Skip to content

[None][docs] Update nemotron 3 super deployment to include tool calling and reasoning parser#12215

Merged
nv-guomingz merged 1 commit intoNVIDIA:mainfrom
tijyojwad:jdaw/update-nemotron-docs
Mar 17, 2026
Merged

[None][docs] Update nemotron 3 super deployment to include tool calling and reasoning parser#12215
nv-guomingz merged 1 commit intoNVIDIA:mainfrom
tijyojwad:jdaw/update-nemotron-docs

Conversation

@tijyojwad
Copy link
Collaborator

@tijyojwad tijyojwad commented Mar 14, 2026

…ng and reasoning parser

Summary by CodeRabbit

  • Documentation
    • Updated deployment guides with new server configuration options for Nemotron model serving, enabling additional parser capabilities for enhanced inference handling.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

  • PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

  • PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

  • Test cases are provided for new code paths (see test instructions)

  • Any new dependencies have been scanned for license and vulnerabilities

  • CODEOWNERS updated if ownership changes

  • Documentation updated as needed

  • Update tava architecture diagram if there is a significant design change in PR.

  • The reviewers assigned automatically/manually are appropriate for the PR.

  • Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

…ng and reasoning parser

Signed-off-by: Joyjit Daw <1127155+tijyojwad@users.noreply.github.com>
@tijyojwad
Copy link
Collaborator Author

/bot run

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Mar 14, 2026

📝 Walkthrough

Walkthrough

Documentation updates to deployment and example guides for Nemotron Super, adding --reasoning_parser nano-v3 and --tool_parser qwen3_coder command-line options to trtllm-serve invocations across multiple configuration examples.

Changes

Cohort / File(s) Summary
Nemotron Deployment Documentation
docs/source/deployment-guide/deployment-guide-for-nemotron-3-super-on-trtllm.md, examples/models/core/nemotron/README_nemotron_super_v3.md
Added --reasoning_parser nano-v3 and --tool_parser qwen3_coder parser options to trtllm-serve launch commands in deployment guides and example configurations.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The PR description is incomplete. It contains only template text with no substantive explanation of changes, test coverage, or rationale for the updates. Complete the Description and Test Coverage sections. Explain what parser options were added, why they're needed, and what tests validate these documentation changes.
✅ Passed checks (2 passed)
Check name Status Explanation
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Title check ✅ Passed The title accurately summarizes the main changes: updating NeMoTron 3 Super deployment documentation to include tool calling (--tool_parser qwen3_coder) and reasoning parser (--reasoning_parser nano-v3) options.

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

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
📝 Coding Plan
  • Generate coding plan for human review comments

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

Tip

You can disable sequence diagrams in the walkthrough.

Disable the reviews.sequence_diagrams setting to disable sequence diagrams in the walkthrough.

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

🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@examples/models/core/nemotron/README_nemotron_super_v3.md`:
- Around line 121-126: Replace the deprecated flag in the example CLI
invocation: in the trtllm-serve command shown (the line containing
--extra_llm_api_options ./extra-llm-api-config.yml), change the flag to --config
so the command uses --config ./extra-llm-api-config.yml; update any adjacent
text that references --extra_llm_api_options to use --config and ensure the
example aligns with the documented CLI preference for trtllm-serve.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 7f2f29ee-ff22-4cad-aa3c-78c0fce5efd2

📥 Commits

Reviewing files that changed from the base of the PR and between 8cdcce9 and 44bdeba.

📒 Files selected for processing (2)
  • docs/source/deployment-guide/deployment-guide-for-nemotron-3-super-on-trtllm.md
  • examples/models/core/nemotron/README_nemotron_super_v3.md

@tensorrt-cicd
Copy link
Collaborator

PR_Github #38953 [ run ] triggered by Bot. Commit: 44bdeba Link to invocation

@tensorrt-cicd
Copy link
Collaborator

PR_Github #38953 [ run ] completed with state SUCCESS. Commit: 44bdeba
/LLM/main/L0_MergeRequest_PR pipeline #30235 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation

@tijyojwad
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #39150 [ run ] triggered by Bot. Commit: 44bdeba Link to invocation

@Wanli-Jiang Wanli-Jiang changed the title [None][docs] Update nemotron 3 super deployment to include tool calli… [None][docs] Update nemotron 3 super deployment to include tool calling and reasoning parser Mar 17, 2026
@nv-guomingz nv-guomingz enabled auto-merge (squash) March 17, 2026 01:51
@tensorrt-cicd
Copy link
Collaborator

PR_Github #39150 [ run ] completed with state SUCCESS. Commit: 44bdeba
/LLM/main/L0_MergeRequest_PR pipeline #30409 completed with status: 'SUCCESS'

CI Report

Link to invocation

@nv-guomingz nv-guomingz merged commit 20fc52c into NVIDIA:main Mar 17, 2026
10 checks passed
limin2021 pushed a commit to limin2021/TensorRT-LLM that referenced this pull request Mar 19, 2026
…ng and reasoning parser (NVIDIA#12215)

Signed-off-by: Joyjit Daw <1127155+tijyojwad@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants