[CI] Pin cu128 nightly wheel for blend ci test #2987
Merged
ApostaC merged 3 commits intoLMCache:devfrom Apr 9, 2026
Merged
Conversation
Contributor
There was a problem hiding this comment.
Code Review
This pull request updates the setup-blend-env.sh script to pin the vLLM installation to a specific version rather than using nightly builds. It removes the complex logic for resolving nightly wheel URLs and introduces a VLLM_VERSION variable. However, the default VLLM_VERSION of 0.18.0 is likely invalid, as current stable releases are in the 0.7.x range, which could cause CI installation failures. Additionally, the updated pip install command for vLLM is missing the [runai,tensorizer,flashinfer] extras, which are necessary for the 'blend' tests.
Signed-off-by: deng451e <838677410@qq.com>
Signed-off-by: deng451e <838677410@qq.com>
Signed-off-by: deng451e <838677410@qq.com>
sammshen
approved these changes
Apr 9, 2026
Oasis-Git
pushed a commit
to Oasis-Git/LMCache
that referenced
this pull request
Apr 13, 2026
* pin version * pin cu128 wheel Signed-off-by: deng451e <838677410@qq.com>
ftian1
pushed a commit
to ftian1/LMCache
that referenced
this pull request
Apr 20, 2026
* pin version * pin cu128 wheel Signed-off-by: deng451e <838677410@qq.com>
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this PR does / why we need it:
Special notes for your reviewers:
If applicable:
Note
Medium Risk
Changes CI dependency resolution (nightly wheel sources + pinned CUDA torch), which may introduce new incompatibilities or flakiness in GPU runs; functional code paths are otherwise unaffected.
Overview
Switches Blend CI environment setup to install
vllmfrom the nightly cu128 wheel index and pinstorch==2.10.0+cu128, including aFLASHINFER_DISABLE_VERSION_CHECKworkaround and extra version diagnostics.Updates the Blend integration test runner to split logs per process (blend server/prefillers/decoders/proxy) and bundle all
/tmp/build_${BUILD_ID}_*.logfiles into the final artifact for easier debugging.Reviewed by Cursor Bugbot for commit fbead04. Bugbot is set up for automated code reviews on this repo. Configure here.