[MISC] Clean up useless env USE_OPTIMIZED_MODEL

[wangxiyuan]

Clean up uesless env USE_OPTIMIZED_MODEL

• vLLM version: v0.15.0
• vLLM main: vllm-project/vllm@d7e17aa

[github-actions]

👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:‌‌

• A PR should do only one thing, smaller PRs enable faster reviews.
• Every PR should include unit tests and end-to-end tests ‌to ensure it works and is not broken by other future PRs.
• Write the commit message by fulfilling the PR description to help reviewer and future developers understand.

If CI fails, you can run linting and testing checks locally according Contributing and Testing.

[gemini-code-assist]

Summary of Changes

Hello @wangxiyuan, 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 code cleanup by removing the USE_OPTIMIZED_MODEL environment variable, which was identified as obsolete. This change simplifies the environment configuration and eliminates unnecessary conditional logic from the multi-modal encoder attention mechanism, contributing to a cleaner and more maintainable system.

Highlights

• Environment Variable Removal: The USE_OPTIMIZED_MODEL environment variable, along with its associated comments, has been completely removed from vllm_ascend/envs.py.
• Dependency Cleanup: The mm_encoder_attention.py module no longer imports vllm_ascend.envs and its enable_pad logic has been updated to remove the dependency on the USE_OPTIMIZED_MODEL flag.
• Code Standardization: A minor cleanup was performed in vllm_ascend/envs.py by standardizing the environment variable access for HCCL_SO_PATH from os.environ.get to os.getenv.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• vllm_ascend/envs.py
  • Removed the USE_OPTIMIZED_MODEL environment variable definition and its descriptive comments.
  • Standardized the retrieval of HCCL_SO_PATH to use os.getenv instead of os.environ.get.
• vllm_ascend/ops/mm_encoder_attention.py
  • Removed the unused import statement for vllm_ascend.envs.
  • Modified the enable_pad condition within the forward_oot function to no longer reference the removed USE_OPTIMIZED_MODEL flag.

Activity

• No specific activity (comments, reviews, or progress updates) has been recorded for this pull request yet.

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 by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

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 pull request 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 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. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

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. ↩

[gemini-code-assist]

Code Review

This pull request aims to clean up a supposedly useless environment variable, USE_OPTIMIZED_MODEL. It removes the variable definition and its usage in the codebase. While the cleanup is straightforward, I have a significant concern about removing the ability to disable the associated optimization, as the original comments suggest it might be necessary for certain use cases like RLHF training. This could be a breaking change for some users. A minor consistency improvement is also included.

I am having trouble creating individual review comments. Click here to see my feedback.

vllm_ascend/envs.py (69-72)

The removal of the USE_OPTIMIZED_MODEL environment variable could introduce a breaking change. The previous implementation allowed disabling an optimization that was noted as potentially unsuitable for use cases like RLHF training. By removing this flag, this control is lost. If this optimization is not universally safe, removing the flag could be a regression. Please either restore this flag or provide a clear justification in the pull request description for why it is no longer necessary.