[None][test] Unwaive test_ray_disaggregated_serving tp1 and tp2 by dominicshanshan · Pull Request #17291 · NVIDIA/TensorRT-LLM

dominicshanshan · 2026-08-05T07:08:02Z

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

Removed the tp1 skip from 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 changes do not introduce API, performance, or error-handling concerns.

QA Engineer Review

Modified test: test_ray_disaggregated_serving.
tp1 is covered by test-db/l0_dgx_h100.yml.
tp2 is covered by test-db/l0_dgx_b200.yml.
Both parameterizations have CI coverage.
CI results are unstable, and CBTS coverage data is unavailable.
Verdict: needs follow-up.

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 · 2026-08-05T07:09:57Z

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: 2700b023-33c4-49d2-a269-f859cad6986f

📥 Commits

Reviewing files that changed from the base of the PR and between a993952 and 77ee2cf.

📒 Files selected for processing (2)

tests/integration/defs/examples/test_ray.py
tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (2)

tests/integration/test_lists/waives.txt
tests/integration/defs/examples/test_ray.py

Walkthrough

The Ray disaggregated serving test now runs for tp_size == 1. Its skip waiver entry was 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` and its related waiver entry are removed.

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

Possibly related PRs

NVIDIA/TensorRT-LLM#17295: Modifies the same Ray disaggregated-serving test and its tp2 skip.
NVIDIA/TensorRT-LLM#17329: Adjusts waived integration tests in the same waiver file.

Suggested reviewers: bowenfu, emmaqiaoch, zhanruisunch

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description states the change, but the required Description and Test Coverage sections remain empty.	Add a concise issue and solution summary under Description, and list the relevant tests, commands, results, and stability evidence under Test Coverage.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the test change and specifies that tp1 and tp2 are being unwaived.
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

🧪 Generate unit tests (beta)

Create PR with unit tests

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

dominicshanshan · 2026-08-05T07:11:17Z

/bot --help

github-actions · 2026-08-05T07:11:24Z

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 · 2026-08-05T07:23:13Z

/bot run

tensorrt-cicd · 2026-08-05T07:29:23Z

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

tensorrt-cicd · 2026-08-05T08:03:11Z

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 · 2026-08-05T08:21:51Z

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

tensorrt-cicd · 2026-08-05T08:27:02Z

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

tensorrt-cicd · 2026-08-05T09:09:54Z

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 · 2026-08-05T09:18:31Z

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 · 2026-08-05T09:39:52Z

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 · 2026-08-05T09:48:29Z

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

tensorrt-cicd · 2026-08-05T09:54:38Z

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

tensorrt-cicd · 2026-08-05T10:25:36Z

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.

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

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

coderabbitai · 2026-08-06T02:06:30Z

Note

GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer.

dominicshanshan · 2026-08-06T02:26:04Z

/bot run

tensorrt-cicd · 2026-08-06T02:32:20Z

PR_Github #64177 [ run ] triggered by Bot. Commit: 77ee2cf Link to invocation

brnguyen2

Approving — the comments below are optional touch-ups, not blockers.

Re-checked on current HEAD: skip block fully removed (no commented-out remnant), waives.txt clean, and both node IDs still registered in pre-merge test-db (l0_dgx_h100.yml:314 for tp1, l0_dgx_b200.yml:133 for tp2). Prior concerns check out.

Still open from last round, non-blocking: the description doesn't say what fixed nvbugs/5682551 and 5612502 or how many clean runs back the unwaive. Worth one line before merge — flaky-looking disagg/Ray unwaives without that tend to bounce back. Please close both NVBugs on merge.

dominicshanshan · 2026-08-06T03:09:28Z

/bot run

tensorrt-cicd · 2026-08-06T03:16:25Z

PR_Github #64194 [ run ] triggered by Bot. Commit: 77ee2cf Link to invocation

tensorrt-cicd · 2026-08-06T03:20:59Z

PR_Github #64177 [ run ] completed with state ABORTED. Commit: 77ee2cf

Link to invocation

dominicshanshan requested review from a team as code owners August 5, 2026 07:08

dominicshanshan requested review from BowenFu, EmmaQiaoCh, LarryXFly, ZhanruiSunCh, brnguyen2, yingguo-trt and yufeiwu-nv August 5, 2026 07:08

github-actions Bot assigned dominicshanshan Aug 5, 2026

coderabbitai Bot mentioned this pull request Aug 5, 2026

[None][feat] support NIXL cache transceiver with Ray #17295

Open

Yigtwxx mentioned this pull request Aug 5, 2026

[#17156][fix] Flush buffered text in DeepSeekR1Parser.finish() #17157

Open

1 task

brnguyen2 approved these changes Aug 5, 2026

View reviewed changes

yufeiwu-nv removed their request for review August 5, 2026 23:32

LarryXFly approved these changes Aug 6, 2026

View reviewed changes

yingguo-trt approved these changes Aug 6, 2026

View reviewed changes

dominicshanshan added 2 commits August 5, 2026 18:58

[None][test] Remove leftover commented-out tp1 skip in test_ray_disag…

77ee2cf

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

dominicshanshan force-pushed the disagg_ray_test branch from 9fc2339 to 77ee2cf Compare August 6, 2026 02:06

dominicshanshan requested a review from a team August 6, 2026 02:24

brnguyen2 approved these changes Aug 6, 2026

View reviewed changes

Uh oh!

Conversation

dominicshanshan commented Aug 5, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Dev Engineer Review

QA Engineer Review

Description

Test Coverage

PR Checklist

GitHub Bot Help

Uh oh!

coderabbitai Bot commented Aug 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

❌ Failed checks (1 warning)

Uh oh!

dominicshanshan commented Aug 5, 2026

Uh oh!

github-actions Bot commented Aug 5, 2026

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

dominicshanshan commented Aug 5, 2026

Uh oh!

tensorrt-cicd commented Aug 5, 2026

Uh oh!

tensorrt-cicd commented Aug 5, 2026

Uh oh!

dominicshanshan commented Aug 5, 2026

Uh oh!

tensorrt-cicd commented Aug 5, 2026

Uh oh!

tensorrt-cicd commented Aug 5, 2026

Uh oh!

BowenFu commented Aug 5, 2026

Uh oh!

dominicshanshan commented Aug 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

dominicshanshan commented Aug 5, 2026

Uh oh!

tensorrt-cicd commented Aug 5, 2026

Uh oh!

tensorrt-cicd commented Aug 5, 2026

Uh oh!

brnguyen2 left a comment

Choose a reason for hiding this comment

Uh oh!

coderabbitai Bot commented Aug 6, 2026

Uh oh!

dominicshanshan commented Aug 6, 2026

Uh oh!

tensorrt-cicd commented Aug 6, 2026

Uh oh!

brnguyen2 left a comment

Choose a reason for hiding this comment

Uh oh!

dominicshanshan commented Aug 6, 2026

Uh oh!

tensorrt-cicd commented Aug 6, 2026

Uh oh!

tensorrt-cicd commented Aug 6, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

6 participants

dominicshanshan commented Aug 5, 2026 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Aug 5, 2026 •

edited

Loading

dominicshanshan commented Aug 5, 2026 •

edited

Loading