Skip to content

Comments

[None][doc] Update Qwen2/3-VL's model on supported_models.md#10797

Merged
yechank-nvidia merged 2 commits intoNVIDIA:mainfrom
yechank-nvidia:qwen3vl_doc
Jan 30, 2026
Merged

[None][doc] Update Qwen2/3-VL's model on supported_models.md#10797
yechank-nvidia merged 2 commits intoNVIDIA:mainfrom
yechank-nvidia:qwen3vl_doc

Conversation

@yechank-nvidia
Copy link
Collaborator

@yechank-nvidia yechank-nvidia commented Jan 19, 2026

Summary by CodeRabbit

  • Documentation
    • Enabled a feature for Qwen2VL and Qwen2.5VL models in the supported models list
    • Added documentation for new Qwen3VL and Qwen3VLMoe models

✏️ Tip: You can customize this high-level summary in your review settings.

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
@yechank-nvidia yechank-nvidia self-assigned this Jan 19, 2026
@yechank-nvidia yechank-nvidia requested a review from a team as a code owner January 19, 2026 05:25
@yechank-nvidia yechank-nvidia added the Multimodal Label for issues & PRs regarding Multimodal related objects label Jan 19, 2026
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jan 19, 2026

📝 Walkthrough

Walkthrough

This pull request updates the supported models documentation to reflect feature support for Qwen models. It enables a specific feature for two existing Qwen2 variants and adds two new Qwen3 model entries to the support matrix.

Changes

Cohort / File(s) Summary
Documentation Update
docs/source/models/supported-models.md
Modified feature support flags for Qwen2VLForConditionalGeneration and Qwen2_5_VLForConditionalGeneration from No to Yes; added new entries for Qwen3VLForConditionalGeneration and Qwen3VLMoeForConditionalGeneration with Yes flags.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~5 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1
❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Description check ⚠️ Warning The pull request has no description provided by the author, only the repository's template is present. The author must provide a clear description explaining what changes are being made to supported_models.md and why (e.g., feature enablement for specific models, addition of new models).
✅ Passed checks (2 passed)
Check name Status Explanation
Title check ✅ Passed The PR title '[None][doc] Update Qwen2/3-VL's model on supported_models.md' directly and clearly matches the changeset, which updates documentation for Qwen2/3-VL models in the supported_models.md file.
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

✏️ Tip: You can configure your own custom pre-merge checks in the settings.

✨ Finishing touches
  • 📝 Generate docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

Comment @coderabbitai help to get the list of available commands and usage tips.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 1

🤖 Fix all issues with AI agents
In `@docs/source/models/supported-models.md`:
- Around line 64-65: The table entry for Qwen2VLForConditionalGeneration
incorrectly claims EPD Disaggregated Serving support; update the table row for
`Qwen2VLForConditionalGeneration` to mark the EPD Disaggregated Serving column
as "No" (instead of "Yes"). Use the model's implementation details (the raised
NotImplementedError "Qwen2VLModel does not support disaggregated inference yet"
and the absence of the `@support_multimodal_disaggregated` decorator on
`Qwen2VLForConditionalGeneration`) as the justification for this change so the
docs match the code.

Copy link
Collaborator

@QiJune QiJune left a comment

Choose a reason for hiding this comment

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

LGTM

Signed-off-by: yechank <161688079+yechank-nvidia@users.noreply.github.com>
@yechank-nvidia
Copy link
Collaborator Author

/bot skip --comment "doc changes"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #34190 [ skip ] triggered by Bot. Commit: 77e7855

@tensorrt-cicd
Copy link
Collaborator

PR_Github #34190 [ skip ] completed with state SUCCESS. Commit: 77e7855
Skipping testing for commit 77e7855

@yechank-nvidia yechank-nvidia merged commit a669a16 into NVIDIA:main Jan 30, 2026
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Multimodal Label for issues & PRs regarding Multimodal related objects

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants