-
Notifications
You must be signed in to change notification settings - Fork 7
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
vllm 0.6.6 #26
vllm 0.6.6 #26
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.
lgtm
To clarify I feel the error of the status check is unrelated to this update. Looking at:
it seems that we might need bigger memory limit to build the image. I'm curious to see here if this can be covered from github or we need something from our side to handle those builds |
I have been thinking about this. I feel like I am going to exclude these set of Containerfiles from renovate.. This should be manually handles because the image sizes are > 5GB |
+1 at least until we find a proper way to cover this |
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.
lgtm. I agree with the comments about manually doing these ones since they are so large. We will need to add some logic to the workflow for skipping images if we'd like to avoid errors
Signed-off-by: Maysun J Faisal <maysunaneek@gmail.com>
c838ea8
to
057936d
Compare
rebased, green check, merging |
What does this PR do?:
Upload the vllm 0.6.6 Containerfile and requirements.txt changes as granite 3.1 require vllm 0.6.6.
This is a copy paste from https://github.com/maysunfaisal/llm-on-openshift/tree/vllm-0.6.6/llm-servers/vllm/gpu
Which issue(s) this PR fixes:
https://issues.redhat.com/browse/RHDHPAI-494
PR acceptance criteria:
Testing and documentation do not need to be complete in order for this PR to be approved. We just need to ensure tracking issues are opened and linked to this PR, if they are not in the PR scope due to various constraints.
Tested and Verified
Documentation (READMEs, Product Docs, Blogs, Education Modules, etc.)
How to test changes / Special notes to the reviewer:
https://quay.io/repository/redhat-ai-dev/vllm-openai-ubi9?tab=tags