[https://nvbugs/5629136][fix] OOM has been fixed and enable test case #9606

HuiGao-NV · 2025-12-02T01:47:31Z

OOM has been fixed by previous buffer sharing PRs

Summary by CodeRabbit

Tests
- Updated test entry organization with no functional impact.

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

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
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.

coderabbitai · 2025-12-02T01:49:27Z

📝 Walkthrough

Walkthrough

A single test entry in the waive list was moved or rewritten with identical content. No functional changes or impact to control flow, error handling, or APIs.

Changes

Cohort / File(s)	Summary
Test waive list entry reorder `tests/integration/test_lists/waives.txt`	Test entry for TestDeepSeekR1::test_nvfp4_multi_gpus[throughput_mtp] deleted and re-added with identical content

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is incomplete and fails to provide the required information according to the template structure.	Provide a formatted PR title following the template, add a detailed description of the changes, list relevant test coverage, and complete all checklist items appropriately.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Title check	✅ Passed	The title references fixing an OOM issue and enabling a test case, which aligns with the changeset that re-enables a previously disabled test entry. However, the title is somewhat unclear about what 'OOM has been fixed' means in context without additional background.

✨ 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.}

HuiGao-NV · 2025-12-02T01:50:40Z

/bot run --only-multi-gpu-test --gpu-type "B200,GB200"

tensorrt-cicd · 2025-12-02T01:56:48Z

PR_Github #26498 [ run ] triggered by Bot. Commit: a02d961

tensorrt-cicd · 2025-12-02T02:51:51Z

PR_Github #26498 [ run ] completed with state SUCCESS. Commit: a02d961
/LLM/main/L0_MergeRequest_PR pipeline #20147 (Partly Tested) completed with status: 'FAILURE'

HuiGao-NV · 2025-12-02T02:56:03Z

/bot run --only-multi-gpu-test --gpu-type "GB200"

tensorrt-cicd · 2025-12-02T03:01:48Z

PR_Github #26507 [ run ] triggered by Bot. Commit: aacfd7a

tensorrt-cicd · 2025-12-02T05:39:15Z

PR_Github #26507 [ run ] completed with state SUCCESS. Commit: aacfd7a
/LLM/main/L0_MergeRequest_PR pipeline #20154 (Partly Tested) completed with status: 'SUCCESS'

HuiGao-NV · 2025-12-02T05:54:16Z

/bot skip --comment "enable one case and it passed in previous CI test"

tensorrt-cicd · 2025-12-02T06:02:53Z

PR_Github #26530 [ skip ] triggered by Bot. Commit: aacfd7a

HuiGao-NV · 2025-12-02T06:03:18Z

/bot run --post-merge --only-multi-gpu-test --gpu-type "GB200"

tensorrt-cicd · 2025-12-02T06:09:06Z

PR_Github #26532 [ run ] triggered by Bot. Commit: aacfd7a

tensorrt-cicd · 2025-12-02T06:09:07Z

PR_Github #26530 [ skip ] completed with state ABORTED. Commit: aacfd7a

tensorrt-cicd · 2025-12-02T07:02:09Z

PR_Github #26532 [ run ] completed with state SUCCESS. Commit: aacfd7a
/LLM/main/L0_MergeRequest_PR pipeline #20174 (Partly Tested) completed with status: 'FAILURE'

HuiGao-NV · 2025-12-02T11:55:25Z

/bot run --only-multi-gpu-test --gpu-type "GB200"

tensorrt-cicd · 2025-12-02T12:01:35Z

PR_Github #26608 [ run ] triggered by Bot. Commit: 31a7368

tensorrt-cicd · 2025-12-02T12:33:01Z

PR_Github #26608 [ run ] completed with state FAILURE. Commit: 31a7368
/LLM/main/L0_MergeRequest_PR pipeline #20235 (Partly Tested) completed with status: 'FAILURE'

