Skip to content
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.

Sign up for GitHub

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

Jump to bottom

[V1][Bugfix] Skip hashing empty or None mm_data #11386

Merged
merged 1 commit into from
Dec 21, 2024
Merged

[V1][Bugfix] Skip hashing empty or None mm_data #11386

merged 1 commit into from
Dec 21, 2024

Conversation

WoosukKwon
Copy link
Collaborator

@WoosukKwon WoosukKwon commented Dec 20, 2024 •
edited by github-actions bot
Loading

prompt["multi_modal_data"] can be None or an empty dict. In such a case, vLLM currently errors at the hash_prompt_mm_data method. This PR fixes the bug.

I met this bug when running benchmark_throughput.py. Not sure why this was not detected in earlier PRs.

@github-actions GitHub Actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.
Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors. You can run other CI tests on top of those by going to your fastcheck build on Buildkite UI (linked in the PR checks section) and unblock them. If you do not have permission to unblock, ping simon-mo or khluu to add you in our Buildkite org.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can do one of these:

  • Add ready label to the PR
  • Enable auto-merge.

🚀

comaniac
comaniac approved these changes Dec 20, 2024
View reviewed changes
Copy link
Collaborator

@comaniac comaniac left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I guess it's because mm hasher was just turned on by default since 2 days ago.

@comaniac comaniac added the ready ONLY add when PR is ready to merge/full CI is needed label Dec 20, 2024
@comaniac comaniac enabled auto-merge (squash) December 20, 2024 23:40
ywang96
ywang96 approved these changes Dec 21, 2024
View reviewed changes
Copy link
Member

@ywang96 ywang96 left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Ah sorry I should have caught this, thanks for the fix!

@WoosukKwon WoosukKwon disabled auto-merge December 21, 2024 05:22
@WoosukKwon WoosukKwon merged commit dd2b563 into main Dec 21, 2024
59 of 67 checks passed
@WoosukKwon WoosukKwon deleted the v1-fix-hash branch December 21, 2024 05:22
BKitor pushed a commit to BKitor/vllm that referenced this pull request Dec 30, 2024
@WoosukKwon @BKitor
[V1][Bugfix] Skip hashing empty or None mm_data (vllm-project#11386)
27e1907 
Signed-off-by: Woosuk Kwon <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@ywang96 ywang96 ywang96 approved these changes

@comaniac comaniac comaniac approved these changes

@robertgshaw2-redhat robertgshaw2-redhat Awaiting requested review from robertgshaw2-redhat

@njhill njhill Awaiting requested review from njhill njhill is a code owner

@alexm-redhat alexm-redhat Awaiting requested review from alexm-redhat

Assignees
No one assigned
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@WoosukKwon @comaniac @ywang96