The output of `python collect_env.py`
(vllm3) [root@hygpu-002 envs]# python vllm/collect_env.py
/mnt/qy-test/envs/vllm/vllm/__init__.py:5: RuntimeWarning: Failed to read commit hash:
No module named 'vllm._version'
from .version import __version__, __version_tuple__ # isort:skip
INFO 03-27 10:36:47 [__init__.py:239] Automatically detected platform cuda.
Traceback (most recent call last):
File "/mnt/qy-test/envs/vllm/collect_env.py", line 17, in <module>
from vllm.envs import environment_variables
File "/mnt/qy-test/envs/vllm/vllm/__init__.py", line 11, in <module>
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
File "/mnt/qy-test/envs/vllm/vllm/engine/arg_utils.py", line 22, in <module>
from vllm.executor.executor_base import ExecutorBase
File "/mnt/qy-test/envs/vllm/vllm/executor/executor_base.py", line 16, in <module>
from vllm.model_executor.layers.sampler import SamplerOutput
File "/mnt/qy-test/envs/vllm/vllm/model_executor/layers/sampler.py", line 23, in <module>
from vllm.spec_decode.metrics import SpecDecodeWorkerMetrics
File "/mnt/qy-test/envs/vllm/vllm/spec_decode/metrics.py", line 9, in <module>
from vllm.model_executor.layers.spec_decode_base_sampler import (
File "/mnt/qy-test/envs/vllm/vllm/model_executor/layers/spec_decode_base_sampler.py", line 10, in <module>
from vllm.platforms import current_platform
File "/mnt/qy-test/envs/vllm/vllm/platforms/__init__.py", line 271, in __getattr__
_current_platform = resolve_obj_by_qualname(
^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/qy-test/envs/vllm/vllm/utils.py", line 1910, in resolve_obj_by_qualname
module = importlib.import_module(module_name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/importlib/__init__.py", line 90, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/qy-test/envs/vllm/vllm/platforms/cuda.py", line 15, in <module>
import vllm._C # noqa
^^^^^^^^^^^^^^
ModuleNotFoundError: No module named 'vllm._C'
</details>
### š Describe the bug
When I tried to run the collect_env.py file, I encountered the error:
ModuleNotFoundError: No module named 'vllm._C'
Additionally, I downloaded a .whl file to install the environment using the command:
pip install vllm-0.8.3.dev166%2Bg29930428e.cu128-cp312-cp312-linux_x86_64.whl
The installation completed without any errors, but when I attempted to deploy a local model, the following command:
python -m vllm.entrypoints.openai.api_server --model /mnt/qy-test/pvc-cd37befa-daf6-42c1-80f5-70b54cbbf302/qwen-QwQ --trust-remote-code --host 0.0.0.0 --port 8080
resulted in an errorļ¼
INFO 03-27 10:47:18 [__init__.py:239] Automatically detected platform cuda.
Traceback (most recent call last):
File "<frozen runpy>", line 189, in _run_module_as_main
File "<frozen runpy>", line 112, in _get_module_details
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/__init__.py", line 11, in <module>
from vllm.engine.arg_utils import AsyncEngineArgs, EngineArgs
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/engine/arg_utils.py", line 22, in <module>
from vllm.executor.executor_base import ExecutorBase
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/executor/executor_base.py", line 16, in <module>
from vllm.model_executor.layers.sampler import SamplerOutput
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/model_executor/layers/sampler.py", line 23, in <module>
from vllm.spec_decode.metrics import SpecDecodeWorkerMetrics
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/spec_decode/metrics.py", line 9, in <module>
from vllm.model_executor.layers.spec_decode_base_sampler import (
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/model_executor/layers/spec_decode_base_sampler.py", line 10, in <module>
from vllm.platforms import current_platform
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/platforms/__init__.py", line 271, in __getattr__
_current_platform = resolve_obj_by_qualname(
^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/utils.py", line 1905, in resolve_obj_by_qualname
module = importlib.import_module(module_name)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/importlib/__init__.py", line 90, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/platforms/cuda.py", line 15, in <module>
import vllm._C # noqa
^^^^^^^^^^^^^^
ImportError: /lib64/libc.so.6: version `GLIBC_2.32' not found (required by /mnt/qy-test/envs/conda/envs/vllm3/lib/python3.12/site-packages/vllm/_C.abi3.so)
### Before submitting a new issue...
- [x] Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the [documentation page](https://docs.vllm.ai/en/latest/), which can answer lots of frequently asked questions.
#16174 logs the error in the same process as the process which raises the error, so we donāt need the error to be serializable.