adapt to main2main for model runner v2 (#7578)

### What this PR does / why we need it?
This PR aims to adapt to newest commit of vllm main branch for model
runner v2. please refer to
https://github.com/vllm-project/vllm-ascend/issues/5208
### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?

- vLLM version: v0.18.0
- vLLM main:
ed359c497a

---------

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>

vllm_ascend/worker/v2/utils.py

@@ -1,12 +1,8 @@
 from contextlib import contextmanager
 
 import torch
-import vllm
 from vllm.logger import logger
 
-from vllm_ascend.worker.v2.block_table import AscendBlockTables
-from vllm_ascend.worker.v2.model_states import init_asecnd_model_state
-
 
 @contextmanager
 def torch_cuda_wrapper():
@@ -27,27 +23,3 @@ def torch_cuda_wrapper():
         yield
     finally:
         pass
-
-
-@contextmanager
-def block_table_wrapper():
-    try:
-        # vllm-ascend need to initialize slot mapping as torch.int32 dtype,
-        # but vllm default is torch.int64 dtype.
-        vllm.v1.worker.gpu.model_runner.BlockTables = AscendBlockTables
-        logger.info_once("Wrapping BlockTables with AscendBlockTables.")
-        yield
-    finally:
-        pass
-
-
-@contextmanager
-def model_states_wrapper():
-    try:
-        # prepare_attn in AscendModelState is different from vllm,
-        # we need to override init_model_state.
-        vllm.v1.worker.gpu.model_runner.init_model_state = init_asecnd_model_state
-        logger.info_once("Wrapping init_model_state with init_asecnd_model_state.")
-        yield
-    finally:
-        pass