[Misc] unify variable for LLM instance #20996

andyxning · 2025-07-15T16:08:37Z

Essential Elements of an Effective PR Description Checklist

The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
The test plan, such as providing test command.
The test results, such as pasting the results comparison before and after, or e2e results
(Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.

Purpose

Unify LLM instance name to llm instead of model to make it more clear. Improve code readibility.

Test Plan

NA

Test Result

NA

(Optional) Documentation Update

github-actions · 2025-07-15T16:08:46Z

👋 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.

🚀

gemini-code-assist

Summary of Changes

Hello @andyxning, 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 focuses on improving code readability and consistency by standardizing the variable name used for vllm.LLM instances. The change involves renaming variables from model or vllm_model to llm throughout the codebase, including documentation, examples, and test files. This refactoring aims to make the code more intuitive and easier to understand for developers.

Highlights

Code Readability & Consistency: Standardized the variable name for vllm.LLM instances from model (or vllm_model) to llm across various parts of the codebase, including documentation, examples, and test files.

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.

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. ↩

gemini-code-assist

Code Review

This pull request consistently renames the LLM instance variable from model to llm across documentation, examples, and tests, which improves code clarity. I found one instance in docs/features/lora.md that needs to be updated to use the new llm variable.

andyxning · 2025-07-15T16:16:54Z

Code Review

This pull request consistently renames the LLM instance variable from model to llm across documentation, examples, and tests, which improves code clarity. I found one instance in docs/features/lora.md that needs to be updated to use the new llm variable.

Done.

DarkLight1337

Thanks for the clean up!

hmellor

Thanks for this PR, I agree this is a good clarification.

My initial review was not complete, I just wanted to request my changes before merging might have happened.

I have a few more comments.

examples/offline_inference/qwen3_reranker.py

examples/offline_inference/neuron_speculation.py

tests/samplers/test_no_bad_words.py

tests/models/language/pooling/mteb_utils.py

DarkLight1337 · 2025-07-17T13:38:57Z

@hmellor can you review again? Tests pass now

andyxning · 2025-07-17T13:43:13Z

@DarkLight1337 @hmellor All ci are finally green. PTAL.

hmellor

Thanks for making those changes, a couple of nits and an issue with a third party method which we shouldn't change

examples/offline_inference/qwen3_reranker.py

examples/offline_inference/neuron_speculation.py

tests/models/language/pooling/mteb_utils.py

andyxning · 2025-07-17T14:12:53Z

Thanks for making those changes, a couple of nits and an issue with a third party method which we shouldn't change

All done.

andyxning · 2025-07-18T07:10:34Z

Seems that tpu-v1-test failure is a flake. @DarkLight1337 @hmellor can you help confirm this?

DarkLight1337 · 2025-07-18T07:11:42Z

Yes it's a known issue. Retrying

andyxning · 2025-07-19T00:00:32Z

@DarkLight1337 @hmellor the ci is all green now. PTAL.

DarkLight1337 · 2025-07-19T05:17:57Z

Can you fix the merge conflicts?

mergify · 2025-07-19T06:34:57Z

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

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

Signed-off-by: Andy Xie <andy.xning@gmail.com>

andyxning · 2025-07-20T00:41:40Z

@DarkLight1337 @hmellor ci is green now. PTAL.

huydhn · 2025-07-22T05:15:43Z

@andyxning It looks like there are some left over tests that needs to be updated https://github.com/vllm-project/vllm/blob/main/tests/models/language/generation/test_gemma.py#L17-L26. I'm seeing that test failing after my recent rebase https://buildkite.com/vllm/ci/builds/24547#01982fc1-9f0c-4a14-9419-0ff0ea5c50f8/209-8333

AttributeError: 'VllmRunner' object has no attribute 'model'

andyxning requested review from hmellor, jeejeelee, comaniac, KuntaiDu, DarkLight1337 and ywang96 as code owners July 15, 2025 16:08

gemini-code-assist bot reviewed Jul 15, 2025

View reviewed changes

mergify bot added documentation Improvements or additions to documentation llama Related to Llama models qwen Related to Qwen models v1 labels Jul 15, 2025

gemini-code-assist bot reviewed Jul 15, 2025

View reviewed changes

andyxning force-pushed the unify_variable_for_LLM_instance branch from 508cac3 to d1978c3 Compare July 15, 2025 16:13

andyxning force-pushed the unify_variable_for_LLM_instance branch 2 times, most recently from d708b55 to cc16303 Compare July 16, 2025 02:06

DarkLight1337 approved these changes Jul 16, 2025

View reviewed changes

DarkLight1337 enabled auto-merge (squash) July 16, 2025 02:49

github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Jul 16, 2025

auto-merge was automatically disabled July 16, 2025 06:46
Head branch was pushed to by a user without write access

andyxning force-pushed the unify_variable_for_LLM_instance branch from cc16303 to 6bb5c9b Compare July 16, 2025 06:46

andyxning requested review from njhill, LiuXiaoxuanPKU, mgoin and robertgshaw2-redhat as code owners July 16, 2025 06:46

mergify bot added multi-modality Related to multi-modality (#4194) speculative-decoding labels Jul 16, 2025

andyxning force-pushed the unify_variable_for_LLM_instance branch from 6bb5c9b to e96128e Compare July 16, 2025 07:14

jeejeelee approved these changes Jul 16, 2025

View reviewed changes

andyxning force-pushed the unify_variable_for_LLM_instance branch from 83ace72 to cb4f32a Compare July 16, 2025 12:06

hmellor requested changes Jul 16, 2025

View reviewed changes

andyxning force-pushed the unify_variable_for_LLM_instance branch 5 times, most recently from 864f553 to 3c4a138 Compare July 17, 2025 07:48

hmellor requested changes Jul 17, 2025

View reviewed changes

examples/offline_inference/qwen3_reranker.py Outdated Show resolved Hide resolved

examples/offline_inference/neuron_speculation.py Outdated Show resolved Hide resolved

tests/models/language/pooling/mteb_utils.py Outdated Show resolved Hide resolved

andyxning force-pushed the unify_variable_for_LLM_instance branch from 3c4a138 to d83e6a6 Compare July 17, 2025 14:12

andyxning force-pushed the unify_variable_for_LLM_instance branch from d83e6a6 to 6b8c116 Compare July 18, 2025 02:21

mergify bot added the needs-rebase label Jul 19, 2025

andyxning force-pushed the unify_variable_for_LLM_instance branch from 6b8c116 to fc96fd5 Compare July 19, 2025 08:50

mergify bot removed the needs-rebase label Jul 19, 2025

andyxning force-pushed the unify_variable_for_LLM_instance branch 2 times, most recently from 9a1aae1 to a8921a2 Compare July 19, 2025 09:15

[Misc] unify variable for LLM instance

25c486b

Signed-off-by: Andy Xie <andy.xning@gmail.com>

andyxning force-pushed the unify_variable_for_LLM_instance branch from a8921a2 to 25c486b Compare July 19, 2025 13:10

hmellor approved these changes Jul 21, 2025

View reviewed changes

hmellor merged commit d978410 into vllm-project:main Jul 21, 2025
63 checks passed

andyxning deleted the unify_variable_for_LLM_instance branch July 21, 2025 13:02

Uh oh!

[Misc] unify variable for LLM instance #20996

[Misc] unify variable for LLM instance #20996

Conversation

andyxning commented Jul 15, 2025 • edited by github-actions bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Essential Elements of an Effective PR Description Checklist

Purpose

Test Plan

Test Result

(Optional) Documentation Update

Uh oh!

github-actions bot commented Jul 15, 2025

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Summary of Changes

Highlights

Footnotes

Uh oh!

gemini-code-assist bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

andyxning commented Jul 15, 2025

Code Review

Uh oh!

DarkLight1337 left a comment

Choose a reason for hiding this comment

Uh oh!

hmellor left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

DarkLight1337 commented Jul 17, 2025

Uh oh!

andyxning commented Jul 17, 2025

Uh oh!

hmellor left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

Uh oh!

Uh oh!

andyxning commented Jul 17, 2025

Uh oh!

andyxning commented Jul 18, 2025

Uh oh!

DarkLight1337 commented Jul 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

andyxning commented Jul 19, 2025

Uh oh!

DarkLight1337 commented Jul 19, 2025

Uh oh!

mergify bot commented Jul 19, 2025

Uh oh!

andyxning commented Jul 20, 2025

Uh oh!

Uh oh!

huydhn commented Jul 22, 2025

Uh oh!

Uh oh!

andyxning commented Jul 15, 2025 •

edited by github-actions bot

Loading

DarkLight1337 commented Jul 18, 2025 •

edited

Loading