Skip to content

Conversation

@HuiGao-NV
Copy link
Collaborator

@HuiGao-NV HuiGao-NV commented Oct 20, 2025

Summary by CodeRabbit

  • Tests
    • Adjusted test execution configurations to remove isolation constraints from cache transceiver tests and re-enable previously skipped test cases.

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.

Copy link
Collaborator

@Superjomn Superjomn left a comment

Choose a reason for hiding this comment

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

LGTM

@Superjomn
Copy link
Collaborator

Disable temporarily, will restore once the ISOLATION bug is fixed.

@Superjomn Superjomn enabled auto-merge (squash) October 20, 2025 06:17
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Oct 20, 2025

📝 Walkthrough

Walkthrough

Test execution configuration is modified across three files to remove ISOLATION qualifiers from four test entries and remove SKIP entries for two cpp/test_multi_gpu.py tests, enabling them to execute as standard tests rather than isolated or skipped tests.

Changes

Cohort / File(s) Summary
ISOLATION qualifier removals
tests/integration/test_lists/test-db/l0_dgx_h100.yml, tests/integration/test_lists/test-db/l0_l40s.yml
Removed ISOLATION qualifiers from four test entries: three cpp/test_multi_gpu.py test variants and one examples/test_llm_api_with_mpi.py test, converting them from isolated execution to standard execution mode
SKIP entry removals
tests/integration/test_lists/waives.txt
Removed two SKIP entries for cpp/test_multi_gpu.py::test_cache_transceiver variants (8proc-nixl_kvcache-90 and 2proc-ucx_kvcache-90), enabling these tests to execute when previously waived

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Description Check ⚠️ Warning The PR description provided consists entirely of the template structure with placeholder comments and no actual content filled in by the author. The critical sections required by the template—Description, Test Coverage, and PR Checklist items—are unfilled and contain only HTML comment placeholders with guidance text. The description does not explain what the issue is, why these changes are needed, what tests validate the modifications, or confirmation that the author reviewed the checklist items. This represents a largely incomplete description that fails to meet the documentation requirements. The author must fill in the PR description with specific content addressing each required section: provide a brief explanation of the issue and solution in the Description section, list the relevant tests that validate these changes in the Test Coverage section, and confirm completion of the applicable PR Checklist items. This will ensure reviewers understand the motivation and impact of removing the ISOLATION qualifiers and skip entries, and can verify appropriate test coverage exists for these test configuration changes.
✅ Passed checks (2 passed)
Check name Status Explanation
Title Check ✅ Passed The PR title "[https://nvbugs/5492250][fix] Remove isolated cases and unwaive cases" follows the required template format with a valid NVBugs ID and type descriptor. The title is specific and concise, clearly indicating the two main changes: removing ISOLATION qualifiers from test entries across multiple YAML files and removing skip entries from the waives file. This directly corresponds to the actual changes in the raw summary, making it a precise and informative title that would help teammates quickly understand the nature of these test configuration modifications.
Docstring Coverage ✅ Passed No functions found in the changes. Docstring coverage check skipped.
✨ Finishing touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Post copyable unit tests in a comment

📜 Recent 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 d05079b and 7aaf856.

📒 Files selected for processing (3)
  • tests/integration/test_lists/test-db/l0_dgx_h100.yml (1 hunks)
  • tests/integration/test_lists/test-db/l0_l40s.yml (1 hunks)
  • tests/integration/test_lists/waives.txt (0 hunks)
💤 Files with no reviewable changes (1)
  • tests/integration/test_lists/waives.txt
⏰ 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 (3)
tests/integration/test_lists/test-db/l0_l40s.yml (1)

68-68: Verify that MPI test is safe to run without isolation.

Removing ISOLATION from an MPI-based test requires confirmation that process spawning and cleanup don't interfere with parallel test execution. This change lacks justification in the PR description.

Please confirm:

  1. This test passes reliably when run in parallel with other tests in recent CI runs
  2. The test code has no process-level side effects or resource cleanup that requires isolation
tests/integration/test_lists/test-db/l0_dgx_h100.yml (2)

1-248: Missing file: waives.txt

The AI summary references changes to tests/integration/test_lists/waives.txt where SKIP entries for two cpp/test_multi_gpu.py::test_cache_transceiver tests were removed. This file is not provided for review, making it impossible to assess the complete scope of the PR changes.

Please include tests/integration/test_lists/waives.txt in the review so we can verify:

  1. Which specific SKIP entries were removed
  2. Whether the removals are consistent with the ISOLATION qualifier removals in the YAML files
  3. Any potential impact on test flakiness or timeout issues

192-194: ****

The review comment is based on an incorrect premise. The actual changes made were:

  1. What actually changed: Two test entries were removed from tests/integration/test_lists/waives.txt (lines with SKIP), not from l0_dgx_h100.yml. This "unwaives" the tests—allowing them to run again.

  2. The misidentification: The review claims "ISOLATION qualifiers were removed" from l0_dgx_h100.yml lines 192-194. However:

    • l0_dgx_h100.yml was not modified in this commit
    • The file contains no ISOLATION qualifiers anywhere
    • The three test entries at lines 192-194 never had isolation markers
  3. What's actually happening: Two of the three test variants were previously skipped (in waives.txt); this PR enables them. The third variant was already running.

If there are legitimate concerns about parallel safety for these multi-GPU cache tests, those concerns are valid but should be reframed based on the actual change (unwaiving previously skipped tests) rather than the incorrect claim about removing ISOLATION qualifiers.

Likely an incorrect or invalid review 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
Copy link
Collaborator Author

/bot run --only-multi-gpu-test --stage-list "DGX_H100-4_GPUs-CPP-1"

@HuiGao-NV HuiGao-NV disabled auto-merge October 20, 2025 06:25
@tensorrt-cicd
Copy link
Collaborator

PR_Github #21867 [ run ] triggered by Bot. Commit: 7aaf856

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21867 [ run ] completed with state SUCCESS. Commit: 7aaf856
/LLM/main/L0_MergeRequest_PR pipeline #16485 (Partly Tested) completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

@HuiGao-NV HuiGao-NV enabled auto-merge (squash) October 20, 2025 11:05
@HuiGao-NV
Copy link
Collaborator Author

/bot skip --comment "unwaived test cases succeed"

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21911 [ skip ] triggered by Bot. Commit: 7aaf856

@tensorrt-cicd
Copy link
Collaborator

PR_Github #21911 [ skip ] completed with state SUCCESS. Commit: 7aaf856
Skipping testing for commit 7aaf856

@HuiGao-NV HuiGao-NV merged commit d0663e1 into NVIDIA:main Oct 20, 2025
7 of 9 checks passed
@HuiGao-NV HuiGao-NV deleted the remove_isolated branch October 27, 2025 14:31
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.

4 participants