HuiGao-NV · 2025-12-02T12:45:28Z

/bot run --only-multi-gpu-test --gpu-type "GB200"

tensorrt-cicd · 2025-12-02T12:51:36Z

PR_Github #26616 [ run ] triggered by Bot. Commit: 2e7ffdd

tensorrt-cicd · 2025-12-02T13:15:05Z

PR_Github #26616 [ run ] completed with state FAILURE. Commit: 2e7ffdd
/LLM/main/L0_MergeRequest_PR pipeline #20242 (Partly Tested) completed with status: 'FAILURE'

HuiGao-NV · 2025-12-02T14:21:51Z

/bot run --only-multi-gpu-test --gpu-type "GB200" --disable-fail-fast

tensorrt-cicd · 2025-12-02T14:27:21Z

PR_Github #26628 [ run ] triggered by Bot. Commit: 2e7ffdd

tensorrt-cicd · 2025-12-26T06:47:05Z

PR_Github #29995 [ run ] completed with state ABORTED. Commit: 9fb02ce
LLM/main/L0_MergeRequest_PR #23076 (Blue Ocean) completed with status: ABORTED

HuiGao-NV · 2025-12-26T07:27:01Z

/bot run --only-multi-gpu-test --disable-fail-fast --gpu-type "GB200"

tensorrt-cicd · 2025-12-26T07:32:59Z

PR_Github #29997 [ run ] triggered by Bot. Commit: ac8e0a6

HuiGao-NV · 2025-12-26T09:55:40Z

/bot run --only-multi-gpu-test --disable-fail-fast --gpu-type "GB200"

tensorrt-cicd · 2025-12-26T10:01:42Z

PR_Github #30004 [ run ] triggered by Bot. Commit: 1f878e2

tensorrt-cicd · 2025-12-26T10:01:47Z

PR_Github #29997 [ run ] completed with state ABORTED. Commit: ac8e0a6
LLM/main/L0_MergeRequest_PR #23078 (Blue Ocean) completed with status: ABORTED

tensorrt-cicd · 2025-12-26T12:48:44Z

PR_Github #30004 [ run ] completed with state SUCCESS. Commit: 1f878e2
/LLM/main/L0_MergeRequest_PR pipeline #23082 (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

HuiGao-NV · 2025-12-27T01:09:28Z

/bot run --only-multi-gpu-test --disable-fail-fast --gpu-type "GB200"

tensorrt-cicd · 2025-12-27T01:24:05Z

PR_Github #30010 [ run ] triggered by Bot. Commit: 64fd723

tensorrt-cicd · 2025-12-27T04:11:30Z

PR_Github #30010 [ run ] completed with state SUCCESS. Commit: 64fd723
/LLM/main/L0_MergeRequest_PR pipeline #23088 (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

HuiGao-NV · 2025-12-27T06:16:52Z

/bot run --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-1,GB200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2025-12-27T06:22:24Z

PR_Github #30014 [ run ] triggered by Bot. Commit: 8d22579

tensorrt-cicd · 2025-12-27T06:44:49Z

PR_Github #30014 [ run ] completed with state FAILURE. Commit: 8d22579
/LLM/main/L0_MergeRequest_PR pipeline #23092 (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

Signed-off-by: Hui Gao <[email protected]>

HuiGao-NV · 2025-12-27T08:04:31Z

/bot run --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-1,GB200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2025-12-27T08:10:13Z

PR_Github #30017 [ run ] triggered by Bot. Commit: dae03f9

tensorrt-cicd · 2025-12-27T08:43:13Z

PR_Github #30017 [ run ] completed with state FAILURE. Commit: dae03f9
/LLM/main/L0_MergeRequest_PR pipeline #23095 (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

HuiGao-NV · 2025-12-27T11:07:10Z

/bot run --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-1,GB200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2025-12-27T11:12:41Z

PR_Github #30020 [ run ] triggered by Bot. Commit: 617296a

tensorrt-cicd · 2025-12-27T11:46:59Z

PR_Github #30020 [ run ] completed with state FAILURE. Commit: 617296a
/LLM/main/L0_MergeRequest_PR pipeline #23098 (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

HuiGao-NV · 2025-12-27T14:04:37Z

/bot run --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-1,GB200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2025-12-27T14:10:32Z

PR_Github #30024 [ run ] triggered by Bot. Commit: 617296a

tensorrt-cicd · 2025-12-27T14:44:47Z

PR_Github #30024 [ run ] completed with state FAILURE. Commit: 617296a
/LLM/main/L0_MergeRequest_PR pipeline #23102 (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

HuiGao-NV · 2025-12-27T23:34:03Z

/bot run --stage-list "GB200-8_GPUs-2_Nodes-PyTorch-1,GB200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2025-12-27T23:39:41Z

PR_Github #30039 [ run ] triggered by Bot. Commit: 617296a

tensorrt-cicd · 2025-12-28T00:15:48Z

PR_Github #30039 [ run ] completed with state FAILURE. Commit: 617296a
/LLM/main/L0_MergeRequest_PR pipeline #23116 (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

HuiGao-NV changed the title ~~[https://nvbugs/5629136] OOM has been fixed, enable case~~ [https://nvbugs/5629136][fix] OOM has been fixed and enable test case Dec 2, 2025

HuiGao-NV marked this pull request as draft December 2, 2025 02:30

HuiGao-NV force-pushed the enable_oom_case branch from a02d961 to aacfd7a Compare December 2, 2025 02:51

HuiGao-NV marked this pull request as ready for review December 2, 2025 05:03

HuiGao-NV requested review from EmmaQiaoCh and tongyuantongyu December 2, 2025 06:05

HuiGao-NV force-pushed the enable_oom_case branch 2 times, most recently from c280de9 to 31a7368 Compare December 2, 2025 11:55

HuiGao-NV force-pushed the enable_oom_case branch from 31a7368 to 2e7ffdd Compare December 2, 2025 12:45

HuiGao-NV force-pushed the enable_oom_case branch from e1dd65c to ac8e0a6 Compare December 26, 2025 07:25

HuiGao-NV force-pushed the enable_oom_case branch from 1f878e2 to 64fd723 Compare December 27, 2025 01:08

[CI][chore] Print device memory information for each case

dae03f9

Signed-off-by: Hui Gao <[email protected]>

HuiGao-NV force-pushed the enable_oom_case branch from 8d22579 to dae03f9 Compare December 27, 2025 08:04

Log more info

617296a

[https://nvbugs/5629136][fix] OOM has been fixed and enable test case #9606

Are you sure you want to change the base?

[https://nvbugs/5629136][fix] OOM has been fixed and enable test case #9606

Uh oh!

Conversation

HuiGao-NV commented Dec 2, 2025 • edited 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 Dec 2, 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!

HuiGao-NV commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

HuiGao-NV commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

HuiGao-NV commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

HuiGao-NV commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

HuiGao-NV commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

HuiGao-NV commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

HuiGao-NV commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 2, 2025

Uh oh!

tensorrt-cicd commented Dec 26, 2025

Uh oh!

HuiGao-NV commented Dec 26, 2025

Uh oh!

tensorrt-cicd commented Dec 26, 2025

Uh oh!

HuiGao-NV commented Dec 26, 2025

Uh oh!

tensorrt-cicd commented Dec 26, 2025

Uh oh!

tensorrt-cicd commented Dec 26, 2025

Uh oh!

tensorrt-cicd commented Dec 26, 2025

Uh oh!

HuiGao-NV commented Dec 27, 2025

Uh oh!

tensorrt-cicd commented Dec 27, 2025

HuiGao-NV commented Dec 2, 2025 •

edited

Loading

coderabbitai bot commented Dec 2, 2025 •

edited

Loading