Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

WHLs for cuda 11.7, 11.8, and 12.0 for future Releases #62

Closed
1 task done
Qubitium opened this issue Jun 26, 2024 · 5 comments
Closed
1 task done

WHLs for cuda 11.7, 11.8, and 12.0 for future Releases #62

Qubitium opened this issue Jun 26, 2024 · 5 comments
Assignees

Comments

@Qubitium
Copy link
Contributor

Qubitium commented Jun 26, 2024

Currently the bitblas whl support is too limited >= 12.1. I understand that building so many whl/python/torch combos is a headache but I think it may be worth it.

Include support for all Cuda supported by Torch >= 2.0.0 which need to add 11.7, 11.8, and 12.0 to the WHL builds.

Reasons:

  1. Lots of gpu-poor academics are locked to institution provided envs where drivers are often locked to cuda 11.7, 11.8 version.
  2. Compiling bitblas has large os lib dependency and a simple git clone + build is not possible even on ubuntu without adding ubuntu pkgs. But if env is not ubuntu the problem becomes quite a problem for users that has no clue about builds.
  3. Allow 3rd party to fully embed Bitblas without raising Torch/Cuda requirements. GPTQModel, for example, has integrated bitblas right now as a non-optional integration but need to add cuda checks for pkg compat and redirect users to src compile during runtime.

Tasks

@LeiWang1999
Copy link
Contributor

LeiWang1999 commented Jun 26, 2024

Hi @Qubitium , thank you for your attention. Indeed, bitblas is not officially released yet. We are currently working on performance-related optimizations, And there are still many items on our roadmap, such as CI/CD integration and support for VLLM. We are committed to completing these tasks and releasing more WHL packages in our official release.

We expect to complete these tasks in approximately two weeks.

@LeiWang1999 LeiWang1999 self-assigned this Jul 1, 2024
@tngh5004
Copy link

We're waiting for this action. Thank you for your efforts :)

@LeiWang1999
Copy link
Contributor

@tngh5004 , thanks for you attention, we will arrange this item as soon as possible.

@LeiWang1999
Copy link
Contributor

Thanks @tzj-fxz for the fix, we just released 0.0.1.dev13 on pypi, the dependency for cuda 12 has been removed, please feel free to test with:

pip install bitblas==0.0.1.dev13

@Qubitium , @tngh5004

@tngh5004
Copy link

Thanks @tzj-fxz for the fix, we just released 0.0.1.dev13 on pypi, the dependency for cuda 12 has been removed, please feel free to test with:

pip install bitblas==0.0.1.dev13

@Qubitium , @tngh5004

Thank you very much, I'm currently busy finalizing my thesis, but I'll experiment with it as soon as possible to see if it works.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
3 participants