Thanks for sending an issue! Please fill in the following template to help quickly solve your problem.

Describe the current behavior / 问题描述 (Mandatory / 必填)

op-plugin和torch-npu的关系是什么，文档写的op-plugin是torch-npu的算子插件，但是最终编译出来的whl包安装后查看就是torch-npu一样，并且缺少torchair

Environment / 环境信息 (Mandatory / 必填)

Atlas I A2

Steps to reproduce the issue / 重现步骤 (Mandatory / 必填)

执行编译：
bash ci/build.sh --python=3.11 --pytorch=v2.7.1-7.2.0
执行安装：
pip3 install torch_npu-2.7.1.post1-cp311-cp311-linux_aarch64.whl

Describe the expected behavior / 预期结果 (Mandatory / 必填)

期望torch-npu相关功能ok

Related log / screenshot / 日志 / 截图 (Mandatory / 必填)

Traceback (most recent call last):
File "/usr/local/python3.11.13/bin/vllm", line 3, in
from vllm.entrypoints.cli.main import main
File "/vllm-workspace/vllm/vllm/entrypoints/cli/init.py", line 3, in
from vllm.entrypoints.cli.benchmark.latency import BenchmarkLatencySubcommand
File "/vllm-workspace/vllm/vllm/entrypoints/cli/benchmark/latency.py", line 5, in
from vllm.benchmarks.latency import add_cli_args, main
File "/vllm-workspace/vllm/vllm/benchmarks/latency.py", line 18, in
from vllm.engine.arg_utils import EngineArgs
File "/vllm-workspace/vllm/vllm/engine/arg_utils.py", line 24, in
from vllm.config import (BlockSize, CacheConfig, CacheDType, CompilationConfig,
File "/vllm-workspace/vllm/vllm/config/init.py", line 34, in
from vllm.config.lora import LoRAConfig
File "/vllm-workspace/vllm/vllm/config/lora.py", line 14, in
from vllm.platforms import current_platform
File "/vllm-workspace/vllm/vllm/platforms/init.py", line 248, in getattr
_current_platform = resolve_obj_by_qualname(
^^^^^^^^^^^^^^^^^^^^^^^^
File "/vllm-workspace/vllm/vllm/utils/init.py", line 2680, in resolve_obj_by_qualname
module = importlib.import_module(module_name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/usr/local/python3.11.13/lib/python3.11/importlib/init.py", line 126, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/vllm-workspace/vllm-ascend/vllm_ascend/platform.py", line 32, in
from vllm_ascend.torchair.utils import (check_torchair_cache_exist,
File "/vllm-workspace/vllm-ascend/vllm_ascend/torchair/utils.py", line 9, in
from torchair.scope import super_kernel as _super_kernel

Special notes for this issue/备注 (Optional / 选填)