Skip to content

Conversation

@Nepherpitou
Copy link
Contributor

@Nepherpitou Nepherpitou commented Nov 18, 2025

Purpose

There is an issue in Qwen3Next model loading because of typo with paddings.

Sorry, not sure if PR description is sufficient. But bug is obvious and I fixed it by modifying files in .venv. Just consider it will be nice to have here as well.

Test Plan

  • Load Qwen3 Next model

Test Result

  • Loaded successfully

Essential Elements of an Effective PR Description Checklist
  • The purpose of the PR, such as "Fix some issue (link existing issues this PR will resolve)".
  • The test plan, such as providing test command.
  • The test results, such as pasting the results comparison before and after, or e2e results
  • (Optional) The necessary documentation update, such as updating supported_models.md and examples for a new model.
  • (Optional) Release notes update. If your change is user facing, please update the release notes draft in the Google Doc.

@github-actions
Copy link

👋 Hi! Thank you for contributing to the vLLM project.

💬 Join our developer Slack at https://slack.vllm.ai to discuss your PR in #pr-reviews, coordinate on features in #feat- channels, or join special interest groups in #sig- channels.

Just a reminder: PRs would not trigger full CI run by default. Instead, it would only run fastcheck CI which starts running only a small and essential subset of CI tests to quickly catch errors.

You ask your reviewers to trigger select CI tests on top of fastcheck CI.

Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging.

To run CI, PR reviewers can either: Add ready label to the PR or enable auto-merge.

If you have any questions, please reach out to us on Slack at https://slack.vllm.ai.

🚀

@mergify mergify bot added the qwen Related to Qwen models label Nov 18, 2025
Copy link
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 addresses a critical bug in the set_moe_parameters method within the Qwen3Next model executor. The original implementation had an indentation error, causing a check for Mixture-of-Experts (MoE) layers to be performed on every iteration of a loop. This would incorrectly raise a RuntimeError if the first layer of a model was not an MoE layer, effectively preventing many models from loading. The fix correctly moves this check to after the loop, ensuring that all layers are evaluated before concluding that no MoE layers are present. The change is correct and essential for the model's functionality.

@sighingnow sighingnow enabled auto-merge (squash) November 19, 2025 02:53
@github-actions github-actions bot added the ready ONLY add when PR is ready to merge/full CI is needed label Nov 19, 2025
@sighingnow sighingnow merged commit 73ff872 into vllm-project:main Nov 19, 2025
54 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

qwen Related to Qwen models ready ONLY add when PR is ready to merge/full CI is needed

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants