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] Fix profiling for models with merged input processor #11370

Merged
merged 1 commit into from
Dec 20, 2024
Merged

[V1] Fix profiling for models with merged input processor #11370

merged 1 commit into from
Dec 20, 2024

Conversation

ywang96
Copy link
Member

@ywang96 ywang96 commented Dec 20, 2024 •
edited by github-actions bot
Loading

This PR adds support for models with merged input processor (instead of separate input_processor and input_mapper) such as llava and phi3v.

Tested with Pixtral-12B and microsoft/Phi-3.5-vision-instruct with --limit-mm-per-prompt image=1 and image=2.

fix
bd4bf38 
Signed-off-by: ywang96 <[email protected]>
@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.

🚀

DarkLight1337
DarkLight1337 approved these changes Dec 20, 2024
View reviewed changes
Copy link
Member

@DarkLight1337 DarkLight1337 left a comment

Choose a reason for hiding this comment

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

Thanks for fixing!

@DarkLight1337 DarkLight1337 enabled auto-merge (squash) December 20, 2024 10:10
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Dec 20, 2024
@ywang96 ywang96 disabled auto-merge December 20, 2024 10:18
@ywang96 ywang96 enabled auto-merge (squash) December 20, 2024 10:19
@ywang96 ywang96 merged commit 04139ad into vllm-project:main Dec 20, 2024
55 of 58 checks passed
lucas-tucker pushed a commit to lucas-tucker/vllm-lucas-tucker that referenced this pull request Dec 21, 2024
@ywang96
[V1] Fix profiling for models with merged input processor (vllm-proje…
db16ec0 
…ct#11370)

Signed-off-by: ywang96 <[email protected]>
Signed-off-by: lucast2021 <[email protected]>
BKitor pushed a commit to BKitor/vllm that referenced this pull request Dec 30, 2024
@ywang96 @BKitor
[V1] Fix profiling for models with merged input processor (vllm-proje…
597a72e 
…ct#11370)

Signed-off-by: ywang96 <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@DarkLight1337 DarkLight1337 DarkLight1337 approved these changes

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

@robertgshaw2-neuralmagic robertgshaw2-neuralmagic Awaiting requested review from robertgshaw2-neuralmagic robertgshaw2-neuralmagic is a code owner

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

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

@alexm-neuralmagic alexm-neuralmagic Awaiting requested review from alexm-neuralmagic alexm-neuralmagic is a code owner

@Isotr0py Isotr0py Awaiting requested review from Isotr0py

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.
2 participants
@ywang96 @DarkLight1337