fix(vllm): try PyPI before GitHub for cu130 wheel installs#5
Merged
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Fix the CUDA 13 wheel install path in install_vllm.sh to try PyPI first and fall back to GitHub release wheels only when needed.
Problem
The CUDA 13 wheel-install path assumed that usable cu130 wheels would always come from GitHub release assets. That worked for older vLLM packaging, but it breaks for newer releases like v0.20.0, where CUDA 13 became the default PyPI wheel path.
As a result, Docker builds could fail by trying to download a GitHub wheel URL that does not exist.
Solution
Update container/deps/vllm/install_vllm.sh so that wheel installs tries PyPI first and then falls back to the GitHub release wheel only if the PyPI install fails