Skip to content

Update CODEOWNERS for multimodal_gen#14995

Merged
mickqian merged 4 commits intosgl-project:mainfrom
mickqian:sgl-diffusion-codeowners
Dec 12, 2025
Merged

Update CODEOWNERS for multimodal_gen#14995
mickqian merged 4 commits intosgl-project:mainfrom
mickqian:sgl-diffusion-codeowners

Conversation

@mickqian
Copy link
Copy Markdown
Collaborator

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello @mickqian, 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 maintenance and minor quality-of-life improvements within the multimodal_gen module. Key changes include updating code ownership for better review processes, refining logging for clearer console output, and cleaning up redundant or unused code. Additionally, it adjusts performance test retry logic and baselines to enhance testing stability and accuracy, ensuring the module remains robust and maintainable without introducing new features.

Highlights

  • CODEOWNERS Update: Added @RubiaCx as a code owner for the /python/sglang/multimodal_gen path, ensuring proper review assignments for changes in this module.
  • Logging Enhancements: Improved console output readability for uvicorn servers by replacing log_config=None with use_colors=True. Several verbose logger.info calls were removed, and print statements in perf_logger.py were standardized to logger.info and logger.error.
  • Code Refactoring and Cleanup: Removed unused device-related imports and variables in layernorm.py. The load_native function in component_loader.py was refactored from a standalone function into a method of the ComponentLoader class. Unused methods (_sigma_to_t, __len__) and related calculations were removed from scheduling_flow_unipc_multistep.py.
  • Performance Test Adjustments: Increased the max_retries for pytest from 2 to 4 in run_suite.py to improve test robustness. Performance baselines in perf_baselines.json were updated, specifically increasing ImageVAEEncodingStage from 350.0 to 400.0 ms and expected_e2e_ms from 198187.89 to 220000 ms.
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.

@mickqian mickqian force-pushed the sgl-diffusion-codeowners branch from d252b81 to 992cc44 Compare December 12, 2025 14:04
Copy link
Copy Markdown
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 includes several code cleanup, refactoring, and minor adjustment changes. It updates the .github/CODEOWNERS file to add a new owner for the multimodal_gen path. Logging configurations for uvicorn.run calls in http_server.py and launch_server.py were modified to enable colored output. In layernorm.py, unused platform-specific checks and imports were removed. The component_loader.py file saw refactoring where a standalone load_native function was inlined into a class method, and several verbose logging statements were removed or refined. The scheduling_flow_unipc_multistep.py file was cleaned up by removing unused methods like _sigma_to_t and __len__, along with some related variable calculations. A redundant logging statement was also removed from composed_pipeline_base.py. In perf_logger.py, print statements were replaced with logger.info and logger.error for performance metric dumping, standardizing the logging approach. Lastly, the run_suite.py file increased the max_retries for pytest from 2 to 4, and perf_baselines.json was updated with new performance baseline values for ImageVAEEncodingStage and expected_e2e_ms.

@mickqian mickqian force-pushed the sgl-diffusion-codeowners branch from 992cc44 to 12d913e Compare December 12, 2025 14:08
@mickqian mickqian merged commit c7c837c into sgl-project:main Dec 12, 2025
5 of 6 checks passed
Liwansi added a commit to iforgetmyname/sglang that referenced this pull request Dec 13, 2025
…n_eagle3_npu

* 'main' of https://github.com/sgl-project/sglang: (121 commits)
  Super tiny add gsp-fast-prepare (sgl-project#14992)
  Super tiny fix confusing slash_command_handler hint (sgl-project#14976)
  Super tiny remove unused argument (sgl-project#14966)
  [registry] Add a strict mode to model registration (sgl-project#14933)
  Feature/Fix multi lora scheduler blocking issue and evict LoRA None lastly (sgl-project#14795)
  Tune triton fused moe for the case of glm-4.6-fp8 b200 tp4 (sgl-project#15020)
  [model-gateway] refactor: unify worker management into modular workflow structure (sgl-project#15010)
  Update ci permission (sgl-project#15014)
  Refactor of http and engine entrypoints to allow custom override  (sgl-project#14869)
  Add KV4-capable backend flashmla and update server args (sgl-project#14989)
  Revert several PRs (sgl-project#14958)
  Super tiny extract route_typed_request_once (sgl-project#14951)
  Fix CI by reverting incorrect metric check logic (sgl-project#15004)
  [model-gateway] refactor: workflow engine cleanup and minor optimization (sgl-project#15001)
  [model-gateway] fix: handle workflow deadlock and optimize cycle detection (sgl-project#15000)
  [model-gateway] feat: add DAG parallel execution support and workflow optimization (sgl-project#14999)
  [model-gateway] refactor: extract workflow engine to src/workflow module (sgl-project#14996)
  Update CODEOWNERS for multimodal_gen (sgl-project#14995)
  [diffusion] docker: Tiny fix Docker Hub link in installation documentation (sgl-project#14987)
  [PD] Add decode PP event loop for PD disaggregation (sgl-project#14945)
  ...

# Conflicts:
#	python/sglang/srt/model_executor/piecewise_cuda_graph_runner.py
Prozac614 pushed a commit to Prozac614/sglang that referenced this pull request Dec 17, 2025
YChange01 pushed a commit to YChange01/sglang that referenced this pull request Jan 13, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

diffusion SGLang Diffusion

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant