[None][fix] Add nemotron-v3 as the proper nemotron-h reasoning parser

[Wanli-Jiang]

Summary by CodeRabbit

• Bug Fixes

  • Fixed reasoning parser routing for Nemotron-H models to use the correct parser implementation.

• Tests

  • Added test coverage for Nemotron-H model auto-detection and parser resolution.
  • Added validation test for parser aliasing consistency.

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)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• 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.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 61d596e8-40c8-47e0-9db2-0822bbddc053

📥 Commits

Reviewing files that changed from the base of the PR and between 6ab5005 and 93d136c.

📒 Files selected for processing (2)

• tensorrt_llm/llmapi/reasoning_parser.py
• tests/unittest/llmapi/test_reasoning_parser.py

---

📝 Walkthrough

Walkthrough

This pull request updates the reasoning parser routing for Nemotron-H models. The NemotronV3ReasoningParser is registered under a dedicated nemotron-v3 key, and both nemotron_h and nemotron_h_puzzle models are remapped to this parser from the legacy nano-v3. Test coverage validates auto-detection and backward compatibility.

Changes

Nemotron Model Reasoning Parser Routing

Layer / File(s)	Summary
Parser registration and model routing tensorrt_llm/llmapi/reasoning_parser.py	NemotronV3ReasoningParser is registered under nemotron-v3, and MODEL_TYPE_TO_REASONING_PARSER maps nemotron_h and nemotron_h_puzzle to this dedicated key instead of the legacy nano-v3.
Test coverage for Nemotron model auto-detection tests/unittest/llmapi/test_reasoning_parser.py	Tests import NemotronV3ReasoningParser and validate that nemotron_h and nemotron_h_puzzle auto-detect to nemotron-v3, and that both nemotron-v3 and nano-v3 resolve to the same parser instance for backward compatibility.

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is entirely a template scaffold with no actual content filled in—no description, test coverage information, or implementation details are provided beyond the template structure.	Fill in the Description section to explain the issue and solution, add Test Coverage section listing the relevant tests (test_auto_detect_nemotron_h and test_nemotron_v3_alias_same_parser), and provide implementation details.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: updating nemotron-h to use the nemotron-v3 reasoning parser instead of nano-v3, which aligns with the code changes in both files.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[Wanli-Jiang]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #51811 [ run ] triggered by Bot. Commit: 93d136c Link to invocation

[JunyiXu-nv]

LGTM

[tensorrt-cicd]

PR_Github #51811 [ run ] completed with state SUCCESS. Commit: 93d136c
/LLM/main/L0_MergeRequest_PR pipeline #41173 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

[Wanli-Jiang]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #51932 [ run ] triggered by Bot. Commit: 93d136c Link to invocation

[tensorrt-cicd]

PR_Github #51932 [ run ] completed with state FAILURE. Commit: 93d136c
/LLM/main/L0_MergeRequest_PR pipeline #41283 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation

[Wanli-Jiang]

/bot run --disable-fail-fast

[tensorrt-cicd]

PR_Github #51967 [ run ] triggered by Bot. Commit: 93d136c Link to invocation

[tensorrt-cicd]

PR_Github #51967 [ run ] completed with state SUCCESS. Commit: 93d136c
/LLM/main/L0_MergeRequest_PR pipeline #41317 completed with status: 'SUCCESS'

CI Report

Link to invocation