Skip to content

Conversation

@wenxindongwork
Copy link
Collaborator

@wenxindongwork wenxindongwork commented Nov 16, 2025

Description

Upstream PR (vllm-project/vllm#28245) broke our logprob handling, and this PR fixes this issue.
Instead of returning a list of floating points as log prob, upstream now expects a numpy array.

This PR also fixes a minor padding issue that was introduced by a recent tpu_inference PR.

Tests

Updated the e2e DP test.
https://buildkite.com/tpu-commons/tpu-inference-ci/builds/5646

Checklist

Before submitting this PR, please make sure:

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.
  • I have made or will make corresponding changes to any relevant documentation.

@github-actions
Copy link

Description

Start with a short description of what the PR does and how this is a change from
the past.

The rest of the description includes relevant details and context, examples:

  • why is this change being made,
  • the problem being solved and any relevant context,
  • why this is a good solution,
  • some information about the specific implementation,
  • shortcomings of the solution and possible future improvements.

If the change fixes a bug or a Github issue, please include a link, e.g.,:
FIXES: b/123456
FIXES: #123456

Tests

Please describe how you tested this change, and include any instructions and/or
commands to reproduce.

Checklist

Before submitting this PR, please make sure:

  • I have performed a self-review of my code.
  • I have necessary comments in my code, particularly in hard-to-understand areas.
  • I have made or will make corresponding changes to any relevant documentation.

@wenxindongwork wenxindongwork changed the title wip [Bug fix] Fix log probabilities handling Nov 16, 2025
Copy link
Collaborator

@vipannalla vipannalla left a comment

Choose a reason for hiding this comment

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

looks good

@wenxindongwork wenxindongwork merged commit 58c99a0 into main Nov 19, 2025
2 of 3 checks passed
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.

4 participants