[v0.33.0] Colab CPU installation gives list index out of range

[justheuristic]

In a blank colab CPU noteboook, you can install like this,

!pip install bitsandbytes==0.33.0
import bitsandbytes

but the import fails

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/main.py](https://localhost:8080/#) in get_compute_capability(cuda)
    106     if ccs is not None:
    107         # TODO: handle different compute capabilities; for now, take the max
--> 108         return ccs[-1]
    109     return None
    110 

IndexError: list index out of range

Here's the example colab notebook

Full traceback

Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/
Collecting bitsandbytes==0.33.0
  Downloading bitsandbytes-0.33.0-py3-none-any.whl (55.9 MB)
     |████████████████████████████████| 55.9 MB 214 kB/s 
Installing collected packages: bitsandbytes
Successfully installed bitsandbytes-0.33.0

===================================BUG REPORT===================================
Welcome to bitsandbytes. For bug reports, please submit your error trace to: https://github.com/TimDettmers/bitsandbytes/issues
For effortless bug reporting copy-paste your error into this form: https://docs.google.com/forms/d/e/1FAIpQLScPB8emS3Thkp66nvqwmjTEgxp8Y9ufuWTzFyr9kJ5AoI47dQ/viewform?usp=sf_link
================================================================================
CUDA_SETUP: WARNING! libcudart.so not found in any environmental path. Searching /usr/local/cuda/lib64...
CUDA SETUP: CUDA runtime path found: /usr/local/cuda/lib64/libcudart.so
CUDA exception! Error code: no CUDA-capable device is detected
CUDA exception! Error code: initialization error

/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:21: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/usr/local/nvidia/lib64'), PosixPath('/usr/local/nvidia/lib')}
  "WARNING: The following directories listed in your path were found to "
/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:99: UserWarning: /usr/local/nvidia/lib:/usr/local/nvidia/lib64 did not contain libcudart.so as expected! Searching further paths...
  f'{candidate_env_vars["LD_LIBRARY_PATH"]} did not contain '
/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:21: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('"172.28.0.3","jupyterArgs"'), PosixPath('true}'), PosixPath('6000,"kernelManagerProxyHost"'), PosixPath('["--ip=172.28.0.2"],"debugAdapterMultiplexerPath"'), PosixPath('{"kernelManagerProxyPort"'), PosixPath('"/usr/local/bin/dap_multiplexer","enableLsp"')}
  "WARNING: The following directories listed in your path were found to "
/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:21: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('/env/python')}
  "WARNING: The following directories listed in your path were found to "
/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/paths.py:21: UserWarning: WARNING: The following directories listed in your path were found to be non-existent: {PosixPath('module'), PosixPath('//ipykernel.pylab.backend_inline')}
  "WARNING: The following directories listed in your path were found to "

---------------------------------------------------------------------------

IndexError                                Traceback (most recent call last)

[<ipython-input-1-e9a23814d8e9>](https://localhost:8080/#) in <module>
      1 get_ipython().system('pip install bitsandbytes==0.33.0')
----> 2 import bitsandbytes

7 frames

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/__init__.py](https://localhost:8080/#) in <module>
      4 # LICENSE file in the root directory of this source tree.
      5 
----> 6 from .autograd._functions import (
      7     MatmulLtState,
      8     bmm_cublas,

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/autograd/_functions.py](https://localhost:8080/#) in <module>
      1 import operator
      2 import torch
----> 3 import bitsandbytes.functional as F
      4 
      5 from dataclasses import dataclass

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/functional.py](https://localhost:8080/#) in <module>
     11 from torch import Tensor
     12 
---> 13 from .cextension import COMPILED_WITH_CUDA, lib
     14 from functools import reduce  # Required in Python 3
     15 

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/cextension.py](https://localhost:8080/#) in <module>
     39 
     40 
---> 41 lib = CUDALibrary_Singleton.get_instance().lib
     42 try:
     43     lib.cadam32bit_g32

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/cextension.py](https://localhost:8080/#) in get_instance(cls)
     35         if cls._instance is None:
     36             cls._instance = cls.__new__(cls)
---> 37             cls._instance.initialize()
     38         return cls._instance
     39 

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/cextension.py](https://localhost:8080/#) in initialize(self)
     13 
     14     def initialize(self):
---> 15         binary_name = evaluate_cuda_setup()
     16         package_dir = Path(__file__).parent
     17         binary_path = package_dir / binary_name

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/main.py](https://localhost:8080/#) in evaluate_cuda_setup()
    130     print(f"CUDA SETUP: CUDA runtime path found: {cudart_path}")
    131     cuda = get_cuda_lib_handle()
--> 132     cc = get_compute_capability(cuda)
    133     print(f"CUDA SETUP: Highest compute capability among GPUs detected: {cc}")
    134     cuda_version_string = get_cuda_version(cuda, cudart_path)

[/usr/local/lib/python3.7/dist-packages/bitsandbytes/cuda_setup/main.py](https://localhost:8080/#) in get_compute_capability(cuda)
    106     if ccs is not None:
    107         # TODO: handle different compute capabilities; for now, take the max
--> 108         return ccs[-1]
    109     return None
    110 

IndexError: list index out of range

[t170815518]

I got the same error, and the reason is there is no available cuda device detected.