-
Notifications
You must be signed in to change notification settings - Fork 46
fix: handle multi meta backends and cpu fallback for cuda #618
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
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This PR introduces support for handling multiple meta backends and updates various configuration files and documentation. The changes appear to be focused on improving backend flexibility and updating infrastructure references.
- Updates documentation to mention Podman as an alternative to Docker and switches from distroless to chiseled images
- Modifies test configuration files to use a different syntax reference
- Implements dual backend installation for CUDA environments with CPU fallback support
Reviewed Changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 2 comments.
Show a summary per file
File | Description |
---|---|
website/docs/intro.md | Updates feature descriptions to include Podman support and chiseled image reference |
test/aikitfile-llama.yaml | Changes syntax reference from aikit:test to sozercan/aikit:test |
test/aikitfile-llama-cuda.yaml | Changes syntax reference from aikit:test to sozercan/aikit:test |
pkg/aikit2llb/inference/convert.go | Updates base image and LocalAI version/endpoint configuration |
pkg/aikit2llb/inference/backend.go | Adds logic to install CPU fallback backend for CUDA llama-cpp configurations |
README.md | Updates feature descriptions to include Podman support and chiseled image reference |
Dockerfile.base | Adds grep_bins to the chisel cut dependencies |
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
8a39718
to
d1df53e
Compare
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
6fd0f66
to
9a01dd7
Compare
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
Signed-off-by: Sertac Ozercan <sozercan@gmail.com>
What this PR does / why we need it:
Which issue(s) this PR fixes (optional, using
fixes #<issue number>(, fixes #<issue_number>, ...)
format, will close the issue(s) when the PR gets merged):Fixes #
Special notes for your reviewer: