Skip to content

Super tiny add gsp-fast-prepare#14992

Merged
fzyzcjy merged 1 commit intosgl-project:mainfrom
fzyzcjy:feat/gsp_fast_prepare
Dec 13, 2025
Merged

Super tiny add gsp-fast-prepare#14992
fzyzcjy merged 1 commit intosgl-project:mainfrom
fzyzcjy:feat/gsp_fast_prepare

Conversation

@fzyzcjy
Copy link
Copy Markdown
Collaborator

@fzyzcjy fzyzcjy commented Dec 12, 2025

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

@gemini-code-assist
Copy link
Copy Markdown
Contributor

Summary of Changes

Hello @fzyzcjy, 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 introduces a mechanism to significantly accelerate the data preparation phase for benchmarking with Generated Shared Prefix (GSP) datasets. By adding a new flag, users can opt to skip detailed tokenization and statistical computations, making it ideal for pressure tests where quick setup is prioritized over precise token metrics.

Highlights

  • New gsp-fast-prepare argument: Introduces a new command-line argument --gsp-fast-prepare to enable a faster preparation mode for Generated Shared Prefix (GSP) datasets in benchmarking.
  • Accelerated prompt length calculation: When gsp-fast-prepare is active, the prompt_len is set to a fixed value of 1, bypassing the potentially time-consuming tokenizer encoding for full prompts.
  • Suppressed statistics output: Under gsp-fast-prepare mode, the detailed statistics regarding total input/output tokens and average prompt lengths are no longer computed or printed, further speeding up the preparation process.
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.

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 introduces a --gsp-fast-prepare flag to the benchmarking script. This flag is designed to accelerate the data preparation process for the generated-shared-prefix dataset by skipping expensive tokenization steps used for calculating statistics. The implementation correctly modifies the prompt length calculation and conditionally prints statistics based on this flag. The changes are logical and well-contained. I have one minor suggestion to improve code readability by reducing redundant code.

Comment thread python/sglang/bench_serving.py
@fzyzcjy fzyzcjy closed this Dec 13, 2025
@fzyzcjy fzyzcjy reopened this Dec 13, 2025
@fzyzcjy fzyzcjy merged commit df111bc into sgl-project:main Dec 13, 2025
102 of 117 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

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant