[None][infra] Let CI continue running other isolation tests when an isolation test get hanging #8471

EmmaQiaoCh · 2025-10-18T07:02:23Z

Summary by CodeRabbit

Tests
- Adjusted test execution timeout configuration for platform test runs.
- Modified test scenarios with intentional delays and failure conditions for debugging purposes.

Note: These changes are internal test infrastructure modifications with no direct impact on end-user functionality.

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)
Any new dependencies have been scanned for license and vulnerabilities
CODEOWNERS updated if ownership changes
Documentation updated as needed
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.

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.

coderabbitai · 2025-10-18T07:05:38Z

📝 Walkthrough

Walkthrough

Pytest timeout reduced from 3600 to 500 seconds in CI pipeline. Test file modified with intentional failure and 6-minute delay for debugging purposes.

Changes

Cohort / File(s)	Summary
CI Timeout Configuration `jenkins/L0_Test.groovy`	Reduced pytestTestTimeout from 3600 to 500 seconds in Run Pytest stage, shortening maximum allowed duration for pytest runs.
Test Debugging Modifications `tests/integration/defs/triton_server/test_triton.py`	Added `import time`. Inserted `pytest.fail("emma test for hang")` in `test_gpt_2b_ib_lora` causing intentional failure. Added `time.sleep(6 * 60)` delay in `test_llava` prior to build_and_run sequence.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings, 1 inconclusive)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.
Description Check	⚠️ Warning	The PR description is largely incomplete and fails to provide substantive information about the changes. The author left the required "Description" and "Test Coverage" sections entirely blank, containing only the template placeholder text. While the PR checklist checkbox at the end is marked as checked, no details are provided explaining the issue being addressed, the solution implemented, or which tests validate the changes, which are all critical information for reviewers.	The author should fill in the Description section to explain what isolation test hang issue exists and how the changes address it, then populate the Test Coverage section to list which tests verify the fix. Additionally, the author should provide context for why the timeout was reduced, why intentional test failures and delays were added, and whether this PR is intended for production or is exploratory work. This information is essential for reviewers to understand and evaluate the PR.
Title Check	❓ Inconclusive	The PR title claims the objective is to "let CI continue running other isolation tests when an isolation test get hanging." The changeset includes a timeout reduction from 3600 to 500 seconds that could theoretically address hanging tests, which relates to the stated objective. However, the actual changes also include an intentional test failure in `test_gpt_2b_ib_lora` and a deliberate 6-minute delay in `test_llava`, which appear to be debugging or test reproduction code rather than a production fix. This raises ambiguity about whether the PR implements a complete solution to the stated problem or if it is work-in-progress code, making it unclear if the title accurately reflects the changeset's purpose and readiness.	Clarify whether the intentional test failures and delays are temporary debugging code that should be removed before merging, or if they are part of the intended fix. Provide additional context in the PR description about how the timeout reduction and test modifications together solve the hanging test issue, ensuring the title accurately reflects the actual implementation approach and that the code is production-ready.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

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.}

coderabbitai

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 (2)

tests/integration/defs/triton_server/test_triton.py (2)
237-245: Critical: Remove intentional test failure before merging.

This pytest.fail("emma test for hang") will cause the test to always fail and prevents the actual test logic from executing. This appears to be temporary debug code for investigating hang issues and must be removed before merging to main.

Apply this diff to remove the debug code:
 @pytest.mark.parametrize("test_name", ["gpt-2b-ib-lora"], indirect=True)
 def test_gpt_2b_ib_lora(tritonserver_test_root, test_name, llm_root, model_path,
                         engine_dir):
-    pytest.fail("emma test for hang")
     build_model(test_name, llm_root, tritonserver_test_root)
     tokenizer_type = "auto"
     run_shell_command(
407-416: Critical: Remove 6-minute debug delay before merging.

The time.sleep(6 * 60) introduces a 6-minute delay that will significantly slow down the CI pipeline. With the pytest timeout reduced to 500 seconds (8.3 minutes) in the related Groovy change, this sleep consumes 72% of the available timeout window. This appears to be temporary debug code for testing timeout behavior and must be removed before merging.

Apply this diff to remove the debug delay:
 @pytest.mark.parametrize("test_name", ["llava"], indirect=True)
 def test_llava(tritonserver_test_root, test_name, llm_root, model_path,
                engine_dir):
-    time.sleep(6 * 60)
     build_model(test_name, llm_root, tritonserver_test_root)
     tokenizer_type = "auto"
     visual_encoder_path = f"{llm_root}/examples/models/core/multimodal/tmp/trt_engines/llava-1.5-7b-hf/multimodal_encoder/"

📜 Review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between 4a8ac8d and 7ed32d0.

📒 Files selected for processing (2)

jenkins/L0_Test.groovy (1 hunks)
tests/integration/defs/triton_server/test_triton.py (3 hunks)

🧰 Additional context used

📓 Path-based instructions (3)

**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Use only spaces, no tabs; indent with 4 spaces.

Files:

tests/integration/defs/triton_server/test_triton.py

**/*.py

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.

Files:

tests/integration/defs/triton_server/test_triton.py

**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}

📄 CodeRabbit inference engine (CODING_GUIDELINES.md)

Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).

Files:

tests/integration/defs/triton_server/test_triton.py

⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)

GitHub Check: Pre-commit Check

🔇 Additional comments (1)

jenkins/L0_Test.groovy (1)

1997-1997: Clarify whether 500-second timeout reduction is correct for this stage or requires verification.

The verification confirms the 6-minute sleep exists in test_llava but contradicts the review comment's assumption that it's a debug change—the sleep is not marked as temporary or debug anywhere in the code. However, the codebase shows two different pytestTestTimeout values in the same file: 7200 seconds at line 767 and 500 seconds at line 1997, indicating different stages have intentionally different timeouts.

The 500-second timeout leaves only ~140 seconds for test logic after the 360-second sleep, which may be intentional for this specific stage. Without understanding the purpose of this particular stage or seeing the full diff context, it's unclear whether this value is correct or needs adjustment.

tests/integration/defs/triton_server/test_triton.py

EmmaQiaoCh · 2025-10-18T07:05:44Z

/bot run --stage-list "B200_PCIe-Triton-Post-Merge-1"

tensorrt-cicd · 2025-10-18T07:11:01Z

PR_Github #21754 [ run ] triggered by Bot. Commit: 7ed32d0

tensorrt-cicd · 2025-10-18T07:58:39Z

PR_Github #21754 [ run ] completed with state SUCCESS. Commit: 7ed32d0
/LLM/main/L0_MergeRequest_PR pipeline #16394 (Partly Tested) completed with status: 'FAILURE'

EmmaQiaoCh · 2025-10-18T08:39:47Z

/bot run --stage-list "B200_PCIe-Triton-Post-Merge-1"

tensorrt-cicd · 2025-10-18T08:45:54Z

PR_Github #21757 [ run ] triggered by Bot. Commit: ca6d5c8

tensorrt-cicd · 2025-10-18T09:38:26Z

PR_Github #21757 [ run ] completed with state SUCCESS. Commit: ca6d5c8
/LLM/main/L0_MergeRequest_PR pipeline #16396 (Partly Tested) completed with status: 'FAILURE'

EmmaQiaoCh · 2025-10-18T11:30:30Z

/bot run --stage-list "B200_PCIe-Triton-Post-Merge-1"

tensorrt-cicd · 2025-10-18T11:36:09Z

PR_Github #21762 [ run ] triggered by Bot. Commit: 043b7b0

tensorrt-cicd · 2025-10-18T12:27:43Z

PR_Github #21762 [ run ] completed with state SUCCESS. Commit: 043b7b0
/LLM/main/L0_MergeRequest_PR pipeline #16401 (Partly Tested) completed with status: 'FAILURE'

EmmaQiaoCh · 2025-10-18T14:39:36Z

/bot run --stage-list "B200_PCIe-Triton-Post-Merge-1"

tensorrt-cicd · 2025-10-18T14:45:11Z

PR_Github #21765 [ run ] triggered by Bot. Commit: 14a7af6

tensorrt-cicd · 2025-10-18T15:37:54Z

PR_Github #21765 [ run ] completed with state SUCCESS. Commit: 14a7af6
/LLM/main/L0_MergeRequest_PR pipeline #16404 (Partly Tested) completed with status: 'FAILURE'

jenkins/L0_Test.groovy

EmmaQiaoCh · 2025-10-20T06:40:30Z

/bot run --stage-list "[DGX_H100-4_GPUs-CPP-1]"

EmmaQiaoCh · 2025-10-20T06:40:52Z

/bot run --stage-list "DGX_H100-4_GPUs-CPP-1"

tensorrt-cicd · 2025-10-20T06:46:12Z

PR_Github #21870 [ run ] triggered by Bot. Commit: 215fe32

tensorrt-cicd · 2025-10-20T06:46:14Z

PR_Github #21871 [ ] completed with state ABORTED. Commit: 215fe32

tensorrt-cicd · 2025-10-20T07:31:14Z

PR_Github #21870 [ run ] completed with state FAILURE. Commit: 215fe32
/LLM/main/L0_MergeRequest_PR pipeline #16487 (Partly Tested) completed with status: 'FAILURE'

EmmaQiaoCh · 2025-10-20T07:36:57Z

/bot run --stage-list "DGX_H100-4_GPUs-CPP-1"

EmmaQiaoCh · 2025-10-20T07:45:55Z

/bot run --stage-list "DGX_H100-4_GPUs-CPP-1"

tensorrt-cicd · 2025-10-20T07:58:34Z

PR_Github #21873 [ run ] triggered by Bot. Commit: 215fe32

Signed-off-by: qqiao <[email protected]>

Co-authored-by: Yanchao Lu <[email protected]> Signed-off-by: Emma Qiao <[email protected]>

Signed-off-by: qqiao <[email protected]>

EmmaQiaoCh · 2025-10-20T14:08:21Z

/bot run

tensorrt-cicd · 2025-10-20T14:13:50Z

PR_Github #21921 [ run ] triggered by Bot. Commit: a56d7f6

tensorrt-cicd · 2025-10-20T14:36:13Z

PR_Github #21921 [ run ] completed with state FAILURE. Commit: a56d7f6
/LLM/main/L0_MergeRequest_PR pipeline #16525 completed with status: 'FAILURE'

HuiGao-NV

LGTM

Signed-off-by: Emma Qiao <[email protected]>

EmmaQiaoCh · 2025-10-21T02:10:02Z

/bot run --stage-list "DGX_H100-4_GPUs-CPP-1"

tensorrt-cicd · 2025-10-21T02:15:56Z

PR_Github #21981 [ run ] triggered by Bot. Commit: 9e1ae4b

tensorrt-cicd · 2025-10-21T05:47:40Z

PR_Github #21981 [ run ] completed with state SUCCESS. Commit: 9e1ae4b
/LLM/main/L0_MergeRequest_PR pipeline #16574 (Partly Tested) completed with status: 'SUCCESS'

EmmaQiaoCh · 2025-10-21T06:30:02Z

/bot run

tensorrt-cicd · 2025-10-21T06:35:26Z

PR_Github #22013 [ run ] triggered by Bot. Commit: 9e1ae4b

tensorrt-cicd · 2025-10-21T08:42:19Z

PR_Github #22013 [ run ] completed with state SUCCESS. Commit: 9e1ae4b
/LLM/main/L0_MergeRequest_PR pipeline #16596 completed with status: 'FAILURE'

EmmaQiaoCh · 2025-10-21T09:53:59Z

/bot run

tensorrt-cicd · 2025-10-21T09:59:06Z

PR_Github #22044 [ run ] triggered by Bot. Commit: 9e1ae4b

tensorrt-cicd · 2025-10-22T04:07:20Z

PR_Github #22044 [ run ] completed with state SUCCESS. Commit: 9e1ae4b
/LLM/main/L0_MergeRequest_PR pipeline #16621 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

…solation test get hanging (NVIDIA#8471) Signed-off-by: qqiao <[email protected]> Signed-off-by: Emma Qiao <[email protected]> Co-authored-by: Yanchao Lu <[email protected]> Signed-off-by: yufeiwu-nv <[email protected]>

…solation test get hanging (NVIDIA#8471) Signed-off-by: qqiao <[email protected]> Signed-off-by: Emma Qiao <[email protected]> Co-authored-by: Yanchao Lu <[email protected]>

