Skip to content

[V0 Deprecation] Remove Prompt Adapters #20588

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

Open
wants to merge 3 commits into
base: main
Choose a base branch
from

Conversation

mgoin
Copy link
Member

@mgoin mgoin commented Jul 7, 2025

Purpose

This PR is part of V0 deprecation. We will remove all support and usage of prompt adapters from the vLLM package, testing, and documentation.

This means vllm/prompt_adapters/ is completely removed.

Test Plan

Rely on green CI since this touches many entrypoints and existing tests

Test Result

Signed-off-by: mgoin <mgoin64@gmail.com>
Copy link

github-actions bot commented Jul 7, 2025

👋 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.

🚀

@mergify mergify bot added documentation Improvements or additions to documentation frontend speculative-decoding v1 tpu Related to Google TPUs labels Jul 7, 2025
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Summary of Changes

Hello @mgoin, I'm Gemini Code Assist1! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request is a significant cleanup effort focused on deprecating and removing the 'Prompt Adapters' feature from the vLLM project. It streamlines the codebase by eliminating unused components, simplifies the configuration and API, and updates the testing infrastructure to reflect the current state of supported functionalities.

Highlights

  • Feature Deprecation: The pull request completely removes all support and usage of 'Prompt Adapters' from the vLLM package, including its core functionalities, testing, and documentation. This is part of a V0 deprecation effort.
  • Codebase Cleanup: The vllm/prompt_adapters/ directory and all related files, configurations, and references across the codebase have been deleted or updated to reflect the removal of this feature. This includes configuration classes, CLI arguments, API endpoints, and internal engine logic.
  • Test Suite Updates: Existing test cases that previously included prompt adapter functionality have been modified to remove any mention or testing of prompt adapters, ensuring the test suite remains relevant and passes with the deprecated feature removed.
  • API and Documentation Alignment: The public API documentation and internal configuration structures have been updated to remove PromptAdapterConfig and any related parameters, providing a cleaner and more accurate representation of the supported features.
Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point in your pull request via creating an issue comment (i.e. comment on the pull request page) using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands.

Feature Command Description
Code Review /gemini review Performs a code review for the current pull request in its current state.
Pull Request Summary /gemini summary Provides a summary of the current pull request in its current state.
Comment @gemini-code-assist Responds in comments when explicitly tagged, both in issue comments and review comments.
Help /gemini help Displays a list of available commands.

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist is currently in preview and may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments to provide feedback.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

Footnotes

  1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution.

@mgoin mgoin moved this to In Progress in V0 Deprecation Jul 7, 2025
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

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

Code Review

This pull request effectively removes the deprecated V0 Prompt Adapters feature. The changes are extensive, touching documentation, configuration, tests, and core engine logic across numerous files. The removal appears to be thorough and consistent, with all related code paths, configurations, and tests being correctly updated or deleted. I've reviewed the changes and found no issues. This is a great cleanup effort that improves the maintainability of the codebase.

mgoin added 2 commits July 7, 2025 18:45
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
@WoosukKwon WoosukKwon added the ready ONLY add when PR is ready to merge/full CI is needed label Jul 8, 2025
Copy link
Member

@hmellor hmellor left a comment

Choose a reason for hiding this comment

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

LGTM

@@ -52,11 +51,9 @@ async def _embedding_score(
texts_1: list[str],
texts_2: list[str],
request: Union[RerankRequest, ScoreRequest],
request_id=str,
request_id: str,
Copy link
Member

Choose a reason for hiding this comment

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

That was a very sneaky bug!

Copy link

mergify bot commented Jul 8, 2025

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

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

@WoosukKwon
Copy link
Collaborator

@mgoin Is there any blocker to this PR? Otherwise, I hope we can merge this soon!

@mgoin
Copy link
Member Author

mgoin commented Jul 10, 2025

I have a lot more high priority work right now. Maybe will get back over the weekend or next week

@WoosukKwon
Copy link
Collaborator

@mgoin sgtm. No pressure!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation frontend needs-rebase ready ONLY add when PR is ready to merge/full CI is needed speculative-decoding tpu Related to Google TPUs v1
Projects
Status: In Progress
Development

Successfully merging this pull request may close these issues.

6 participants