Qwen

/

Qwen3.5-27B

like 952

Follow

Qwen 80.5k

Where is the working whl file of vLLM?
thanks

https://drive.google.com/file/d/1u53vaR-HOicoGsPcsIQx4IGbwhDSIr1h/view?usp=sharing

Please use up the above link and let us know if it not works

Installing the vllm version in the link, there are still the following errors when using lm-eval：

  File "/home/wangshuo/wangshuo01/Qwen3.5/lm-evaluation-harness/lm_eval/models/vllm_causallms.py", line 18, in <module>
    from vllm import LLM, SamplingParams, TokensPrompt
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/__init__.py", line 70, in __getattr__
    module = import_module(module_name, __package__)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/importlib/__init__.py", line 90, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/entrypoints/llm.py", line 15, in <module>
    from vllm.beam_search import (
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/beam_search.py", line 9, in <module>
    from vllm.multimodal.inputs import MultiModalInputs, mm_inputs
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/multimodal/__init__.py", line 14, in <module>
    from .registry import MultiModalRegistry
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/multimodal/registry.py", line 13, in <module>
    from .cache import (
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/multimodal/cache.py", line 14, in <module>
    from vllm.distributed.device_communicators.shm_object_storage import (
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/distributed/__init__.py", line 4, in <module>
    from .communication_op import *
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/distributed/communication_op.py", line 9, in <module>
    from .parallel_state import get_tp_group
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/distributed/parallel_state.py", line 256, in <module>
    direct_register_custom_op(
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/utils/torch_utils.py", line 785, in direct_register_custom_op
    from vllm.platforms import current_platform
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/platforms/__init__.py", line 252, in __getattr__
    _current_platform = resolve_obj_by_qualname(platform_cls_qualname)()
                        ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/utils/import_utils.py", line 111, in resolve_obj_by_qualname
    module = importlib.import_module(module_name)
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/importlib/__init__.py", line 90, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/platforms/cuda.py", line 16, in <module>
    import vllm._C  # noqa
    ^^^^^^^^^^^^^^
ImportError: /home/wangshuo/wangshuo01/anaconda3/envs/EVAL3/lib/python3.12/site-packages/vllm/_C.abi3.so: undefined symbol: _ZN3c104cuda29c10_cuda_check_implementationEiPKcS2_ib

update your torch version

Name: torch
Version: 2.10.0
Summary: Tensors and Dynamic neural networks in Python with strong GPU acceleration
Home-page: https://pytorch.org
Author:
Author-email: PyTorch Team packages@pytorch.org
License: BSD-3-Clause
Requires: cuda-bindings, filelock, fsspec, jinja2, networkx, nvidia-cublas-cu12, nvidia-cuda-cupti-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-runtime-cu12, nvidia-cudnn-cu12, nvidia-cufft-cu12, nvidia-cufile-cu12, nvidia-curand-cu12, nvidia-cusolver-cu12, nvidia-cusparse-cu12, nvidia-cusparselt-cu12, nvidia-nccl-cu12, nvidia-nvjitlink-cu12, nvidia-nvshmem-cu12, nvidia-nvtx-cu12, setuptools, sympy, triton, typing-extensions
Required-by: compressed-tensors, flashinfer-python, torchaudio, torchvision, vllm, xgrammar