[https://nvbugs/6427411][chore] Waive failed tests in Pre-merge

[shuyixiong]

Summary by CodeRabbit

• Tests
  • Updated the integration test waiver list to account for additional skipped cases across disaggregated serving, LLM API, PyTorch, and Ray scenarios.
  • Adjusted existing waivers and added new ones for broader model and configuration coverage, including inference and output-processing cases.

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.

[shuyixiong]

/bot skip --comment "Waive tests"

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR updates the integration test waives list by adding new SKIP entries with nvbug references for disaggregated serving, LLM API PyTorch/Ray accuracy tests, and unittest multi-GPU cases, and replaces one existing unittest waive with three new ones.

Changes

Waives list additions

Layer / File(s)	Summary
Disaggregated serving and disaggregated test waives tests/integration/test_lists/waives.txt	New SKIP entries for DeepSeekV3Lite helix/precision configurations, Llama3_1_8BInstruct tensor-parallelism patterns in test_disaggregated_serving.py, and a new test_disaggregated_ctxpp2_genpp2 waive.
LLM API PyTorch and Ray accuracy test waives tests/integration/test_lists/waives.txt	New SKIP entries for DeepSeekV3Lite fp8_block_scales_4gpus/nvfp4_4gpus, Llama3/Nemotron parallelism variants, test_pp2_ray, and Ray example inference tests (pp2, tp2pp2).
Unittest multi-GPU waive replacement tests/integration/test_lists/waives.txt	Removed the phi3 lora fused modules waive and added waives for test_additional_model_outputs_integration_pp2 and two tinyllama logits processor multi-GPU cases.

Estimated code review effort: 1 (Trivial) | ~5 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#16093: Both PRs add new SKIP/waive entries to the same waives.txt file for newly failing DeepSeek/disaggregated/Ray-related CI test parameterizations.

Suggested reviewers: dongxuy04, pcastonguay, yuxianq, mzweilz

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description is still the template skeleton and does not explain the issue, solution, or test coverage.	Fill in the Description and Test Coverage sections with the problem, the waiver changes made, and the tests that cover them.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title follows the required ticket/type format and clearly summarizes the test-waiver change.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
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.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@tests/integration/test_lists/waives.txt`:
- Around line 431-434: The waiver list update is adding new skips without
removing the stale phi3 waiver, so this replacement is broader than intended. In
the waives file, update the affected hunk so the existing
unittest/llmapi/test_llm_multi_gpu_pytorch.py::test_phi3_lora_fused_modules_output_on_tp2_identical_to_tp1
entry is removed if this change is meant to replace it, while keeping the
intended new tinyllama-related waives only. Verify the final list reflects the
exact current skip set and does not retain obsolete entries.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: b733868e-56a0-4c7c-b0de-33710f84a52d

📥 Commits

Reviewing files that changed from the base of the PR and between 3eb7feb and 8f5a95d.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[tensorrt-cicd]

PR_Github #58155 [ skip ] triggered by Bot. Commit: 8f5a95d Link to invocation

[tensorrt-cicd]

PR_Github #58155 [ skip ] completed with state SUCCESS. Commit: 8f5a95d
Skipping testing for commit 8f5a95d

Link to invocation