Skip to content

Conversation

@dongxuy04
Copy link
Collaborator

@dongxuy04 dongxuy04 commented Oct 28, 2025

Summary by CodeRabbit

  • Tests
    • Enabled two DeepSeekV3Lite model tests that were previously excluded (bfloat16_4gpus and nvfp4_4gpus configurations).
    • Enhanced Docker test container configuration to expose additional device capabilities for LLM testing scenarios.

Description

  • Enable GDRCopy on dlcluster
  • Unwaive online eplb

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.

@dongxuy04
Copy link
Collaborator Author

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22759 [ run ] triggered by Bot. Commit: d583b1a

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22759 [ run ] completed with state SUCCESS. Commit: d583b1a
/LLM/main/L0_MergeRequest_PR pipeline #17161 (Partly Tested) completed with status: 'SUCCESS'

@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@dongxuy04 dongxuy04 changed the title [None][fix] Enable GDRCopy and unwaive online eplb tests [TRTLLM-7008][fix] Enable GDRCopy and unwaive online eplb tests Oct 29, 2025
@tensorrt-cicd
Copy link
Collaborator

PR_Github #22811 [ run ] triggered by Bot. Commit: d583b1a

@dongxuy04 dongxuy04 marked this pull request as ready for review October 29, 2025 00:38
@dongxuy04 dongxuy04 requested review from a team as code owners October 29, 2025 00:38
@coderabbitai
Copy link
Contributor

coderabbitai bot commented Oct 29, 2025

📝 Walkthrough

Walkthrough

Docker configuration modified to expose the GDRDRV device (/dev/gdrdrv) when deploying on the DL cluster. Two test entries removed from the waiver exclusion list, enabling them to run during test execution.

Changes

Cohort / File(s) Summary
Docker Device Configuration
jenkins/L0_Test.groovy
Added --device=/dev/gdrdrv:/dev/gdrdrv to Docker arguments for DL cluster deployments to expose GDRDRV device to containers.
Test Waiver List Updates
tests/integration/test_lists/waives.txt
Removed two waived test entries: TestDeepSeekV3Lite::test_bfloat16_4gpus_online_eplb[mtp_nextn=2] and TestDeepSeekV3Lite::test_nvfp4_4gpus_online_eplb[fp8kv=True], allowing these tests to run.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

  • The Groovy change is a single device argument addition to Docker configuration with no logic modifications.
  • The waiver list change is a straightforward removal of two test entries from a text file with no conditional logic.

Pre-merge checks and finishing touches

❌ Failed checks (2 warnings)
Check name Status Explanation Resolution
Description Check ⚠️ Warning The PR description is largely incomplete relative to the required template. While a Description section is present with two bullet points ("Enable GDRCopy on dlcluster" and "Unwaive online eplb"), it lacks substantive context explaining the issue, rationale, or impact of these changes. More critically, the Test Coverage section—which is explicitly required by the template and particularly important for a PR involving test waivers—is entirely empty with no tests listed. The PR Checklist has been marked as complete, but the preceding required sections are insufficient to meet the template expectations. The author should expand the Description section to explain why GDRCopy is being enabled and why these specific tests are now safe to unwaive. More importantly, the Test Coverage section must be completed by listing the specific tests being unwaived (test_bfloat16_4gpus_online_eplb and test_nvfp4_4gpus_online_eplb) and explaining how they safeguard the changes. This context is especially important given that the PR modifies test waivers and test infrastructure.
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.
✅ Passed checks (1 passed)
Check name Status Explanation
Title Check ✅ Passed The PR title "[TRTLLM-7008][fix] Enable GDRCopy and unwaive online eplb tests" follows the required template format with a valid JIRA ticket ID, appropriate type flag, and a clear, concise summary. The title directly corresponds to the actual changes made: adding GDRCopy device configuration to the Jenkins test script and removing two test entries from the waiver list. The title is specific enough that a developer reviewing commit history would immediately understand the primary objectives of the changeset.
✨ Finishing touches
🧪 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.

Copy link
Contributor

@coderabbitai coderabbitai bot left a comment

Choose a reason for hiding this comment

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

Actionable comments posted: 0

🧹 Nitpick comments (1)
jenkins/L0_Test.groovy (1)

649-652: Consider adding device existence validation for robustness.

The GDRCopy device mapping is correct, but the code doesn't verify that /dev/gdrdrv exists on the host before attempting to map it. If the device is unavailable, Docker container creation will fail with a potentially unclear error message.

Consider adding a device check within the node context before appending the Docker argument:

if (partition.clusterName == "dlcluster") {
    dockerArgs += " -e NVIDIA_IMEX_CHANNELS=0"
    // Check if GDRCopy device exists before mapping
    def gdrDeviceExists = sh(
        script: "[ -e /dev/gdrdrv ] && echo 'true' || echo 'false'",
        returnStdout: true
    ).trim() == 'true'
    if (gdrDeviceExists) {
        dockerArgs += " --device=/dev/gdrdrv:/dev/gdrdrv"
        echo "GDRCopy device /dev/gdrdrv mapped to container"
    } else {
        echo "Warning: GDRCopy device /dev/gdrdrv not found, skipping device mapping"
    }
}

Alternatively, if the device is expected to always be present on dlcluster nodes, document this requirement and allow the failure to occur with Docker's error message.

📜 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 6b9b73e and d583b1a.

📒 Files selected for processing (2)
  • jenkins/L0_Test.groovy (1 hunks)
  • tests/integration/test_lists/waives.txt (0 hunks)
💤 Files with no reviewable changes (1)
  • tests/integration/test_lists/waives.txt

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22811 [ run ] completed with state SUCCESS. Commit: d583b1a
/LLM/main/L0_MergeRequest_PR pipeline #17206 completed with status: 'FAILURE'

@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22833 [ run ] triggered by Bot. Commit: d583b1a

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22833 [ run ] completed with state SUCCESS. Commit: d583b1a
/LLM/main/L0_MergeRequest_PR pipeline #17223 completed with status: 'FAILURE'

@dongxuy04 dongxuy04 force-pushed the user/dongxuy/enable_eplb_ci branch from d583b1a to 08b546b Compare October 29, 2025 06:53
@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22859 [ run ] triggered by Bot. Commit: 08b546b

@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22895 [ run ] triggered by Bot. Commit: 250de73

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22859 [ run ] completed with state ABORTED. Commit: 08b546b
LLM/main/L0_MergeRequest_PR #17240 (Blue Ocean) completed with status: ABORTED

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22895 [ run ] completed with state ABORTED. Commit: 250de73
/LLM/main/L0_MergeRequest_PR pipeline #17266 completed with status: 'FAILURE'

@dongxuy04 dongxuy04 force-pushed the user/dongxuy/enable_eplb_ci branch from 250de73 to 2315bd8 Compare October 30, 2025 00:26
@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22939 [ run ] triggered by Bot. Commit: 2315bd8

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22939 [ run ] completed with state SUCCESS. Commit: 2315bd8
/LLM/main/L0_MergeRequest_PR pipeline #17299 completed with status: 'FAILURE'

@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22988 [ run ] triggered by Bot. Commit: 2315bd8

@tensorrt-cicd
Copy link
Collaborator

PR_Github #22988 [ run ] completed with state SUCCESS. Commit: 2315bd8
/LLM/main/L0_MergeRequest_PR pipeline #17330 completed with status: 'FAILURE'

@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #23017 [ run ] triggered by Bot. Commit: 2315bd8

@tensorrt-cicd
Copy link
Collaborator

PR_Github #23017 [ run ] completed with state SUCCESS. Commit: 2315bd8
/LLM/main/L0_MergeRequest_PR pipeline #17353 completed with status: 'FAILURE'

@dongxuy04 dongxuy04 force-pushed the user/dongxuy/enable_eplb_ci branch from 2315bd8 to 4d7e5e4 Compare October 30, 2025 11:43
@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #23040 [ run ] triggered by Bot. Commit: 4d7e5e4

@tensorrt-cicd
Copy link
Collaborator

PR_Github #23040 [ run ] completed with state SUCCESS. Commit: 4d7e5e4
/LLM/main/L0_MergeRequest_PR pipeline #17373 completed with status: 'FAILURE'

@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@dongxuy04 dongxuy04 force-pushed the user/dongxuy/enable_eplb_ci branch from 4d7e5e4 to 3118335 Compare October 31, 2025 00:46
@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #23089 [ run ] triggered by Bot. Commit: 3118335

@dongxuy04 dongxuy04 enabled auto-merge (squash) October 31, 2025 07:56
@tensorrt-cicd
Copy link
Collaborator

PR_Github #23089 [ run ] completed with state SUCCESS. Commit: 3118335
/LLM/main/L0_MergeRequest_PR pipeline #17413 completed with status: 'FAILURE'

@dongxuy04
Copy link
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Collaborator

PR_Github #23207 [ run ] triggered by Bot. Commit: 3118335

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