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] Add TP and BNB quantization support to LlavaMultiModalProjector #10834

Merged
merged 6 commits into from
Dec 2, 2024
Merged

[Model] Add TP and BNB quantization support to LlavaMultiModalProjector #10834

merged 6 commits into from
Dec 2, 2024

Conversation

Isotr0py
Copy link
Collaborator

@Isotr0py Isotr0py commented Dec 2, 2024 •
edited by github-actions bot
Loading

I just realized that we still can't load unsloth/llava-1.5-7b-hf-bnb-4bit mentioned in #10813, because it has llava multimodal projector quantized as well. 😅

  • Add TP and quantization support to llava multimodal projector
  • Enable uninitialized weights tracking for BNB model loader

@github-actions GitHub Actions
Copy link

github-actions bot commented Dec 2, 2024

👋 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 2, 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.

Otherwise looks good

jeejeelee
jeejeelee approved these changes Dec 2, 2024
View reviewed changes
Copy link
Collaborator

@jeejeelee jeejeelee 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 your fixing.

@jeejeelee jeejeelee enabled auto-merge (squash) December 2, 2024 16:12
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Dec 2, 2024
@jeejeelee jeejeelee merged commit 4c05edb into vllm-project:main Dec 2, 2024
60 checks passed
@Isotr0py Isotr0py deleted the llava-bnb branch December 3, 2024 00:31
lixiaobai09 pushed a commit to lixiaobai09/vllm that referenced this pull request Dec 4, 2024
@Isotr0py @DarkLight1337
[Model] Add TP and BNB quantization support to LlavaMultiModalProject…
59dde9e 
…or (vllm-project#10834)

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

@jeejeelee jeejeelee jeejeelee approved these changes

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
@Isotr0py @jeejeelee @DarkLight1337