[https://nvbugs/6215678][fix] Point `--output-artifact-dir` at a unique per-run subdir `{model}-openai-complet by tensorrt-cicd · Pull Request #14742 · NVIDIA/TensorRT-LLM

tensorrt-cicd · 2026-05-29T08:45:17Z

Summary

Root cause: aiperf was given a single shared --output-artifact-dir, so each concurrency run overwrote the prior export and no <model>-openai-completions-<...> subdir existed for the directory-name parser to match.
Fix: Point --output-artifact-dir at a unique per-run subdir {model}-openai-completions-concurrency{N}, gitignore the test-generated artifacts dir, and remove the obsolete nvbugs/6215678 waivers.
Automated fix generated by repair-bot

Test plan

Verify fix on the same GPU type as the original failure
Check for regressions in related tests

Links

Bug: https://nvbugs/6215678

Summary by CodeRabbit

Tests
- Reorganized stress test artifact storage by model and concurrency parameters
- Removed outdated test waivers for stress tests
Chores
- Updated version control to exclude stress test output artifacts

coderabbitai · 2026-05-29T08:48:25Z

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: d218fc94-fc3b-49af-9fd3-c7526bfab8f3

📥 Commits

Reviewing files that changed from the base of the PR and between b1dfd30 and d943fc4.

📒 Files selected for processing (3)

.gitignore
tests/integration/defs/stress_test/stress_test.py
tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

tests/integration/test_lists/waives.txt

📝 Walkthrough

Walkthrough

This PR reorganizes stress test aiperf artifact output by directing profiles into model-and-concurrency-specific subdirectories rather than a shared directory. The .gitignore is updated to exclude the artifacts folder, and two outdated test waivers are removed to reflect updated test expectations.

Changes

Stress Test Artifact Handling

Layer / File(s)	Summary
Artifact directory structure and cleanup `tests/integration/defs/stress_test/stress_test.py`, `.gitignore`, `tests/integration/test_lists/waives.txt`	The `create_aiperf_command()` function directs aiperf to write artifacts into a model-and-concurrency-specific subdirectory under `ARTIFACTS_DIR`. The `.gitignore` is updated to exclude `tests/integration/defs/stress_test/artifacts/`, and two outdated test waivers for `stress_test/stress_test.py::test_run_stress_test` are removed.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Suggested reviewers

niukuo
mzweilz
litaotju
jieli-matrix

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The PR title clearly identifies the main fix: setting `--output-artifact-dir` to a unique per-run subdirectory, addressing the root cause described in the objectives.
Description check	✅ Passed	The PR description includes a clear summary explaining root cause and fix, a test plan section with verification steps, and relevant bug link, though it lacks explicit sections matching the template structure.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
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.}

dominicshanshan · 2026-06-10T07:53:38Z

/bot command

github-actions · 2026-06-10T07:53:49Z

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) --high-priority]

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. Supports wildcard * for pattern matching (e.g., "*PerfSanity*" matches all stages containing PerfSanity). Examples: "A10-PyTorch-1, xxx", "PerfSanity". 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. Supports wildcard * for pattern matching. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx", --extra-stage "Post-Merge".

--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.

--high-priority (OPTIONAL) : Run the pipeline with high priority. This option is restricted to authorized users only and will route the job to a high-priority queue.

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.

dominicshanshan · 2026-06-10T08:02:12Z

/bot run --stage-list "A10-PyTorch-1, A10-PyTorch-2"

tensorrt-cicd · 2026-06-10T08:07:55Z

PR_Github #53271 [ run ] triggered by Bot. Commit: b9c5f97 Link to invocation

tensorrt-cicd · 2026-06-10T10:17:49Z

PR_Github #53271 [ run ] completed with state SUCCESS. Commit: b9c5f97
/LLM/main/L0_MergeRequest_PR pipeline #42461 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

dominicshanshan · 2026-06-11T01:58:49Z

/bot run --stage-list "A10-PyTorch-Post-Merge-1"

tensorrt-cicd · 2026-06-11T02:04:33Z

PR_Github #53430 [ run ] triggered by Bot. Commit: b9c5f97 Link to invocation

tensorrt-cicd · 2026-06-11T03:01:47Z

PR_Github #53430 [ run ] completed with state SUCCESS. Commit: b9c5f97
/LLM/main/L0_MergeRequest_PR pipeline #42600 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

dominicshanshan · 2026-06-11T03:42:29Z

/bot run

tensorrt-cicd · 2026-06-11T03:48:11Z

PR_Github #53463 [ run ] triggered by Bot. Commit: 70acfe6 Link to invocation

tensorrt-cicd · 2026-06-11T06:24:27Z

PR_Github #53463 [ run ] completed with state FAILURE. Commit: 70acfe6
/LLM/main/L0_MergeRequest_PR pipeline #42627 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

dominicshanshan · 2026-06-15T03:47:36Z

/bot run

tensorrt-cicd · 2026-06-15T03:53:20Z

PR_Github #54209 [ run ] triggered by Bot. Commit: ae6cfe4 Link to invocation

dominicshanshan · 2026-06-15T04:23:29Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-06-15T08:19:31Z

PR_Github #54213 [ run ] completed with state SUCCESS. Commit: e70fb7a
/LLM/main/L0_MergeRequest_PR pipeline #43291 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

dominicshanshan · 2026-06-16T01:46:16Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-06-16T01:52:52Z

PR_Github #54407 [ run ] triggered by Bot. Commit: 4f711fd Link to invocation

tensorrt-cicd · 2026-06-16T04:15:50Z

PR_Github #54407 [ run ] completed with state FAILURE. Commit: 4f711fd
/LLM/main/L0_MergeRequest_PR pipeline #43471 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

Link to invocation

dominicshanshan · 2026-06-16T09:06:45Z

/bot run

tensorrt-cicd · 2026-06-16T09:12:36Z

PR_Github #54556 [ run ] triggered by Bot. Commit: 4f711fd Link to invocation

tensorrt-cicd · 2026-06-16T13:10:57Z

PR_Github #54556 [ run ] completed with state SUCCESS. Commit: 4f711fd
/LLM/main/L0_MergeRequest_PR pipeline #43601 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

Link to invocation

dominicshanshan · 2026-06-17T02:01:53Z

/bot run

tensorrt-cicd · 2026-06-17T02:08:30Z

PR_Github #54704 [ run ] triggered by Bot. Commit: 4f711fd Link to invocation

tensorrt-cicd · 2026-06-17T05:11:01Z

PR_Github #54704 [ run ] completed with state FAILURE. Commit: 4f711fd
/LLM/main/L0_MergeRequest_PR pipeline #43734 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

dominicshanshan · 2026-06-17T06:12:55Z

/bot run

tensorrt-cicd · 2026-06-17T06:18:34Z

PR_Github #54775 [ run ] triggered by Bot. Commit: 4f711fd Link to invocation

tensorrt-cicd · 2026-06-17T07:17:21Z

PR_Github #54775 [ run ] completed with state FAILURE. Commit: 4f711fd
/LLM/main/L0_MergeRequest_PR pipeline #43793 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

dominicshanshan · 2026-06-17T08:50:37Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-06-17T08:56:15Z

PR_Github #54814 [ run ] triggered by Bot. Commit: edae8f4 Link to invocation

tensorrt-cicd · 2026-06-17T12:30:23Z

PR_Github #54814 [ run ] completed with state SUCCESS. Commit: edae8f4
/LLM/main/L0_MergeRequest_PR pipeline #43828 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

…ress test aiperf was given a single shared --output-artifact-dir, so each concurrency run overwrote the previous export and no <model>-openai-completions-<...> subdir existed for extract_stress_test_metrics to parse, raising "No model directories found ...". Point --output-artifact-dir at a unique per-run subdir so every run is preserved and the directory-name parser matches. Gitignore the test-generated artifacts dir and remove the obsolete waivers. Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

dominicshanshan · 2026-06-18T04:12:40Z

/bot run --disable-fail-fast

tensorrt-cicd · 2026-06-18T04:18:44Z

PR_Github #54902 [ run ] triggered by Bot. Commit: 0eb3bb7 Link to invocation

tensorrt-cicd · 2026-06-18T07:49:57Z

PR_Github #54902 [ run ] completed with state SUCCESS. Commit: 0eb3bb7
/LLM/main/L0_MergeRequest_PR pipeline #43906 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

dominicshanshan · 2026-06-19T04:39:36Z

/bot run

tensorrt-cicd · 2026-06-19T04:45:49Z

PR_Github #54958 [ run ] triggered by Bot. Commit: 0eb3bb7 Link to invocation

tensorrt-cicd · 2026-06-19T07:31:53Z

PR_Github #54958 [ run ] completed with state SUCCESS. Commit: 0eb3bb7
/LLM/main/L0_MergeRequest_PR pipeline #43958 completed with status: 'SUCCESS'

CI Report

Link to invocation

…ue per-run subdir `{model}-openai-complet (NVIDIA#14742) Signed-off-by: tensorrt-cicd <90828364+tensorrt-cicd@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com> Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>

tensorrt-cicd requested a review from a team as a code owner May 29, 2026 08:45

tensorrt-cicd assigned dominicshanshan May 29, 2026

github-actions Bot assigned tensorrt-cicd May 29, 2026

tensorrt-cicd force-pushed the repair-bot-bug6215678 branch 7 times, most recently from d5efdbd to b4ade65 Compare June 2, 2026 23:23

jieli-matrix approved these changes Jun 3, 2026

View reviewed changes

tensorrt-cicd force-pushed the repair-bot-bug6215678 branch from b4ade65 to b9c5f97 Compare June 9, 2026 07:28

dominicshanshan force-pushed the repair-bot-bug6215678 branch from b9c5f97 to 70acfe6 Compare June 11, 2026 03:38

tensorrt-cicd force-pushed the repair-bot-bug6215678 branch from 70acfe6 to ae6cfe4 Compare June 11, 2026 10:11

dominicshanshan force-pushed the repair-bot-bug6215678 branch from ae6cfe4 to e70fb7a Compare June 15, 2026 04:16

dominicshanshan force-pushed the repair-bot-bug6215678 branch from e70fb7a to 4f711fd Compare June 16, 2026 01:43

dominicshanshan force-pushed the repair-bot-bug6215678 branch from 4f711fd to edae8f4 Compare June 17, 2026 08:47

tensorrt-cicd added 2 commits June 17, 2026 21:08

[nvbugs/6215678][chore] Remove stale waiver after fix

0eb3bb7

Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>

dominicshanshan force-pushed the repair-bot-bug6215678 branch from edae8f4 to 0eb3bb7 Compare June 18, 2026 04:08

dominicshanshan merged commit 7060827 into NVIDIA:main Jun 19, 2026
7 checks passed

Uh oh!

Conversation

tensorrt-cicd commented May 29, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Test plan

Links

Summary by CodeRabbit

Uh oh!

coderabbitai Bot commented May 29, 2026

Walkthrough

Changes

Estimated code review effort

Suggested reviewers

Uh oh!

dominicshanshan commented Jun 10, 2026

Uh oh!

github-actions Bot commented Jun 10, 2026

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

dominicshanshan commented Jun 10, 2026

Uh oh!

tensorrt-cicd commented Jun 10, 2026

Uh oh!

tensorrt-cicd commented Jun 10, 2026

Uh oh!

dominicshanshan commented Jun 11, 2026

Uh oh!

tensorrt-cicd commented Jun 11, 2026

Uh oh!

tensorrt-cicd commented Jun 11, 2026

Uh oh!

dominicshanshan commented Jun 11, 2026

Uh oh!

tensorrt-cicd commented Jun 11, 2026

Uh oh!

tensorrt-cicd commented Jun 11, 2026

Uh oh!

dominicshanshan commented Jun 15, 2026

Uh oh!

tensorrt-cicd commented Jun 15, 2026

Uh oh!

dominicshanshan commented Jun 15, 2026

Uh oh!

tensorrt-cicd commented Jun 15, 2026

Uh oh!

dominicshanshan commented Jun 16, 2026

Uh oh!

tensorrt-cicd commented Jun 16, 2026

Uh oh!

tensorrt-cicd commented Jun 16, 2026

Uh oh!

dominicshanshan commented Jun 16, 2026

Uh oh!

tensorrt-cicd commented Jun 16, 2026

Uh oh!

tensorrt-cicd commented Jun 16, 2026

Uh oh!

dominicshanshan commented Jun 17, 2026

Uh oh!

tensorrt-cicd commented Jun 17, 2026

Uh oh!

tensorrt-cicd commented Jun 17, 2026

Uh oh!

dominicshanshan commented Jun 17, 2026

Uh oh!

tensorrt-cicd commented Jun 17, 2026

Uh oh!

tensorrt-cicd commented Jun 17, 2026

Uh oh!

dominicshanshan commented Jun 17, 2026

Uh oh!

tensorrt-cicd commented Jun 17, 2026

Uh oh!

tensorrt-cicd commented Jun 17, 2026

Uh oh!

dominicshanshan commented Jun 18, 2026

tensorrt-cicd commented May 29, 2026 •

edited by coderabbitai Bot

Loading