chore: upgrade vllm and transformers to the latest stable versions #1373
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
|
Got flagged by https://github.com/kaito-project/kaito/actions/runs/16813076971/job/47623004035?pr=1373 for using torch==2.7.1 due to GHSA-887c-mr87-cxwp, but I can't upgrade torch to 2.8.0 until vLLM also upgrades it. |
|
Hold until we release 0.6.0 |
Signed-off-by: Ernest Wong <chwong719@gmail.com>
Signed-off-by: Ernest Wong <chwong719@gmail.com>
|
Closing in favor of #1378 |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Reason for Change:
Upgrade vllm and transformers to the latest stable versions as a prerequisite to #1354.
"max_new_tokens": Noneinpresets/workspace/inference/text-generation/tests/test_inference_api.pygenerate_kwargssince max_new_tokens (default 200) takes precedence overmax_length, causing the test to generate more tokens than it supposed to.TODO after merging this PR:
TODO when upgrading vLLM to 0.11.0 (v0 engine will be completely removed)
Requirements
Issue Fixed:
Notes for Reviewers: