Skip to content

Conversation

@nv-lschneider
Copy link
Collaborator

@nv-lschneider nv-lschneider commented Jan 7, 2026

Summary by CodeRabbit

  • Tests
    • Removed four exemptions from the test waives list, adjusting which tests are subject to skip requirements.

✏️ Tip: You can customize this high-level summary in your review settings.

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)

  • 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

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

Details

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental)]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Examples: "A10-PyTorch-1, xxx". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

@nv-lschneider nv-lschneider changed the title [https://nvbugspro.nvidia.com/bug/5741392][fix] @coderabbitai tile [https://nvbugspro.nvidia.com/5741392][fix] @coderabbitai tile Jan 7, 2026
@nv-lschneider
Copy link
Collaborator Author

/bot run --disable-fail-fast --add-multi-gpu-test

@nv-lschneider nv-lschneider changed the title [https://nvbugspro.nvidia.com/5741392][fix] @coderabbitai tile [https://nvbugs/5741392][fix] @coderabbitai tile Jan 7, 2026
@tensorrt-cicd
Copy link
Collaborator

PR_Github #30925 [ run ] triggered by Bot. Commit: a99602e

@nv-lschneider
Copy link
Collaborator Author

/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #30958 [ run ] triggered by Bot. Commit: 7fd98b7

@tensorrt-cicd
Copy link
Collaborator

PR_Github #30958 [ run ] completed with state SUCCESS. Commit: 7fd98b7
/LLM/main/L0_MergeRequest_PR pipeline #23920 (Partly Tested) completed with status: 'FAILURE'

⚠️ 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

@nv-lschneider nv-lschneider force-pushed the lschneider/unwaive-hanging-test branch from 7fd98b7 to b5709ec Compare January 8, 2026 16:44
@nv-lschneider
Copy link
Collaborator Author

/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31093 [ run ] triggered by Bot. Commit: b5709ec

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31093 [ run ] completed with state FAILURE. Commit: b5709ec
/LLM/main/L0_MergeRequest_PR pipeline #24010 (Partly Tested) completed with status: 'FAILURE'

⚠️ 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

@nv-lschneider nv-lschneider force-pushed the lschneider/unwaive-hanging-test branch from b5709ec to 98da37b Compare January 9, 2026 13:42
@nv-lschneider
Copy link
Collaborator Author

/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31260 [ run ] triggered by Bot. Commit: 98da37b

@nv-lschneider nv-lschneider force-pushed the lschneider/unwaive-hanging-test branch from c6c1a96 to f2407a1 Compare January 9, 2026 14:35
@nv-lschneider
Copy link
Collaborator Author

/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31265 [ run ] triggered by Bot. Commit: f2407a1

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31260 [ run ] completed with state ABORTED. Commit: 98da37b

@nv-lschneider
Copy link
Collaborator Author

/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31284 [ run ] triggered by Bot. Commit: f2407a1

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31284 [ run ] completed with state FAILURE. Commit: f2407a1
/LLM/main/L0_MergeRequest_PR pipeline #24178 (Partly Tested) completed with status: 'FAILURE'

⚠️ 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

@nv-lschneider nv-lschneider force-pushed the lschneider/unwaive-hanging-test branch from f2407a1 to 4b768bb Compare January 12, 2026 13:34
@nv-lschneider
Copy link
Collaborator Author

/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31574 [ run ] triggered by Bot. Commit: 4b768bb

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31574 [ run ] completed with state SUCCESS. Commit: 4b768bb
/LLM/main/L0_MergeRequest_PR pipeline #24415 (Partly Tested) completed with status: 'FAILURE'

⚠️ 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

@nv-lschneider nv-lschneider force-pushed the lschneider/unwaive-hanging-test branch from 2d95142 to 9ccd0be Compare January 12, 2026 20:39
@nv-lschneider
Copy link
Collaborator Author

/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1"

1 similar comment
@nv-lschneider
Copy link
Collaborator Author

/bot run --stage-list "DGX_H100-2_GPUs-PyTorch-Others-1"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31801 [ run ] triggered by Bot. Commit: 9ccd0be

@nv-lschneider nv-lschneider force-pushed the lschneider/unwaive-hanging-test branch from 9ccd0be to e1c1947 Compare January 13, 2026 19:28
@nv-lschneider
Copy link
Collaborator Author

/bot run --disable-fail-fast --add-multi-gpu-test

@nv-lschneider nv-lschneider marked this pull request as ready for review January 13, 2026 19:29
@coderabbitai coderabbitai bot changed the title [https://nvbugs/5741392][fix] @coderabbitai tile [https://nvbugs/5741392][fix] [chore] Remove test exemptions from waivers tile Jan 13, 2026
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Jan 13, 2026

📝 Walkthrough

Walkthrough

Four test exemptions are removed from the waives list: entries for allreduce fusion pattern tests, row linear residual norm fusion tests, and a speculative decoding test. No test behavior or functionality is modified.

Changes

Cohort / File(s) Summary
Test exemptions list
tests/integration/test_lists/waives.txt
Removed 4 SKIP exemptions: test_allreduce_fusion_patterns, test_row_linear_residual_norm_fusion (2 entries), and test_gpt_speculative_decoding

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 1 | ❌ 2
❌ Failed checks (1 warning, 1 inconclusive)
Check name Status Explanation Resolution
Description check ⚠️ Warning The PR description is largely incomplete; it contains only a checklist template and GitHub bot help text with no substantive explanation of what changes are being made or why. Add a clear description explaining the purpose of removing test exemptions, the tests affected, and the justification for these changes.
Title check ❓ Inconclusive The PR title references a valid NVBugs ticket and uses appropriate type markers, but contains a typo ('waivers tile' instead of 'waivers list') and is somewhat unclear about the specific action being taken. Clarify the title to accurately describe the change, e.g., '[https://nvbugs/5741392][chore] Remove test exemptions from waives list' or similar.
✅ Passed checks (1 passed)
Check name Status Explanation
Docstring Coverage ✅ Passed No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

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

✨ Finishing touches
  • 📝 Generate docstrings

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31815 [ run ] triggered by Bot. Commit: e1c1947

@tensorrt-cicd
Copy link
Collaborator

PR_Github #31815 [ run ] completed with state SUCCESS. Commit: e1c1947
/LLM/main/L0_MergeRequest_PR pipeline #24628 completed with status: 'FAILURE'

⚠️ 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

@nv-lschneider
Copy link
Collaborator Author

2 failing SBSA tests, because lost connection with jenkins server, 1 x86 failure timed out mid test without hang.
/bot run --disable-fail-fast --add-multi-gpu-test

@nv-lschneider
Copy link
Collaborator Author

/bot run --disable-fail-fast --add-multi-gpu-test

1 similar comment
@nv-lschneider
Copy link
Collaborator Author

/bot run --disable-fail-fast --add-multi-gpu-test

@tensorrt-cicd
Copy link
Collaborator

PR_Github #32002 [ run ] triggered by Bot. Commit: e1c1947

@tensorrt-cicd
Copy link
Collaborator

PR_Github #32003 [ run ] triggered by Bot. Commit: e1c1947

@tensorrt-cicd
Copy link
Collaborator

PR_Github #32002 [ run ] completed with state ABORTED. Commit: e1c1947

@tensorrt-cicd
Copy link
Collaborator

PR_Github #32003 [ run ] completed with state SUCCESS. Commit: e1c1947
/LLM/main/L0_MergeRequest_PR pipeline #24795 completed with status: 'FAILURE'

⚠️ 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

@nv-lschneider
Copy link
Collaborator Author

Only failing test was on SBSA: GB200-4_GPUs-PyTorch-PerfSanity-2/perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_grace_blackwell-r1_fp4_v2_tep4_mtp3_8k1k]
which is unrelated to this unwaiving. Continue to rerun for results.

@nv-lschneider
Copy link
Collaborator Author

/bot run --disable-fail-fast --add-multi-gpu-test

@tensorrt-cicd
Copy link
Collaborator

PR_Github #32015 [ run ] triggered by Bot. Commit: e1c1947

@tensorrt-cicd
Copy link
Collaborator

PR_Github #32015 [ run ] completed with state SUCCESS. Commit: e1c1947
/LLM/main/L0_MergeRequest_PR pipeline #24805 completed with status: 'FAILURE'

⚠️ 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

@nv-lschneider
Copy link
Collaborator Author

PR_Github #32015 [ run ] completed with state SUCCESS. Commit: e1c1947 /LLM/main/L0_MergeRequest_PR pipeline #24805 completed with status: 'FAILURE'

⚠️ 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

failure in node setup. retrying.

@nv-lschneider
Copy link
Collaborator Author

/bot run --disable-fail-fast --add-multi-gpu-test

@tensorrt-cicd
Copy link
Collaborator

PR_Github #32023 [ run ] triggered by Bot. Commit: e1c1947

@tensorrt-cicd
Copy link
Collaborator

PR_Github #32023 [ run ] completed with state SUCCESS. Commit: e1c1947
/LLM/main/L0_MergeRequest_PR pipeline #24815 completed with status: 'SUCCESS'

@nv-lschneider
Copy link
Collaborator Author

These 2 tests can be re-enabled since the failures were caused by inadequate tear down of NCCL_SYMMETRIC.
This has been fixed previously by #10166.

The tests have been tried locally, and now they have been run here successfully.

@Tabrizian Tabrizian merged commit e12a711 into NVIDIA:main Jan 15, 2026
7 checks passed
greg-kwasniewski1 pushed a commit to nv-auto-deploy/TensorRT-LLM that referenced this pull request Jan 15, 2026
@nv-lschneider nv-lschneider deleted the lschneider/unwaive-hanging-test branch January 15, 2026 13:53
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