[None][test] Unwaive test_ray_disaggregated_serving tp1 and tp2

[dominicshanshan]

• Remove in-code skip for tp1 (https://nvbugs/5682551)
• Remove waives.txt entry for tp2 (https://nvbugs/5612502)

Re-enables Ray disaggregated serving test coverage (UCX backend).

Dev Engineer Review

• Disabled the tp1 skip in test_ray_disaggregated_serving.
• Removed the tp2 waiver from waives.txt.
• The existing GPU-count skip remains active.
• The waiver format and test selector are valid.
• The old NVBugs reference remains in comments and does not affect execution.

QA Engineer Review

• Modified test: test_ray_disaggregated_serving.
• tp1 is listed in test-db/l0_dgx_h100.yml.
• tp2 is listed in test-db/l0_dgx_b200.yml.
• Both parameterizations have CI coverage.
• Verdict: sufficient.

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)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• 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

To see a list of available CI bot commands, please comment /bot help.

[coderabbitai]

Caution

Review failed

An error occurred during the review process. Please try again later.

Walkthrough

The Ray disaggregated serving test now runs for tp_size == 1. Its skip waiver entry and associated NVBug reference were removed.

Changes

Ray serving test execution

Layer / File(s)	Summary
Enable single-device Ray serving test tests/integration/defs/examples/test_ray.py, tests/integration/test_lists/waives.txt	The conditional skip for tp_size == 1 is disabled. The related test waiver and NVBug reference are removed.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Suggested reviewers: brnguyen2, bowenfu

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the test and the tp1 and tp2 unwaive changes.
Description check	✅ Passed	The description explains the changes, references the related issues, identifies restored test coverage, and includes the completed checklist.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
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.

✨ Finishing Touches 💡 1

🛠️ Fix failing CI checks 💡

• Create stacked PR
• Commit on current branch

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands.}

[dominicshanshan]

/bot --help

[github-actions]

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". The patterns "*", "*Post-Merge*", and "*PerfSanity*", including equivalent escaped or repeated-star forms and their use in comma-separated lists, require the ci: post-merge approved PR label. 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. Requires the ci: full pre-merge approved label on the PR (ask a member of NVIDIA/trt-llm-ci-approvers). 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. Requires the ci: full pre-merge approved label on the PR (ask a member of NVIDIA/trt-llm-ci-approvers).

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline. Requires the ci: post-merge approved PR label applied by an active member of NVIDIA/trt-llm-ci-approvers. The approval label remains in place when new commits are pushed.

--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". The patterns "*", "*Post-Merge*", and "*PerfSanity*", including equivalent escaped or repeated-star forms and their use in comma-separated lists, require the ci: post-merge approved PR label.

--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]

/bot run

[tensorrt-cicd]

PR_Github #63984 [ run ] triggered by Bot. Commit: d48aaf9 Link to invocation

[tensorrt-cicd]

PR_Github #63984 [ run ] completed with state FAILURE. Commit: d48aaf9
/LLM/main/L0_MergeRequest_PR pipeline #51918 completed with status: 'UNSTABLE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ 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]

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Ray-1-cbts"

[tensorrt-cicd]

PR_Github #63999 [ run ] triggered by Bot. Commit: d48aaf9 Link to invocation

[tensorrt-cicd]

PR_Github #63999 [ run ] completed with state FAILURE. Commit: d48aaf9
/LLM/main/L0_MergeRequest_PR pipeline #51934 (Partly Tested) 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

[BowenFu]

Holding on evidence, not on the change itself — both entries land straight in pre-merge, so a flake here blocks everyone:

• test_ray_disaggregated_serving[tp1] → test-db/l0_dgx_h100.yml:314, stage: pre_merge, 2-GPU
• test_ray_disaggregated_serving[tp2] → test-db/l0_dgx_b200.yml:133, stage: pre_merge, 4-GPU

The description doesn't cite a run for either bug. Could you add what you'd add for any unwaive — board, commit, command, iteration count? Two bugs are being retired here (5682551 and 5612502) and neither has evidence attached.

One thing that makes me want that evidence more: nvbug 5682551 is still waiving a different test on main — waives.txt:275, full:H100_PCIe/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_multi_lora_evict_and_reload_lora_gpu_cache. If that bug is live enough to keep another test waived, it's worth saying why the ray path is clear.

Minor: please delete the tp1 skip rather than commenting it out —

    # if tp_size == 1:
    #     pytest.skip("https://nvbugs/5682551")

git history is the record if it has to come back, and a commented-out skip carrying a live nvbug number reads as unfinished.

Happy to approve once a passing run is on the PR.

[dominicshanshan]

Holding on evidence, not on the change itself — both entries land straight in pre-merge, so a flake here blocks everyone:

• test_ray_disaggregated_serving[tp1] → test-db/l0_dgx_h100.yml:314, stage: pre_merge, 2-GPU
• test_ray_disaggregated_serving[tp2] → test-db/l0_dgx_b200.yml:133, stage: pre_merge, 4-GPU

The description doesn't cite a run for either bug. Could you add what you'd add for any unwaive — board, commit, command, iteration count? Two bugs are being retired here (5682551 and 5612502) and neither has evidence attached.

One thing that makes me want that evidence more: nvbug 5682551 is still waiving a different test on main — waives.txt:275, full:H100_PCIe/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_multi_lora_evict_and_reload_lora_gpu_cache. If that bug is live enough to keep another test waived, it's worth saying why the ray path is clear.

Minor: please delete the tp1 skip rather than commenting it out —

    # if tp_size == 1:
    #     pytest.skip("https://nvbugs/5682551")

git history is the record if it has to come back, and a commented-out skip carrying a live nvbug number reads as unfinished.

Happy to approve once a passing run is on the PR.

Got it, waive those two tests for check if they are still being flaky in current main branch and it use UCX backend (quite old), a new test may come from this PR: #17295. I will also offline test its flakiness and post the result here.

[dominicshanshan]

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-Ray-1, DGX_H100-2_GPUs-PyTorch-Ray-1"

[tensorrt-cicd]

PR_Github #64020 [ run ] triggered by Bot. Commit: 9fc2339 Link to invocation

[tensorrt-cicd]

PR_Github #64020 [ run ] completed with state FAILURE. Commit: 9fc2339
/LLM/main/L0_MergeRequest_PR pipeline #51951 (Partly Tested) completed with status: 'UNSTABLE'

CI Report

⚠️ Multi-GPU Label Required:
Multi-GPU tests require the ci: full pre-merge approved label on this PR. Ask a member of NVIDIA/trt-llm-ci-approvers to add the label, then re-trigger CI with the same bot command (no rebase needed).

⚠️ 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

[brnguyen2]

Both node IDs are in pre-merge test-db lists (l0_dgx_h100.yml:314 for tp1, l0_dgx_b200.yml:133 for tp2), so /bot run will genuinely cover this — good. Worth stating in the description what fixed nvbugs/5682551 and 5612502, or how many clean runs back the unwaive; these are flaky-looking disagg/Ray tests, and "can't repro" alone tends to bounce back. Please also close both NVBugs when this merges.