7 @@ from vllm.v1.attention.backends.utils import AttentionCGSupport
 
 from vllm_ascend import envs
 from vllm_ascend.ascend_config import get_ascend_config
+from vllm_ascend.ascend_forward_context import get_cos_and_sin
 from vllm_ascend.attention.attention_v1 import AscendAttentionState
 from vllm_ascend.attention.utils import (AscendCommonAttentionMetadata,
                                          maybe_save_kv_layer_to_connector,
@@ -625,8 +626,7 @@ class AscendMLAMetadataBuilder:
 
         decode_metadata = None
         if num_decodes > 0:
-            cos = common_attn_metadata.cos
-            sin = common_attn_metadata.sin
+            cos, sin = get_cos_and_sin()
             # Notice that num_decodes != num_decode_tokens in SpecDecoding Scenario
             actual_seq_lengths_q = query_start_loc_cpu[1:num_decodes +
                                                        1].tolist()