[TRTLLM-12762][test] Add multi-node TP coverage for MiniMax-M2

[jieli-matrix]

Add a MiniMax-M2 (FP8 block-scales) case to test_multi_nodes_eval at TP16/PP1/EP16, covering the cross-node tensor-parallel fallback added in PR #14314: NCCL all-reduce RMS norm, per-tensor QK-norm, and head-level weight replication (num_kv_heads=8 < tp_size=16). The case is marked skip_pre_hopper and reuses the existing MMLU threshold. Registered the TP16 case in the QA multi-node functional test list.

Summary by CodeRabbit

• Tests
  • Added test coverage for MiniMax-M2 model in multi-node evaluation scenarios.

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: b56e9e77-c9cc-4514-ba8b-d7bb2596dc0c

📥 Commits

Reviewing files that changed from the base of the PR and between aa3236b and a8e18bc.

📒 Files selected for processing (2)

• tests/integration/defs/test_e2e.py
• tests/integration/test_lists/qa/llm_function_multinode.txt

---

📝 Walkthrough

Walkthrough

Adds MiniMax-M2 as a new parametrized model entry in test_multi_nodes_eval with the skip_pre_hopper marker, and registers the corresponding test_e2e.py::test_multi_nodes_eval[MiniMax-M2-tp16-mmlu] test identifier in the QA multi-node function test list.

Changes

MiniMax-M2 Multi-Node Eval Registration

Layer / File(s)	Summary
MiniMax-M2 test parameter and QA list entry tests/integration/defs/test_e2e.py, tests/integration/test_lists/qa/llm_function_multinode.txt	Adds pytest.param('MiniMax-M2', marks=skip_pre_hopper) to test_multi_nodes_eval parametrization and adds the MiniMax-M2-tp16-mmlu test identifier to the QA multi-node list.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	Write docstrings for the functions missing them to satisfy the coverage threshold.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically describes the main change: adding MiniMax-M2 model coverage to the multi-node tensor-parallel test suite.
Description check	✅ Passed	The PR description is mostly complete with a detailed explanation of what was added and why, covering the technical details of the test case and its purpose. However, it lacks a formal "Description" section and "Test Coverage" section as specified in the template structure.
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.}