gha: do not use cuda torch improvements #67
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Author
|
Based on #57 |
dtrifiro
commented
Aug 28, 2025
| uv pip install \ | ||
| --force-reinstall \ | ||
| --no-cache-dir \ | ||
| --no-binary "vllm" \ |
Author
There was a problem hiding this comment.
I guess this works well in CI scenarios, but we need a way to make sure that when users install the plugin from pypi, they have
VLLM_TARGET_DEVICE=cpu
UV_EXTRA_INDEX_URL=https://download.pytorch.org/whl/cpu
UV_INDEX_STRATEGY="unsafe-best-match"`
set and use --no-binary=vllm.
Perhaps we can provide a vllm cpu wheel that you can install via an extra index url that could simplify this process. More thought needed.
dtrifiro
force-pushed
the
do-not-use-cuda-torch-improvements
branch
from
1f513bc to
4396b22
Compare
rebel-jonghewk
approved these changes
Sep 23, 2025
Collaborator
rebel-jonghewk
left a comment
rebel-jonghewk
left a comment
There was a problem hiding this comment.
https://github.com/rebellions-sw/vllm-rbln/actions/runs/17910125135
LGTM. works well with our current ci.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
--no-binary=vllmto force a vllm rebuild