chatglm3 本地部署windows bitsandbytes不支持报错

先说结论：bitsandbytes不支持windows，目前很多教程写的使用bitsandbytes-windows也不可以用，下面说另外一个途径，使用

卸载：pip uninstall bitsandbytes
卸载：pip uninstall bitsandbytes-windows
安装： pip install https://github.com/jllllll/bitsandbytes-windows-webui/releases/download/wheels/bitsandbytes-0.41.1-py3-none-win_amd64.whl

初步怀疑是bitsandbytes-windows版本比较旧导致不能运行，换了上述内容就好用了；

报错信息：

 

RuntimeError:
        CUDA Setup failed despite GPU being available. Please run the following command to get more information:

        python -m bitsandbytes

        Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
        to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
        and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues
(venv) PS D:\gpt\ChatGLM3\composite_demo> python -m bitsandbytes
 

===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes

 and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
bin D:\gpt\ChatGLM3\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda123.dll
False
CUDA SETUP: CUDA runtime path found: D:\cuda\bin\cudart64_12.dll
CUDA SETUP: Highest compute capability among GPUs detected: 8.6
CUDA SETUP: Detected CUDA version 123
CUDA SETUP: Required library version not found: libbitsandbytes_cuda123.dll. Maybe you need to compile it from source?
CUDA SETUP: Defaulting to libbitsandbytes_cpu.dll...

================================================ERROR=====================================
CUDA SETUP: CUDA detection failed! Possible reasons:
1. CUDA driver not installed
2. CUDA not installed
3. You have multiple conflicting CUDA libraries
4. Required library not pre-compiled for this bitsandbytes release!
CUDA SETUP: If you compiled from source, try again with `make CUDA_VERSION=DETECTED_CUDA_VERSION` for example, `make CUDA_VERSION=113`.
CUDA SETUP: The CUDA version for the compile might depend on your conda install. Inspect CUDA version via `conda list | grep cuda`.
================================================================================

CUDA SETUP: Something unexpected happened. Please compile from source:
git clone git@github.com:TimDettmers/bitsandbytes.git
cd bitsandbytes
CUDA_VERSION=123
python setup.py install
CUDA SETUP: Setup Failed!
Traceback (most recent call last):
  File "D:\Python\Python310\lib\runpy.py", line 187, in _run_module_as_main
    mod_name, mod_spec, code = _get_module_details(mod_name, _Error)
  File "D:\Python\Python310\lib\runpy.py", line 146, in _get_module_details
    return _get_module_details(pkg_main_name, error)
  File "D:\Python\Python310\lib\runpy.py", line 110, in _get_module_details
    __import__(pkg_name)
  File "D:\gpt\ChatGLM3\venv\lib\site-packages\bitsandbytes\__init__.py", line 6, in <module>
    from . import cuda_setup, utils, research
  File "D:\gpt\ChatGLM3\venv\lib\site-packages\bitsandbytes\research\__init__.py", line 1, in <module>
    from . import nn
  File "D:\gpt\ChatGLM3\venv\lib\site-packages\bitsandbytes\research\nn\__init__.py", line 1, in <module>
    from .modules import LinearFP8Mixed, LinearFP8Global
  File "D:\gpt\ChatGLM3\venv\lib\site-packages\bitsandbytes\research\nn\modules.py", line 8, in <module>
    from bitsandbytes.optim import GlobalOptimManager
  File "D:\gpt\ChatGLM3\venv\lib\site-packages\bitsandbytes\optim\__init__.py", line 6, in <module>
    from bitsandbytes.cextension import COMPILED_WITH_CUDA
  File "D:\gpt\ChatGLM3\venv\lib\site-packages\bitsandbytes\cextension.py", line 20, in <module>
    raise RuntimeError('''
RuntimeError:
        CUDA Setup failed despite GPU being available. Please run the following command to get more information:

        python -m bitsandbytes

        Inspect the output of the command and see if you can locate CUDA libraries. You might need to add them
        to your LD_LIBRARY_PATH. If you suspect a bug, please take the information from python -m bitsandbytes
        and open an issue at: https://github.com/TimDettmers/bitsandbytes/issues
(venv) PS D:\gpt\ChatGLM3\composite_demo> python -m bitsandbytes           

===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please run

python -m bitsandbytes

 and submit this information together with your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
================================================================================
bin D:\gpt\ChatGLM3\venv\lib\site-packages\bitsandbytes\libbitsandbytes_cuda123.dll
False
CUDA SETUP: CUDA runtime path found: D:\cuda\bin\cudart64_12.dll
CUDA SETUP: Highest compute capability among GPUs detected: 8.6
CUDA SETUP: Detected CUDA version 123
CUDA SETUP: Required library version not found: libbitsandbytes_cuda123.dll. Maybe you need to compile it from source?
CUDA SETUP: Defaulting to libbitsandbytes_cpu.dll...

================================================ERROR=====================================
CUDA SETUP: CUDA detection failed! Possible reasons:
1. CUDA driver not installed
2. CUDA not installed
3. You have multiple conflicting CUDA libraries
4. Required library not pre-compiled for this bitsandbytes release!
CUDA SETUP: If you compiled from source, try again with `make CUDA_VERSION=DETECTED_CUDA_VERSION` for example, `make CUDA_VERSION=113`.
CUDA SETUP: The CUDA version for the compile might depend on your conda install. Inspect CUDA version via `conda list | grep cuda`.
================================================================================

CUDA SETUP: Something unexpected happened. Please compile from source:
git clone