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

[Model] Refactor Qwen2-VL to use merged multimodal processor #11258

Merged
merged 14 commits into from
Dec 19, 2024
Merged

[Model] Refactor Qwen2-VL to use merged multimodal processor #11258

merged 14 commits into from
Dec 19, 2024

Conversation

Isotr0py
Copy link
Collaborator

@Isotr0py Isotr0py commented Dec 17, 2024 •
edited by github-actions bot
Loading

No description provided.

@Isotr0py
init
c094e25 
Signed-off-by: Isotr0py <[email protected]>
@Isotr0py
clean up
5c4bcce 
Signed-off-by: Isotr0py <[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.

🚀

This was referenced Dec 17, 2024
Open
Open
@DarkLight1337 DarkLight1337 self-assigned this Dec 17, 2024
@Isotr0py Isotr0py marked this pull request as ready for review December 18, 2024 08:55
@Isotr0py Isotr0py requested a review from ywang96 as a code owner December 18, 2024 08:55
DarkLight1337
DarkLight1337 approved these changes Dec 19, 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.

LGTM, thanks for the refactor!

@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label Dec 19, 2024
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) December 19, 2024 02:56
@DarkLight1337
Copy link
Member

The failure in embeddings input test should be fixed by the Qwen2-Audio PR.

@Isotr0py Isotr0py disabled auto-merge December 19, 2024 07:37
@Isotr0py Isotr0py enabled auto-merge (squash) December 19, 2024 09:32
@DarkLight1337
Fix incorrect max tokens
cabc8fa 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix type error
ce13cff 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Fix incorrect dummy data
9bd81af 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337 DarkLight1337 enabled auto-merge (squash) December 19, 2024 10:33
@DarkLight1337
Fix multi input
505c07c 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337
Oops
3f0ce3e 
Signed-off-by: DarkLight1337 <[email protected]>
@DarkLight1337 DarkLight1337 merged commit e24113a into vllm-project:main Dec 19, 2024
53 checks passed
@Isotr0py Isotr0py deleted the refactor-qwen2vl branch December 19, 2024 16:31
@B-201
Copy link
Contributor

B-201 commented Dec 23, 2024

Hi, I encountered some issues while using this PR:
image

Is this caused by the version of hf? I'm using 4.46.0.

@DarkLight1337
Copy link
Member

Hi, I encountered some issues while using this PR:
image

Is this caused by the version of hf? I'm using 4.46.0.

I think so; try updating to v4.47.

@B-201
Copy link
Contributor

B-201 commented Dec 23, 2024

Hi, I encountered some issues while using this PR:
image
Is this caused by the version of hf? I'm using 4.46.0.

I think so; try updating to v4.47.

It works, thank you!

DarkLight1337 added a commit to DarkLight1337/vllm that referenced this pull request Dec 25, 2024
@DarkLight1337
Fix incorrect max image tokens (Updated in vllm-project#11258)
93bba0a 
Signed-off-by: DarkLight1337 <[email protected]>
BKitor pushed a commit to BKitor/vllm that referenced this pull request Dec 30, 2024
@Isotr0py @DarkLight1337 @BKitor
[Model] Refactor Qwen2-VL to use merged multimodal processor (vllm-pr…
9c86373 
…oject#11258)

Signed-off-by: Isotr0py <[email protected]>
Signed-off-by: DarkLight1337 <[email protected]>
Co-authored-by: Cyrus Leung <[email protected]>
Co-authored-by: DarkLight1337 <[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

@ywang96 ywang96 Awaiting requested review from ywang96 ywang96 is a code owner

Assignees

@DarkLight1337 DarkLight1337

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
@Isotr0py @DarkLight1337 @B-201