Skip to content

[diffusion] fix: fix video model sp when resolution is not specified#15047

Merged
mickqian merged 10 commits intomainfrom
diffusion-fix
Dec 15, 2025
Merged

[diffusion] fix: fix video model sp when resolution is not specified#15047
mickqian merged 10 commits intomainfrom
diffusion-fix

Conversation

@mickqian
Copy link
Copy Markdown
Collaborator

@mickqian mickqian commented Dec 13, 2025 •
edited
Loading

fixes #15045

Motivation

Modifications

Accuracy Tests

Benchmarking and Profiling

Checklist

@mickqian mickqian requested a review from yhyang201 as a code owner December 13, 2025 08:16
@github-actions github-actions Bot added the diffusion SGLang Diffusion label Dec 13, 2025
@gemini-code-assist
Copy link
Copy Markdown
Contributor

gemini-code-assist Bot commented Dec 13, 2025

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 addresses a robustness issue in the video model's spatial partitioning logic. It introduces a crucial change to handle cases where the video's time dimension is not perfectly divisible by the spatial partitioning degree. By adding strategic padding to the latent representations, the system can now gracefully process such inputs, ensuring stable and correct sharding operations without requiring specific resolution alignments.

Highlights

  • Video Model Spatial Partitioning Fix: Resolved an issue where the video model's spatial partitioning (SP) could fail when the input resolution's time dimension was not a perfect multiple of the SP world size.
  • Latent Tensor Padding: Implemented a padding mechanism for the latents tensor along the time dimension to ensure its size is always a multiple of sp_world_size before sharding, preventing errors in the rearrange operation.
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 Dec 13, 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 aims to fix an issue with sequence parallelism (SP) for video models by padding latents when their time dimension is not divisible by the SP world size. While the intent is correct, the implementation introduces two critical bugs: an incorrect shape construction for the padding tensor which would cause a runtime error, and a logical flaw that prevents the sharding operation from executing after padding. My review provides a single, comprehensive code suggestion to fix both issues and ensure the logic is correct.

Comment thread python/sglang/multimodal_gen/configs/pipeline_configs/base.py Outdated
@github-actions github-actions Bot added the npu label Dec 13, 2025
@mickqian
Copy link
Copy Markdown
Collaborator Author

mickqian commented Dec 13, 2025

/tag-and-rerun-ci

@mickqian
Copy link
Copy Markdown
Collaborator Author

mickqian commented Dec 13, 2025

/rerun-failed-ci

@mickqian mickqian merged commit b098b1a into main Dec 15, 2025
137 of 143 checks passed
@mickqian mickqian deleted the diffusion-fix branch December 15, 2025 12:25
Liwansi added a commit to iforgetmyname/sglang that referenced this pull request Dec 15, 2025
@Liwansi
Merge branch 'main' of https://github.com/sgl-project/sglang into qwe…
ff39600 
…n_eagle3_npu

* 'main' of https://github.com/sgl-project/sglang: (89 commits)
  [model-gateway] Remove legacy RouterMetrics and Rename SmgMetrics to Metrics and smg_labels to metrics_labels (sgl-project#15160)
  [diffusion] fix: fix video model sp when resolution is not specified (sgl-project#15047)
  [diffusion] fix: fix pytorch non-writable array warning (sgl-project#15017)
  [diffusion] fix: cache dit with parallel (sgl-project#15163)
  chore: change npu pr-test a2 runner (sgl-project#15152)
  [Feature] Fuse mrope all in 1 kernel (sgl-project#14906)
  Fix num running requests (load) wrong cleared for ongoing requests (sgl-project#15116)
  Fused two elementwise kernels for k_nope and k_pe concat (sgl-project#14862)
  fix: adding date and fixing release name issue (sgl-project#15174)
  [CPU] Add Gemma3RMSNorm kernel in sgl-kernel and add ut (sgl-project#9324)
  feature: PR wheel (sgl-project#15170)
  [diffusion] model: support mutli-image input and qwen-image-edit-2509 (sgl-project#15005)
  fix CompressedTensorsW8A8Int8 min_capability (sgl-project#13914)
  Tiny improve summary text in `bench_one_batch_server.py` (sgl-project#15158)
  [model-gateway] add mcp and discovery metrics (sgl-project#15156)
  fix: move ci-bot (sgl-project#15154)
  Fix import warnings (sgl-project#15144)
  ci: adding errors to Github summary (sgl-project#14778)
  [model-gateway] Add streaming metrics for harmony gRPC router (sgl-project#15147)
  [model-gateway] upgrade axum and axum server (sgl-project#15146)
  ...

# Conflicts:
#	python/sglang/srt/server_args.py
tonyluj pushed a commit to openanolis/sglang that referenced this pull request Dec 17, 2025
@mickqian @Brain97 @tonyluj
[diffusion] fix: fix video model sp when resolution is not specified (s…
7ec536c 
…gl-project#15047)

Co-authored-by: Brain97 <Brain97@users.noreply.github.com>
YChange01 pushed a commit to YChange01/sglang that referenced this pull request Jan 13, 2026
@mickqian @Brain97 @YChange01
[diffusion] fix: fix video model sp when resolution is not specified (s…
9011ba5 
…gl-project#15047)

Co-authored-by: Brain97 <Brain97@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@yhyang201 yhyang201 Awaiting requested review from yhyang201 yhyang201 is a code owner

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

diffusion SGLang Diffusion npu run-ci

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

[Bug] Diffusion profiler wan2.2 bug

2 participants

@mickqian @Brain97