tloen / llama-int8

Quantized inference code for LLaMA models
GNU General Public License v3.0
1.05k stars 105 forks source link

Issue for bitsandbytes /// NameError: name 'cuda_setup' is not defined. Did you mean: 'CUDASetup'? #15

Closed kskim-phd closed 1 year ago

kskim-phd commented 1 year ago

Hi, thanks for sharing the wonderful code. But I got the following error so could you clarify how to solve it? I think it is better if you can clarify how to install bitsandbytes with version (e.g., https://pypi.org/project/bitsandbytes-cuda113/) in requirements.txt

Thank you!!

===========================================================

$MYPATH/python3.10/site-packages/bitsandbytes/cuda_setup/main.py", line 153, in is_cublasLt_compatible cuda_setup.add_log_entry("WARNING: Compute capability < 7.5 detected! Only slow 8-bit matmul is supported for your GPU!", is_warning=True)

NameError: name 'cuda_setup' is not defined. Did you mean: 'CUDASetup'?

tloen commented 1 year ago

See https://github.com/TimDettmers/bitsandbytes/pull/115/files