Skip to content

[PP] put pp assert in model runner#12934

Merged
hnyls2002 merged 1 commit intosgl-project:mainfrom
openanolis:Xuchun/pp-clean
Nov 10, 2025
Merged

[PP] put pp assert in model runner#12934
hnyls2002 merged 1 commit intosgl-project:mainfrom
openanolis:Xuchun/pp-clean

Conversation

@XucSh
Copy link
Copy Markdown
Collaborator

@XucSh XucSh commented Nov 10, 2025

Motivation

put the assert in model runner to make error more clear

Checklist

@XucSh
[PP] put pp assert in model runner
a095e82 
Signed-off-by: Xuchun Shang <xuchun.shang@gmail.com>
@gemini-code-assist
Copy link
Copy Markdown
Contributor

gemini-code-assist Bot commented Nov 10, 2025

Summary of Changes

Hello @XucSh, 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 refines the handling of pipeline parallelism within the SGLang runtime by improving error reporting and type safety. It centralizes an important assertion to ensure that pipeline parallelism is only enabled for models that explicitly support it, making debugging easier. Additionally, it updates function signatures to correctly reflect the data types returned when pipeline parallelism is active, enhancing code clarity and maintainability.

Highlights

  • Assertion Relocation: Moved a pipeline parallelism (PP) related assertion from scheduler_pp_mixin.py to model_runner.py to provide clearer error messages when PP is configured incorrectly.
  • Pipeline Parallelism Support Check: Introduced a new assertion in the ModelRunner's initialization to explicitly check if a model supports pipeline parallelism when pp_size is greater than 1, preventing runtime issues with unsupported models.
  • Type Hint Enhancement: Updated the return type hints for forward_decode, forward_extend, and forward_idle methods in model_runner.py to include PPProxyTensors, accurately reflecting their potential return values during pipeline parallelism operations.
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[bot]
gemini-code-assist Bot reviewed Nov 10, 2025
View reviewed changes
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 improves error handling by moving an assertion for pipeline parallelism support to the ModelRunner's initialization, which is a good change for fail-fast behavior. The related type hints have also been updated. I've added a few suggestions to further improve type safety and code readability by adding type hints for the pp_proxy_tensors argument in several methods.

Comment thread python/sglang/srt/model_executor/model_runner.py
@@ -2056,7 +2061,7 @@ def forward_decode(
forward_batch: ForwardBatch,
skip_attn_backend_init: bool = False,
pp_proxy_tensors=None,
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Nov 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To improve type safety and code readability, please add a type hint for the pp_proxy_tensors argument. It should be Optional[PPProxyTensors].

Suggested change
pp_proxy_tensors=None,
pp_proxy_tensors: Optional[PPProxyTensors] = None,

Comment thread python/sglang/srt/model_executor/model_runner.py
@@ -2079,7 +2084,7 @@ def forward_extend(
forward_batch: ForwardBatch,
skip_attn_backend_init: bool = False,
pp_proxy_tensors=None,
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Nov 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To improve type safety and code readability, please add a type hint for the pp_proxy_tensors argument. It should be Optional[PPProxyTensors].

Suggested change
pp_proxy_tensors=None,
pp_proxy_tensors: Optional[PPProxyTensors] = None,

Comment thread python/sglang/srt/model_executor/model_runner.py
@@ -2106,7 +2111,7 @@ def forward_extend(

def forward_idle(
self, forward_batch: ForwardBatch, pp_proxy_tensors=None
Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist Bot Nov 10, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

medium

To improve type safety and code readability, please add a type hint for the pp_proxy_tensors argument. It should be Optional[PPProxyTensors].

Suggested change
self, forward_batch: ForwardBatch, pp_proxy_tensors=None
self, forward_batch: ForwardBatch, pp_proxy_tensors: Optional[PPProxyTensors] = None

@XucSh XucSh mentioned this pull request Nov 10, 2025
Closed
5 tasks
@hnyls2002 hnyls2002 merged commit ac19ce7 into sgl-project:main Nov 10, 2025
73 of 81 checks passed
ocss884 pushed a commit to ocss884/sglang that referenced this pull request Nov 10, 2025
@XucSh @ocss884
[PP] put pp assert in model runner (sgl-project#12934)
06fa9c7 
Signed-off-by: Xuchun Shang <xuchun.shang@gmail.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@hnyls2002 hnyls2002 hnyls2002 approved these changes

@merrymercy merrymercy Awaiting requested review from merrymercy merrymercy is a code owner

@Ying1123 Ying1123 Awaiting requested review from Ying1123 Ying1123 is a code owner

@Fridge003 Fridge003 Awaiting requested review from Fridge003 Fridge003 is a code owner

@ispobock ispobock Awaiting requested review from ispobock ispobock is a code owner

@zhyncs zhyncs Awaiting requested review from zhyncs

@xiezhq-hermann xiezhq-hermann Awaiting requested review from xiezhq-hermann

+1 more reviewer

@gemini-code-assist gemini-code-assist[bot] gemini-code-assist[bot] left review comments

Reviewers whose approvals may not affect merge requirements

Assignees

No one assigned

Labels

run-ci

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@XucSh @hnyls2002 @stmatengss