[None][test] Waive 6 failed cases for main in QA CI

[tensorrt-cicd]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Jenkins build: https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/LLM_FUNCTION_CLUSTER_TEST/1482/
Bug(s): 6185150, 6211193, 6223556, 6245098

Waive entries added

accuracy/test_llm_api_pytorch.py::TestQwen3_6_27B::test_fp8 SKIP (https://nvbugs/6185150)
disaggregated/test_disaggregated.py::test_disaggregated_overlap_gen_first[ctx_pp1-TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6223556)
test_e2e.py::test_ptp_quickstart_advanced_deepseek_multi_nodes[DeepSeek-V3] SKIP (https://nvbugs/6245098)
test_e2e.py::test_openai_disagg_multi_nodes_completion_service_discovery[etcd] SKIP (https://nvbugs/6211193)
disaggregated/test_disaggregated.py::test_disaggregated_overlap_gen_first[ctx_pp4-TinyLlama-1.1B-Chat-v1.0] SKIP (https://nvbugs/6223556)
accuracy/test_llm_api_pytorch.py::TestQwen3NextInstruct::test_bf16_4gpu[tp4ep4_cudagraph_overlap_adp_off] SKIP (https://nvbugs/6185150)

---

This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.

Summary by CodeRabbit

• Tests
  • Updated test waiver configurations for internal quality assurance processes.

Note: This release contains no user-visible changes—updates are limited to internal testing infrastructure only.

[xinhe-nv]

/bot run --skip-test

[tensorrt-cicd]

PR_Github #51327 [ run ] triggered by Bot. Commit: b8f1953 Link to invocation

[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`:
- Line 118: Add a waiver entry for the DeepSeek-V3 failure in
tests/integration/test_lists/waives.txt for the test named
test_e2e.py::test_ptp_quickstart_advanced_deepseek_multi_nodes[DeepSeek-V3] that
references https://nvbugs/6245098 (or alternatively update the PR summary to
remove the claim that 6245098 is waived); ensure the new line follows the
existing waive list format and includes the exact test identifier and the nvbugs
URL so the waiver is recognized.

🪄 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: db2d8b90-3a6b-467b-abc2-8a17a079d954

📥 Commits

Reviewing files that changed from the base of the PR and between 35cce74 and b8f1953.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[coderabbitai]

📝 Walkthrough

Walkthrough

This PR adds 5 new SKIP waiver entries to the integration test skip list. The entries cover failing test cases: Qwen3NextInstruct BF16 with tensor parallelism and cuGraphs, Qwen3 FP8, two TinyLlama disaggregated overlap generation variants, and OpenAI disaggregated multi-node completion service discovery with etcd.

Changes

Test Skip Waivers

Layer / File(s)	Summary
Integration test SKIP waivers tests/integration/test_lists/waives.txt	Five SKIP entries added for failing tests: Qwen3NextInstruct bf16 4-gpu with tp4ep4_cudagraph_overlap_adp_off, Qwen3_6_27B FP8, TinyLlama disaggregated overlap generation with ctx_pp1 and ctx_pp4, and OpenAI disaggregated multi-node completion service discovery with etcd backend.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#14503: Both PRs update tests/integration/test_lists/waives.txt by adding new SKIP waiver entries for different failing tests.
• NVIDIA/TensorRT-LLM#14136: Both PRs add entries to the same waiver file to skip failing/unstable tests.
• NVIDIA/TensorRT-LLM#14163: Both PRs update tests/integration/test_lists/waives.txt to add test-skip/waiver entries.

Suggested reviewers

• crazydemo
• jieli-matrix
• StanleySun639
• LarryXFly

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title follows the required format [None][test] and clearly indicates the PR purpose is waiving 6 failed test cases for QA CI, matching the changeset content.
Description check	✅ Passed	The PR description is auto-generated and includes the Jenkins build link, bug references, and specific waive entries with links. However, it lacks the recommended sections from the template (Description, Test Coverage, PR Checklist) which are typically expected for manual PRs.
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.

_{✏️ 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.}

[coderabbitai]

♻️ Duplicate comments (1)

tests/integration/test_lists/waives.txt (1)

118-118: ⚠️ Potential issue | 🟡 Minor | ⚡ Quick win

PR summary claims 6 waivers but only 5 entries are present

The PR summary states that 6 test cases are being waived, but this file contains only 5 new SKIP entries. The missing case test_e2e.py::test_ptp_quickstart_advanced_deepseek_multi_nodes[DeepSeek-V3] (https://nvbugs/6245098) referenced in the summary is not present in the waives.txt file. Either add the missing waiver entry or update the PR summary to accurately reflect 5 waivers.

🤖 Prompt for 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.

In `@tests/integration/test_lists/waives.txt` at line 118, PR summary claims 6
waived tests but only 5 SKIP entries exist in the waives list; either add the
missing waiver for the
test_e2e.py::test_ptp_quickstart_advanced_deepseek_multi_nodes[DeepSeek-V3]
(link nvbugs/6245098) to the waives file or change the PR summary to state 5
waivers; update the waives file by adding the exact SKIP line for
test_e2e.py::test_ptp_quickstart_advanced_deepseek_multi_nodes[DeepSeek-V3]
referencing the bug URL, or if that waiver is not needed remove the extra count
in the PR summary so it matches the current entries.

🤖 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.

Duplicate comments:
In `@tests/integration/test_lists/waives.txt`:
- Line 118: PR summary claims 6 waived tests but only 5 SKIP entries exist in
the waives list; either add the missing waiver for the
test_e2e.py::test_ptp_quickstart_advanced_deepseek_multi_nodes[DeepSeek-V3]
(link nvbugs/6245098) to the waives file or change the PR summary to state 5
waivers; update the waives file by adding the exact SKIP line for
test_e2e.py::test_ptp_quickstart_advanced_deepseek_multi_nodes[DeepSeek-V3]
referencing the bug URL, or if that waiver is not needed remove the extra count
in the PR summary so it matches the current entries.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: a4ed7824-1b18-4ef1-876b-a1b7813d8c65

📥 Commits

Reviewing files that changed from the base of the PR and between 35cce74 and b8f1953.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[tensorrt-cicd]

PR_Github #51327 [ run ] completed with state SUCCESS. Commit: b8f1953
/LLM/main/L0_MergeRequest_PR pipeline #40740 (Partly Tested) 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

[tensorrt-cicd]

/bot run --skip-test

[xinhe-nv]

/bot run --skip-test

[tensorrt-cicd]

PR_Github #51465 [ run ] triggered by Bot. Commit: 2a6b9d5 Link to invocation

[tensorrt-cicd]

PR_Github #51465 [ run ] completed with state SUCCESS. Commit: 2a6b9d5
/LLM/main/L0_MergeRequest_PR pipeline #40871 (Partly Tested) completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

CI Report

Link to invocation

[xinhe-nv]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #51510 [ reuse-pipeline ] triggered by Bot. Commit: 6e49f96 Link to invocation

[xinhe-nv]

/bot reuse-pipeline

[tensorrt-cicd]

PR_Github #51515 [ reuse-pipeline ] triggered by Bot. Commit: 6dffdeb Link to invocation

[tensorrt-cicd]

PR_Github #51510 [ reuse-pipeline ] completed with state ABORTED. Commit: 6e49f96
Can't reuse PR_Github #51465 (Partly Tested) with status: SUCCESS

Link to invocation

[tensorrt-cicd]

PR_Github #51515 [ reuse-pipeline ] completed with state SUCCESS. Commit: 6dffdeb
Reusing PR_Github #51465 (Partly Tested) for commit 6dffdeb

Link to invocation