Skip to content

[TRTQA-3282][test] Waive 3 failed cases for main in QA CI#16600

Merged
xinhe-nv merged 4 commits into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260720-061500
Jul 20, 2026
Merged

[TRTQA-3282][test] Waive 3 failed cases for main in QA CI#16600
xinhe-nv merged 4 commits into
NVIDIA:mainfrom
trtllm-agent:trtllm-ci-report/waive-20260720-061500

Conversation

@trtllm-agent

@trtllm-agent trtllm-agent commented Jul 20, 2026

Copy link
Copy Markdown
Collaborator

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Bug(s): 6327718, 6473397, 6479324

Waive entries added

full:H100/accuracy/test_llm_api_pytorch.py::TestLagunaXS_2_1::test_bf16_dflash SKIP (https://nvbugs/6473397)
full:H100/disaggregated/test_disaggregated.py::test_disaggregated_stress_test[input8k-output1k-conc512-qwen3_5_4b_fp8_stress] SKIP (https://nvbugs/6479324)
full:H100/accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[nemotron_nano_v3_omni_fp8] SKIP (https://nvbugs/6327718)

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

Summary by CodeRabbit

  • Tests
    • Updated H100 test coverage configuration with additional skip entries for video, BF16 DFlash, and stress-test scenarios.
    • Preserved existing DeepSeek V3 Lite BF16 test waivers.

Bug(s): 6327718, 6473397, 6479324
Requested by: qa@nvidia.com

Signed-off-by: trtllm-agent <296075020+trtllm-agent@users.noreply.github.com>
@xinhe-nv
xinhe-nv enabled auto-merge (squash) July 20, 2026 06:15
@xinhe-nv xinhe-nv changed the title [None][test] Waive 3 failed cases for main in QA CI [TRTQA-3282][test] Waive 3 failed cases for main in QA CI Jul 20, 2026
@xinhe-nv

Copy link
Copy Markdown
Collaborator

/bot skip --comment "waive test on H100 only"

@coderabbitai

coderabbitai Bot commented Jul 20, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

📝 Walkthrough

Walkthrough

The integration waiver list adds four H100 SKIP entries covering VideoMMEEPD, LagunaXS, and Qwen stress tests, while retaining the existing DeepSeek waivers.

Changes

H100 Integration Waivers

Layer / File(s) Summary
Add H100 waiver entries
tests/integration/test_lists/waives.txt
Adds H100 skips for disaggregated VideoMME, LagunaXS BF16 DFlash, and the Qwen stress-test configuration while preserving existing DeepSeek waivers.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The description explains the waiver, but it omits the required Description, Test Coverage, and PR Checklist sections from the template. Add the template sections with a brief issue summary, test coverage, and PR checklist confirmation or notes for any unchecked items.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title is concise, uses the required ticket/type format, and accurately summarizes waiving three QA CI failures.
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 coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Actionable comments posted: 1

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)
tests/integration/test_lists/waives.txt (1)

245-257: 📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Add the NVIDIA copyright header required for modified files.

This modified file has no visible NVIDIA copyright header or year. Add the repository-standard header at the top; comment lines are ignored by the waiver parser.

🤖 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` around lines 245 - 257, Prepend the
repository-standard NVIDIA copyright header, including the appropriate year, to
the modified waives.txt file. Keep the existing waiver entries unchanged; the
header’s comment lines will be ignored by the parser.

Source: Coding guidelines

🧹 Nitpick comments (1)
tests/integration/test_lists/waives.txt (1)

245-257: 🩺 Stability & Availability | 🔵 Trivial

Track QA follow-up outside this waiver PR.

Coverage is intentionally insufficient while these cases are skipped. Keep root-cause fixes tracked for accuracy/test_epd_disagg_multimodal.py, accuracy/test_llm_api_pytorch.py, and disaggregated/test_disaggregated.py against the linked bugs.

🤖 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` around lines 245 - 257, Track QA
follow-up separately from this waiver update: retain the listed skips and linked
bug references, while ensuring root-cause fixes remain tracked for the affected
accuracy tests in test_epd_disagg_multimodal.py and test_llm_api_pytorch.py,
plus the disaggregated tests in test_disaggregated.py.

Source: Path instructions

🤖 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 245: Remove the duplicate H100 VideoMMEEPD waiver entry from the waiver
list, or replace it with the intended unscoped entry if the waiver must apply
only to H100; ensure the processed waiver set does not contain redundant entries
and retains the Bug 6327718 association.

---

Outside diff comments:
In `@tests/integration/test_lists/waives.txt`:
- Around line 245-257: Prepend the repository-standard NVIDIA copyright header,
including the appropriate year, to the modified waives.txt file. Keep the
existing waiver entries unchanged; the header’s comment lines will be ignored by
the parser.

---

Nitpick comments:
In `@tests/integration/test_lists/waives.txt`:
- Around line 245-257: Track QA follow-up separately from this waiver update:
retain the listed skips and linked bug references, while ensuring root-cause
fixes remain tracked for the affected accuracy tests in
test_epd_disagg_multimodal.py and test_llm_api_pytorch.py, plus the
disaggregated tests in test_disaggregated.py.
🪄 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: 89e5fec0-e388-451a-857a-e3c428d6cc8d

📥 Commits

Reviewing files that changed from the base of the PR and between 447a628 and 342a764.

📒 Files selected for processing (1)
  • tests/integration/test_lists/waives.txt

Comment thread tests/integration/test_lists/waives.txt Outdated
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #60291 [ skip ] triggered by Bot. Commit: 342a764 Link to invocation

xinhe-nv added 2 commits July 20, 2026 14:27
Signed-off-by: xinhe-nv <200704525+xinhe-nv@users.noreply.github.com>
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #60291 [ skip ] completed with state SUCCESS. Commit: 342a764
Skipping testing for commit 342a764

Link to invocation

@xinhe-nv

Copy link
Copy Markdown
Collaborator

/bot skip --comment "waive test on H100 only"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #60308 [ skip ] triggered by Bot. Commit: 21b9a71 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #60308 [ skip ] completed with state SUCCESS. Commit: 21b9a71
Skipping testing for commit 21b9a71

Link to invocation

@xinhe-nv
xinhe-nv merged commit 32110a8 into NVIDIA:main Jul 20, 2026
7 checks passed
@xinhe-nv
xinhe-nv deleted the trtllm-ci-report/waive-20260720-061500 branch July 20, 2026 07:47
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.

3 participants