Adjust wrong `mtp` meaning introduce by mimo by hnyls2002 · Pull Request #15632 · sgl-project/sglang

hnyls2002 · 2025-12-22T10:10:50Z

basically rename: mtp -> multi_layer_eagle

gemini-code-assist · 2025-12-22T10:11:07Z

Summary of Changes

Hello @hnyls2002, 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 a significant refactoring effort to enhance code clarity and consistency. It systematically renames the mtp identifier to multi_layer_eagle throughout the codebase, particularly within the speculative decoding components. This change addresses an inaccurate naming convention, ensuring that the terminology accurately reflects the underlying multi-layer Eagle functionality and streamlines future development and understanding.

Highlights

Renaming mtp to multi_layer_eagle: The primary change in this pull request is the renaming of the mtp identifier to multi_layer_eagle across several files to correct a previous misnomer and improve clarity.
Updated ServerArgs: The ServerArgs class has been updated to remove the enable_mtp flag and introduce enable_multi_layer_eagle, along with corresponding changes to CLI argument parsing and help text.
Refactored Scheduler class: The Scheduler class no longer stores enable_mtp as an instance attribute, instead directly referencing server_args.enable_multi_layer_eagle where needed.

🧠 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.

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.

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 rename mtp to multi_layer_eagle for clarity. The changes are mostly correct and cover several files where this flag is used. However, I've found a few places where the old naming mtp or MTP is still present, either in variable names or comments. I've left specific comments on these to ensure the renaming is consistent throughout the codebase. Additionally, I've suggested renaming related classes and files in a follow-up to complete this refactoring effort.

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

hnyls2002 · 2025-12-22T10:24:35Z

/gemini review

gemini-code-assist

Code Review

This pull request refactors the codebase to rename mtp to multi_layer_eagle. The changes are mostly correct and cover many files. However, I've found a few critical typos that would break the code, as well as some incomplete renames that should be addressed for consistency. Please see the detailed comments for suggestions.

hnyls2002 · 2025-12-22T10:35:24Z

/gemini review

gemini-code-assist

Code Review

This pull request is a large-scale refactoring to rename mtp to multi_layer_eagle across the codebase for better clarity and correctness, which is a great improvement. The changes are mostly straightforward renaming of variables, classes, files, and arguments. I've found a few minor inconsistencies in the renaming that could be addressed to make the changes complete. Overall, the refactoring is well-executed.

hnyls2002 · 2025-12-22T17:57:36Z

/gemini review

gemini-code-assist · 2025-12-22T17:57:39Z

Warning

You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again!

hnyls2002 · 2025-12-22T17:57:43Z

/tag-and-rerun-ci

…n_eagle3_dp * 'main' of https://github.com/sgl-project/sglang: (208 commits) MoE: Skip SiLU/GELU activation for masked experts (sgl-project#15539) [GLM-ASR] GLM-ASR Support (sgl-project#15570) Improve engine customization interface (sgl-project#15635) chore: bump sgl-kernel version to 0.3.20 (sgl-project#15590) bugfix[schedule]: Refactor sort method and add related UT (sgl-project#13576) Adjust wrong `mtp` meaning introduce by mimo (sgl-project#15632) Tiny add back missing router per attempt response metric (sgl-project#15621) Fix router gRPC mode launch error caused by async loading (sgl-project#15368) [model-gateway] return 503 when all workers are circuit-broken (sgl-project#15611) [Diffusion] Support peak memory record in offline generate and serving (sgl-project#15610) [VLM] Tiny: Unify VLM environment variables (sgl-project#15572) [diffusion] chore: remove default post-denoising dit offload in local mode (sgl-project#15573) Tiny enable soft watchdog in CI for stuck without logs (sgl-project#15616) Tiny add stuck simulation (sgl-project#15613) Support soft watchdog for tokenizer/detokenizer/dp-controller processes (sgl-project#15607) Tiny avoid EnvField misuse (sgl-project#15612) add decode round robin policy (sgl-project#15164) Add glm-4.6-fp8 with/without mtp in nightly ci (sgl-project#15566) Adapt fixture-kit to gsm8k mixin (sgl-project#15599) [model-gateway] add retry support to OpenAI router chat endpoint (sgl-project#15589) ...

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

hnyls2002 added 2 commits December 22, 2025 18:00

rename

cde6cbd

rename

68280ca

hnyls2002 requested review from ByronHsu, ShangmingCai, Ying1123, merrymercy and xiezhq-hermann as code owners December 22, 2025 10:10

gemini-code-assist Bot reviewed Dec 22, 2025

View reviewed changes

Comment thread python/sglang/srt/configs/model_config.py Outdated

Comment thread python/sglang/srt/managers/scheduler.py

Comment thread python/sglang/srt/server_args.py Outdated

hnyls2002 and others added 6 commits December 22, 2025 18:13

rename

f9e3df9

rename

6dd1491

rename

68129d6

auto set

2065cfe

Update python/sglang/srt/server_args.py

1bce0be

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

rename

eb2bcd3

gemini-code-assist Bot reviewed Dec 22, 2025

View reviewed changes

hnyls2002 added 4 commits December 22, 2025 18:29

rename

bba8059

rename

51f6d5d

rename

58bfe52

rename

72bda25

gemini-code-assist Bot reviewed Dec 22, 2025

View reviewed changes

Comment thread python/sglang/srt/speculative/multi_layer_eagle_draft_extend_cuda_graph_runner.py Outdated

Comment thread python/sglang/srt/speculative/multi_layer_eagle_draft_extend_cuda_graph_runner.py Outdated

hnyls2002 added 2 commits December 23, 2025 01:53

rename

81a4d83

rename

c62c171

github-actions Bot added the run-ci label Dec 22, 2025

hnyls2002 merged commit 3c882db into main Dec 22, 2025
88 of 129 checks passed

hnyls2002 deleted the lsyin/adjust-mimo branch December 22, 2025 18:06

jiaming1130 pushed a commit to zhuyijie88/sglang that referenced this pull request Dec 25, 2025

Adjust wrong mtp meaning introduce by mimo (sgl-project#15632)

3348350

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

YChange01 pushed a commit to YChange01/sglang that referenced this pull request Jan 13, 2026

Adjust wrong mtp meaning introduce by mimo (sgl-project#15632)

2c34ba2

Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

Conversation

hnyls2002 commented Dec 22, 2025

Uh oh!

gemini-code-assist Bot commented Dec 22, 2025

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!

Uh oh!

Uh oh!

Uh oh!

hnyls2002 commented Dec 22, 2025

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

hnyls2002 commented Dec 22, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

gemini-code-assist Bot left a comment

Choose a reason for hiding this comment

Code Review

Uh oh!

Uh oh!

Uh oh!

hnyls2002 commented Dec 22, 2025

Uh oh!

gemini-code-assist Bot commented Dec 22, 2025

Uh oh!

hnyls2002 commented Dec 22, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

hnyls2002 commented Dec 22, 2025 •

edited

Loading