Closed yaldashbz closed 3 months ago
@yaldashbz Unit tests are done on python 3.10 + cuda 12.1 + pytorch 2.3.1 but should be compatible with anything torch 2.0.0 and up.
This is a very strange import error.
Did you get any strange errors or warnings during src compile pip install -v ./ --no-build-isolation
?
I had the same a few hours ago, I switched to yesterdays commit and it worked, seems like a new thing? (torch 2.1 cuda 11.8)
@FrederikHandberg You also experienced the exact libnvcrtc.so import error or slightly diff errors?
@CSY-ModelCloud We may have linking issue due to c++ compat with different python/cuda builds. We need a unit test env with cuda 11.8 paired with torch 2.1.0
exactly the same ```
Traceback (most recent call last):
File "/workspace/GPTQModel/fred_quant.py", line 2, in
Did you get any strange errors or warnings during src compile
pip install -v ./ --no-build-isolation
?
@Qubitium No, there were no strange things, just some missed packages in my env. But I'm not sure about the warnings during src compile.
@yaldashbz @FrederikHandberg There are actually two issues here. One we fixed. Second is bitblas compat with Cuda < 12.1.
To resolve both errors, please:
pip intall -v ./ --no-build-isolation
Or if you can't upgrade to cuda >= 12.1, then you need to:
pip intall -v ./ --no-build-isolation
@yaldashbz @FrederikHandberg v0.9.1 has been released with all our CI unit test passing. Please try it now and let us know. For env with cuda < 12.1 and with bitblas enabled in quantize_config, you will be prompted to manual src compile bitblas. But if you don't use bitblas kernel, then cuda < 12.1 should be fine (including the import errors) as long you have a gpu with cuda compute capability >= 6.0 support.
Closing this as resolved with 0.9.1 release. If the issue persist, feel free to re-open this issue.
Great! Thank you so much
Hi,
I'm trying to install GPTQModel from the source, but I'm facing this error during import. Could you please specify the versions which are working for you? My cuda version is 11.7 (via
nvcc --version
), python 3.10, and also:pytorch 2.0.0
,g++ 10.4.0
Thanks.