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

Binary Update Jan 2024 #460

Closed

Conversation

martindevans
Copy link
Member

@martindevans
Copy link
Member Author

martindevans commented Jan 27, 2024

Testing:

  • Windows (CPU)
  • Windows (GPU)
  • Linux (CPU)
  • Linux (GPU)
  • MacOS (ARM)
  • MacOS (x86)

@Theoistic
Copy link

Ran the LLama.Examples using phi-2.Q5_K_M.gguf .. works perfectly on CPU.
not tested on GPU.
Machine: Windows 11 .. Intel i5-10400F .. 16GB Ram .. nvidia 1660 Super

@SignalRT
Copy link
Collaborator

@martindevans It works on osx-arm64 metal.

@jasoncouture
Copy link
Contributor

Tested CUDA on an A2000, works flawlessly.

@martindevans
Copy link
Member Author

Thanks for testing @jasoncouture. Was that test on Windows or Linux?

@martindevans
Copy link
Member Author

@jasoncouture has been doing some work on binaries (renaming them in #465 and adding CLBLAST in #468). I'll re-run the build step and update this PR based on those changes soon.

@jasoncouture
Copy link
Contributor

a1d6df129bcd3d42cda38c09217d8d4ec4ea3bdd

Sorry, @martindevans , that was windows.

@jasoncouture
Copy link
Contributor

I also tested linux CPU, that also works fine.

@martindevans
Copy link
Member Author

Closing this PR, various changes have been made to the binaries in some other PRs. I'll open a new one soon.

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

Successfully merging this pull request may close these issues.

4 participants