Skip to content

[Bugfix] Added embed_is_patch mask for fuyu model #15731

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

Merged
merged 1 commit into from
Mar 30, 2025

Conversation

kylehh
Copy link
Contributor

@kylehh kylehh commented Mar 28, 2025

Address issue #15144 for Fuyu model.
Added embed_is_patch mask in the format of torch.tensor(([True] * ncols + [False]) * nrows) ( Fuyu had newline for each row according to this)

Signed-off-by: Kyle Huang <[email protected]>
Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

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 either: Add ready label to the PR or enable auto-merge.

🚀

@DarkLight1337 DarkLight1337 added the ready ONLY add when PR is ready to merge/full CI is needed label Mar 30, 2025
@DarkLight1337 DarkLight1337 self-requested a review March 30, 2025 10:44
@vllm-bot vllm-bot merged commit bb103b2 into vllm-project:main Mar 30, 2025
44 of 49 checks passed
kylesayrs pushed a commit to neuralmagic/vllm that referenced this pull request Apr 2, 2025
Alex4210987 pushed a commit to LeiWang1999/vllm-bitblas that referenced this pull request Apr 5, 2025
lulmer pushed a commit to lulmer/vllm that referenced this pull request Apr 7, 2025
dtrifiro pushed a commit to dtrifiro/vllm that referenced this pull request Apr 7, 2025
SUMMARY:

upstream sync to `bb103b29bf3d26fa831458a8ca5af1bb820c4712` this is as
of 2025-03-30 Boston AM.

```bash
> git log
commit f44d253 (HEAD -> upstreamsync-20250330, origin/upstreamsync-20250330)
Merge: 2602d9d bb103b2
Author: andy-neuma <[email protected]>
Date:   Sun Mar 30 11:17:52 2025 -0400

    Merge remote-tracking branch 'upstream/main'

commit bb103b2 (upstream/main)
Author: kYLe <[email protected]>
Date:   Sun Mar 30 05:45:08 2025 -0500

    [Bugfix] Added `embed_is_patch` mask for fuyu model (vllm-project#15731)
    
    Signed-off-by: Kyle Huang <[email protected]>
...
```

created via "merge" not cherry-pick

TEST PLAN:
accept sync is green -
https://github.com/neuralmagic/nm-cicd/actions/runs/14225725956
nishith-fujitsu pushed a commit to nishith-fujitsu/vllm that referenced this pull request Apr 9, 2025
lk-chen pushed a commit to lk-chen/vllm that referenced this pull request Apr 29, 2025
shreyankg pushed a commit to shreyankg/vllm that referenced this pull request May 3, 2025
RichardoMrMu pushed a commit to RichardoMrMu/vllm that referenced this pull request May 12, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ready ONLY add when PR is ready to merge/full CI is needed
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants