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

ggml : add predefined list of CPU backend variants to build #10626

Merged
merged 4 commits into from
Dec 4, 2024
Merged

ggml : add predefined list of CPU backend variants to build #10626

merged 4 commits into from
Dec 4, 2024

Conversation

slaren
Copy link
Collaborator

@slaren slaren commented Dec 2, 2024 •
edited
Loading

GGML_CPU_ALL_VARIANTS enables the build of multiple variants of the CPU backend for different intel microarchitectures.

@github-actions github-actions bot added script Script related devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning labels Dec 2, 2024
@slaren slaren mentioned this pull request Dec 2, 2024
Merged
@slaren slaren force-pushed the sl/dl-backend-6 branch 2 times, most recently from e48c2eb to 726f515 Compare December 3, 2024 00:41
@slaren
Copy link
Collaborator Author

slaren commented Dec 4, 2024

This changes the working directory of the CPU docker images to /app (previously it was the root directory, which seems too crude, even for a container). It is possible that this may break scripts that use a relative path to load models. cc @ngxson

@ngxson
Copy link
Collaborator

ngxson commented Dec 4, 2024

Thanks for pinging. Yes it make much more sense to set workdir to /app in Dockerfile. HF endpoints should not be affected because model path is always an absolute path.

We should mention this change in the server changelog too, just in case.

@slaren slaren merged commit 59f4db1 into master Dec 4, 2024
44 checks passed
@slaren slaren deleted the sl/dl-backend-6 branch December 4, 2024 13:45
This was referenced Dec 4, 2024
Open
Closed
tinglou pushed a commit to tinglou/llama.cpp that referenced this pull request Dec 7, 2024
@slaren @tinglou
ggml : add predefined list of CPU backend variants to build (ggergano…
c34ec84 
…v#10626)

* ggml : add predefined list of CPU backend variants to build

* update CPU dockerfiles
arthw pushed a commit to arthw/llama.cpp that referenced this pull request Dec 20, 2024
@slaren @arthw
ggml : add predefined list of CPU backend variants to build (ggergano…
545316b 
…v#10626)

* ggml : add predefined list of CPU backend variants to build

* update CPU dockerfiles
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ggerganov ggerganov ggerganov approved these changes

Assignees
No one assigned
Labels
devops improvements to build systems and github actions ggml changes relating to the ggml tensor library for machine learning script Script related
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@slaren @ngxson @ggerganov