EmmaQiaoCh requested review from a team as code owners October 18, 2025 07:02

EmmaQiaoCh requested review from niukuo and zeroepoch October 18, 2025 07:02

EmmaQiaoCh changed the title ~~[None][Infra] Fix isolation test hang, let ci continue run other isolation tests~~ [None][infra] Fix isolation test hang, let ci continue run other isolation tests Oct 18, 2025

coderabbitai bot reviewed Oct 18, 2025

View reviewed changes

tests/integration/defs/triton_server/test_triton.py Outdated Show resolved Hide resolved

zeroepoch approved these changes Oct 19, 2025

View reviewed changes

chzblych changed the title ~~[None][infra] Fix isolation test hang, let ci continue run other isolation tests~~ [None][infra] Let CI continue running other isolation tests when an isolation test get hanging Oct 19, 2025

chzblych reviewed Oct 19, 2025

View reviewed changes

jenkins/L0_Test.groovy Show resolved Hide resolved

jenkins/L0_Test.groovy Show resolved Hide resolved

EmmaQiaoCh and others added 5 commits October 20, 2025 21:08

Test

d9bcd10

Signed-off-by: qqiao <[email protected]>

Move isolation tests under env LD_LIBRARY_PATH changed

3b5ee7d

Signed-off-by: qqiao <[email protected]>

When there are tests can't be rerun, return false for rerunFailedTests

ab82c63

Signed-off-by: qqiao <[email protected]>

Remove the test data

e7cb7e3

Signed-off-by: qqiao <[email protected]>

Update jenkins/L0_Test.groovy

874ea8c

Co-authored-by: Yanchao Lu <[email protected]> Signed-off-by: Emma Qiao <[email protected]>

EmmaQiaoCh force-pushed the emma/fix_isolation_hang branch from 98e059e to 874ea8c Compare October 20, 2025 13:08

Add back the isolation marker

a56d7f6

Signed-off-by: qqiao <[email protected]>

EmmaQiaoCh requested a review from HuiGao-NV October 20, 2025 14:09

HuiGao-NV approved these changes Oct 21, 2025

View reviewed changes

Merge branch 'main' into emma/fix_isolation_hang

9e1ae4b

Signed-off-by: Emma Qiao <[email protected]>

yiqingy0 approved these changes Oct 21, 2025

View reviewed changes

EmmaQiaoCh enabled auto-merge (squash) October 21, 2025 13:41

EmmaQiaoCh merged commit 2b4e812 into NVIDIA:main Oct 22, 2025
5 checks passed

[None][infra] Let CI continue running other isolation tests when an isolation test get hanging #8471

[None][infra] Let CI continue running other isolation tests when an isolation test get hanging #8471

Uh oh!

Conversation

EmmaQiaoCh commented Oct 18, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

coderabbitai bot commented Oct 18, 2025 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

coderabbitai bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

EmmaQiaoCh commented Oct 18, 2025

Uh oh!

tensorrt-cicd commented Oct 18, 2025

Uh oh!

tensorrt-cicd commented Oct 18, 2025

Uh oh!

EmmaQiaoCh commented Oct 18, 2025

Uh oh!

tensorrt-cicd commented Oct 18, 2025

Uh oh!

tensorrt-cicd commented Oct 18, 2025

Uh oh!

EmmaQiaoCh commented Oct 18, 2025

Uh oh!

tensorrt-cicd commented Oct 18, 2025

Uh oh!

tensorrt-cicd commented Oct 18, 2025

Uh oh!

EmmaQiaoCh commented Oct 18, 2025

Uh oh!

tensorrt-cicd commented Oct 18, 2025

Uh oh!

tensorrt-cicd commented Oct 18, 2025

Uh oh!

Uh oh!

Uh oh!

EmmaQiaoCh commented Oct 20, 2025

Uh oh!

EmmaQiaoCh commented Oct 20, 2025

Uh oh!

tensorrt-cicd commented Oct 20, 2025

Uh oh!

tensorrt-cicd commented Oct 20, 2025

Uh oh!

tensorrt-cicd commented Oct 20, 2025

Uh oh!

EmmaQiaoCh commented Oct 20, 2025

Uh oh!

EmmaQiaoCh commented Oct 20, 2025

Uh oh!

tensorrt-cicd commented Oct 20, 2025

Uh oh!

EmmaQiaoCh commented Oct 20, 2025

Uh oh!

tensorrt-cicd commented Oct 20, 2025

Uh oh!

tensorrt-cicd commented Oct 20, 2025

Uh oh!

HuiGao-NV left a comment • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Choose a reason for hiding this comment

Uh oh!

EmmaQiaoCh commented Oct 21, 2025

Uh oh!

EmmaQiaoCh commented Oct 18, 2025 •

edited by coderabbitai bot

Loading

coderabbitai bot commented Oct 18, 2025 •

edited

Loading

HuiGao-NV left a comment •

edited

Loading