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.

Sign up for GitHub

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

Jump to bottom

Log llama.cpp commit hash when installing using --verbose #256

Open
gjmulder opened this issue May 21, 2023 · 1 comment
Open

Log llama.cpp commit hash when installing using --verbose #256

gjmulder opened this issue May 21, 2023 · 1 comment
Labels
documentation Improvements or additions to documentation enhancement New feature or request llama.cpp Problem with llama.cpp shared lib

Comments

@gjmulder
Copy link
Contributor

gjmulder commented May 21, 2023 •
edited
Loading

See #223 (comment)

A bug looks to be with libllama, but in order to log the bug with llama.cpp we ideally need to specify which commit hash of libllama the bug occurs in for the upstream devs to isolate the regression.
@gjmulder gjmulder added documentation Improvements or additions to documentation enhancement New feature or request llama.cpp Problem with llama.cpp shared lib labels May 21, 2023
@abetlen
Copy link
Owner

abetlen commented May 21, 2023

Makes sense, there should be a build-info.h file generated inside the vendor/llama.cpp folder so we should be able to use that, I'll write a get_version function in the llama_cpp.py file to pull that in.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
documentation Improvements or additions to documentation enhancement New feature or request llama.cpp Problem with llama.cpp shared lib
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@abetlen @gjmulder