Skip to content

Inference: Add the nemotron_v3 reasoning parser#5634

Merged
sidsingh-nvidia merged 8 commits into
NVIDIA:mainfrom
sidsingh-nvidia:siddharth/add-nemotron-parsers
Jul 15, 2026
Merged

Inference: Add the nemotron_v3 reasoning parser#5634
sidsingh-nvidia merged 8 commits into
NVIDIA:mainfrom
sidsingh-nvidia:siddharth/add-nemotron-parsers

Conversation

@sidsingh-nvidia

@sidsingh-nvidia sidsingh-nvidia commented Jul 2, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor
  • I, the PR author, have personally reviewed every line of this PR.

What does this PR do?

⚠️ For major changes (either in lines of code or in its impact), please make sure to first share a design doc with the team. If you're unsure what's the best way to do so, contact @NVIDIA/mcore-oncall.

Issue tracking

For PRs from open-source community contributors:

  • New features: a linked issue is required. Please open a feature request and reference it here before submitting the PR.
  • Small updates (bug fixes, minor improvements): a linked issue is recommended and will accelerate the PR review process.

Linked issue:

Contribution process

Pre-checks

  • I have added relevant unit tests
  • I have added relevant functional tests
  • I have added proper typing to my code Typing guidelines
  • I have added relevant documentation
  • I have run the autoformatter.sh on my PR

Code review

Feel free to message or comment @NVIDIA/mcore-oncall to help accelerate your merge into main. The less complex your PR is, the faster it will be approved and merged!

All PRs start as draft. If you open a non-draft PR, it will be automatically converted to draft.

Step 1: Mark PR as "Ready for Review"

  1. When your PR is ready, click Ready for Review.
  2. An oncall reviewer is auto-assigned and expert reviewers are notified based on your changes.
    • Some PRs may jump straight to step 2. This is determined by .github/CODEOWNERS.

⚠️ Only mark as ready once merge-conflicts are resolved and the CI is passing.
Final Review might get declined if these requirements are not fulfilled.

Step 2: Final Review

For PRs that change megatron/core, once all expert reviewers have approved, the Final Review label is applied automatically and final reviewers are assigned.

For PRs outside megatron/core, this step is skipped.

Step 3: Approved

Once all required reviewers have approved, the Approved label is applied automatically.

Merge

Any member of mcore-engineers will be able to merge your PR.

@sidsingh-nvidia
sidsingh-nvidia requested review from a team as code owners July 2, 2026 21:58
@svcnvidia-nemo-ci
svcnvidia-nemo-ci marked this pull request as draft July 2, 2026 21:59
@github-actions

github-actions Bot commented Jul 2, 2026

Copy link
Copy Markdown
Contributor

This PR has been automatically converted to draft because all PRs must start as drafts.

When you are ready for review, click Ready for Review to begin the review process. This will:

  1. Add the oncall reviewer (optional reviewer)
  2. Add required review teams based on your changes

See the contribution guide for more details.

@copy-pr-bot

copy-pr-bot Bot commented Jul 2, 2026

Copy link
Copy Markdown

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

@kvareddy
kvareddy requested a review from ArEsKay3 July 6, 2026 09:49
@kvareddy

kvareddy commented Jul 6, 2026

Copy link
Copy Markdown
Contributor

@ArEsKay3 Can you please take a look at this MR?

@sidsingh-nvidia
sidsingh-nvidia marked this pull request as ready for review July 13, 2026 19:28
ArEsKay3
ArEsKay3 approved these changes Jul 14, 2026
View reviewed changes

@ArEsKay3 ArEsKay3 left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

LGTM. A side question. Where does the VLLM version of this code exist? Is it delivered as part of the Super/Ultra HF artifacts? I think that's how the Nano ones worked.

@sidsingh-nvidia

sidsingh-nvidia commented Jul 14, 2026

Copy link
Copy Markdown
Contributor Author

@ArEsKay3 this was eventually upstreamed into vllm here - https://github.com/vllm-project/vllm/blob/main/vllm/parser/nemotron_v3.py.

@sidsingh-nvidia sidsingh-nvidia changed the title Inference: Add super_v3 and ultra_v3 reasoning parsers Inference: Add the nemotron_v3 reasoning parser Jul 14, 2026
@svcnvidia-nemo-ci svcnvidia-nemo-ci added the Final Review PR is in the "final review" stage label Jul 14, 2026
@svcnvidia-nemo-ci svcnvidia-nemo-ci added Approved All necessary approvals have been made and removed Final Review PR is in the "final review" stage labels Jul 14, 2026
@sidsingh-nvidia
sidsingh-nvidia added this pull request to the merge queue Jul 15, 2026
@svcnvidia-nemo-ci

svcnvidia-nemo-ci commented Jul 15, 2026

Copy link
Copy Markdown
Contributor

🔄 Merge queue validation started!

You can track the progress here: https://github.com/NVIDIA/Megatron-LM/actions/runs/29407065923

Merged via the queue into NVIDIA:main with commit 82e9dc6 Jul 15, 2026
89 checks passed
@sidsingh-nvidia
sidsingh-nvidia deleted the siddharth/add-nemotron-parsers branch July 15, 2026 10:43
chochowski pushed a commit to chochowski/Megatron-LM that referenced this pull request Jul 20, 2026
@sidsingh-nvidia @chochowski
Inference: Add the nemotron_v3 reasoning parser (NVIDIA#5634)
06ad605 
Signed-off-by: Siddharth Singh <sidsingh@nvidia.com>
Signed-off-by: mchochowski <mchochowski@nvidia.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@claude claude[bot] claude[bot] left review comments
@ArEsKay3 ArEsKay3 ArEsKay3 approved these changes
@kvareddy kvareddy kvareddy approved these changes
@dimapihtar dimapihtar dimapihtar approved these changes
@shanmugamr1992 shanmugamr1992 shanmugamr1992 approved these changes

Assignees

No one assigned

Labels

Approved All necessary approvals have been made complexity: low

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

6 participants

@sidsingh-nvidia @kvareddy @svcnvidia-nemo-ci @ArEsKay3 @dimapihtar @shanmugamr1992