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.

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

[V1][VLM] Enable proper chunked prefill for multimodal models #9950

Closed
wants to merge 17 commits into from

Conversation

ywang96
Copy link
Member

@ywang96 ywang96 commented Nov 2, 2024

This PR will be merged after #9871 which supports chunked prefill of LMMs natively in V1.

The goals of this PR are:
- Refactor model interface to be compatible with both V0 and V1 engine implementation (calling encoder at model executable vs calling encoder at model runner)
- Add placeholder ranges to input processor of all LMMs so that placeholder locations can be precisely tracked for chunked prefill in V1 (and potentially prefix caching)

See comment

Signed-off-by: Roger Wang <[email protected]>
Copy link

github-actions bot commented Nov 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.

🚀

Signed-off-by: Roger Wang <[email protected]>
@ywang96 ywang96 changed the title [1/N][Core][VLM] Enable proper chunked prefill for multimodal models [V1][VLM] Enable proper chunked prefill for multimodal models Nov 6, 2024
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
@ywang96
Copy link
Member Author

ywang96 commented Nov 7, 2024

The description has been updated to reflect the repurpose of this PR.

Copy link

mergify bot commented Nov 9, 2024

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @ywang96.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Nov 9, 2024
@mergify mergify bot removed the needs-rebase label Nov 9, 2024
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Signed-off-by: Roger Wang <[email protected]>
Copy link

mergify bot commented Nov 13, 2024

This pull request has merge conflicts that must be resolved before it can be
merged. Please rebase the PR, @ywang96.

https://docs.github.com/en/pull-requests/collaborating-with-pull-requests/working-with-forks/syncing-a-fork

@mergify mergify bot added the needs-rebase label Nov 13, 2024
@mergify mergify bot removed the needs-rebase label Nov 13, 2024
Signed-off-by: Roger Wang <[email protected]>
@ywang96 ywang96 closed this Nov 27, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants