[https://nvbugs/6011317][test] DONT REVIEW / CI DEBUG by dongfengy · Pull Request #14156 · NVIDIA/TensorRT-LLM

dongfengy · 2026-05-14T21:24:44Z

Summary by CodeRabbit

Tests

Removed a test skip waiver, re-enabling a previously skipped integration test to run.

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.

dongfengy · 2026-05-14T21:25:57Z

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

github-actions · 2026-05-14T21:26:05Z

⚠️ Bot command ignored: The /bot command must appear at the very beginning of the comment (no leading blank lines or spaces). Please post a new comment with /bot as the first character.

dongfengy · 2026-05-14T21:26:16Z

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

brb-nv

LGTM.

coderabbitai · 2026-05-14T21:30:50Z

📝 Walkthrough

Walkthrough

This PR removes a single test skip waiver entry for disaggregated/test_disaggregated.py::test_disaggregated_gpt_oss_120b_harmony[gpt_oss/gpt-oss-120b] from the integration test waiver list, enabling that test to run instead of being skipped during test execution.

Changes

Test Skip Waiver Removal

Layer / File(s)	Summary
Unskip GPT-OSS 120B harmony test `tests/integration/test_lists/waives.txt`	The waiver entry for the disaggregated GPT-OSS 120B harmony test variant is removed, allowing the test to execute in integration test runs.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~1 minute

Possibly related PRs

NVIDIA/TensorRT-LLM#14114: Also removes a specific test skip entry from tests/integration/test_lists/waives.txt.
NVIDIA/TensorRT-LLM#14103: Removes an integration test skip waiver entry from the same waiver list.
NVIDIA/TensorRT-LLM#14058: Removes disaggregation-related test skip entries from the same waiver file.

Suggested reviewers

jieli-matrix
reasonsolo
xinhe-nv

🚥 Pre-merge checks | ✅ 3 | ❌ 2

❌ Failed checks (2 warnings)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is empty—it only contains the template with all sections (Description, Test Coverage, PR Checklist) left unfilled, providing no explanation of the change or its rationale.	Fill in the Description section explaining what test was unwaived and why, and the Test Coverage section confirming the test now runs without skip.
Title check	⚠️ Warning	The title contains 'DONT REVIEW / CI DEBUG', which contradicts the actual change (unwaiving a passing test). The debug/CI-only language is misleading about the PR's true purpose.	Update the title to accurately reflect the main change, such as '[https://nvbugs/6011317][test] Unwaive passing test' to match the commit message and actual intent.

✅ Passed checks (3 passed)

Check name	Status	Explanation
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.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

Tip

💬 Introducing Slack Agent: The best way for teams to turn conversations into code.

Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.

Generate code and open pull requests
Plan features and break down work
Investigate incidents and troubleshoot customer tickets together
Automate recurring tasks and respond to alerts with triggers
Summarize progress and report instantly

Built for teams:

Shared memory across your entire org—no repeating context
Per-thread sandboxes to safely plan and execute work
Governance built-in—scoped access, auditability, and budget controls

One agent for your entire SDLC. Right inside Slack.

👉 Get started

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

dongfengy · 2026-05-14T23:01:01Z

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

tensorrt-cicd · 2026-05-14T23:07:03Z

PR_Github #48457 [ run ] triggered by Bot. Commit: b9e0b45 Link to invocation

tensorrt-cicd · 2026-05-15T01:25:51Z

PR_Github #48457 [ run ] completed with state SUCCESS. Commit: b9e0b45
/LLM/main/L0_MergeRequest_PR pipeline #38253 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

dongfengy · 2026-05-15T02:21:06Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2,DGX_B200-4_GPUs-PyTorch-3"

chienchunhung

Have we verified that the test now passes?

tensorrt-cicd · 2026-05-15T02:27:21Z

PR_Github #48489 [ run ] triggered by Bot. Commit: b9e0b45 Link to invocation

dongfengy · 2026-05-15T02:32:45Z

Have we verified that the test now passes?

verified locally. will also run the stages on ci before merge.

tensorrt-cicd · 2026-05-15T05:03:47Z

PR_Github #48489 [ run ] completed with state SUCCESS. Commit: b9e0b45
/LLM/main/L0_MergeRequest_PR pipeline #38285 (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

dongfengy · 2026-05-15T18:44:30Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2,DGX_B200-4_GPUs-PyTorch-3"

tensorrt-cicd · 2026-05-15T18:49:41Z

PR_Github #48624 [ run ] triggered by Bot. Commit: d292f00 Link to invocation

tensorrt-cicd · 2026-05-15T21:26:53Z

PR_Github #48624 [ run ] completed with state SUCCESS. Commit: d292f00
/LLM/main/L0_MergeRequest_PR pipeline #38406 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy · 2026-05-16T01:54:32Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2,DGX_B200-4_GPUs-PyTorch-3"

tensorrt-cicd · 2026-05-16T02:00:39Z

PR_Github #48660 [ run ] triggered by Bot. Commit: 9b36a8d Link to invocation

tensorrt-cicd · 2026-05-16T04:47:44Z

PR_Github #48660 [ run ] completed with state FAILURE. Commit: 9b36a8d
/LLM/main/L0_MergeRequest_PR pipeline #38440 (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

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy · 2026-05-17T02:08:14Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2026-05-17T02:14:26Z

PR_Github #48725 [ run ] triggered by Bot. Commit: 6878879 Link to invocation

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

tensorrt-cicd · 2026-05-17T04:59:21Z

PR_Github #48725 [ run ] completed with state SUCCESS. Commit: 6878879
/LLM/main/L0_MergeRequest_PR pipeline #38494 (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

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy · 2026-05-17T05:12:47Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2026-05-17T05:18:05Z

PR_Github #48739 [ run ] triggered by Bot. Commit: 27d8ddf Link to invocation

tensorrt-cicd · 2026-05-17T05:49:34Z

PR_Github #48739 [ run ] completed with state FAILURE. Commit: 27d8ddf
/LLM/main/L0_MergeRequest_PR pipeline #38506 (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

dongfengy · 2026-05-17T06:15:31Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2026-05-17T06:20:41Z

PR_Github #48744 [ run ] triggered by Bot. Commit: 27d8ddf Link to invocation

tensorrt-cicd · 2026-05-17T07:56:17Z

PR_Github #48744 [ run ] completed with state SUCCESS. Commit: 27d8ddf
/LLM/main/L0_MergeRequest_PR pipeline #38511 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy · 2026-05-17T15:59:40Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2026-05-17T16:05:50Z

PR_Github #48770 [ run ] triggered by Bot. Commit: 5addc50 Link to invocation

tensorrt-cicd · 2026-05-17T17:37:39Z

PR_Github #48770 [ run ] completed with state SUCCESS. Commit: 5addc50
/LLM/main/L0_MergeRequest_PR pipeline #38535 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy · 2026-05-17T19:10:26Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2026-05-17T19:17:10Z

PR_Github #48780 [ run ] triggered by Bot. Commit: b90612f Link to invocation

tensorrt-cicd · 2026-05-17T22:08:37Z

PR_Github #48780 [ run ] completed with state FAILURE. Commit: b90612f
/LLM/main/L0_MergeRequest_PR pipeline #38544 (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

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy · 2026-05-17T23:07:38Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2"

tensorrt-cicd · 2026-05-17T23:12:55Z

PR_Github #48793 [ run ] triggered by Bot. Commit: 109e53e Link to invocation

tensorrt-cicd · 2026-05-18T02:01:05Z

PR_Github #48793 [ run ] completed with state SUCCESS. Commit: 109e53e
/LLM/main/L0_MergeRequest_PR pipeline #38556 (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

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy · 2026-05-18T02:17:29Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2"

dongfengy · 2026-05-18T03:27:16Z

/bot run --stage-list "DGX_B200-4_GPUs-PyTorch-2"

dongfengy requested a review from chienchunhung May 14, 2026 21:24

github-actions Bot assigned dongfengy May 14, 2026

dongfengy requested a review from brb-nv May 14, 2026 21:25

brb-nv approved these changes May 14, 2026

View reviewed changes

dongfengy force-pushed the user/dongfengy/6011317 branch from b7ef790 to b9e0b45 Compare May 14, 2026 23:00

dongfengy changed the title ~~[https://nvbugs/6011317][test] Unwaive passing test~~ [https://nvbugs/6011317][test] Unwaive passing test test_disaggregated_gpt_oss_120b_harmony May 15, 2026

chienchunhung approved these changes May 15, 2026

View reviewed changes

dongfengy force-pushed the user/dongfengy/6011317 branch from b9e0b45 to d292f00 Compare May 15, 2026 16:57

[https://nvbugs/6011317][test]: Unwaive passing test

9b36a8d

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy force-pushed the user/dongfengy/6011317 branch from d292f00 to 9b36a8d Compare May 16, 2026 01:54

Add disaggregated serving hang diagnostics

18b7f81

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy requested review from a team as code owners May 16, 2026 19:16

Keep post-disagg DGX B200 debug waives

a0fba79

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

Add disagg cache transfer debug logs

27d8ddf

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

Add DGX B200 CI rerun marker

5addc50

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

dongfengy added 3 commits May 17, 2026 18:28

Revert DGX B200 debug changes

ee7c1b3

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

Add conservative disagg sender debug logs

48f8117

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

Tighten disagg debug log placement

b90612f

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

Add conservative disagg notification diagnostics

109e53e

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

Add conservative NIXL notification diagnostics

fb8dd31

Signed-off-by: Dongfeng Yu <dongfengy@nvidia.com>

yingguo-trt approved these changes May 21, 2026

View reviewed changes

dongfengy closed this Jun 4, 2026

Uh oh!

Conversation

dongfengy commented May 14, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Tests

Description

Test Coverage

PR Checklist

GitHub Bot Help

Uh oh!

dongfengy commented May 14, 2026

Uh oh!

github-actions Bot commented May 14, 2026

Uh oh!

dongfengy commented May 14, 2026

Uh oh!

brb-nv left a comment

Choose a reason for hiding this comment

Uh oh!

coderabbitai Bot commented May 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

Possibly related PRs

Suggested reviewers

❌ Failed checks (2 warnings)

Uh oh!

dongfengy commented May 14, 2026

Uh oh!

tensorrt-cicd commented May 14, 2026

Uh oh!

tensorrt-cicd commented May 15, 2026

Uh oh!

dongfengy commented May 15, 2026

Uh oh!

chienchunhung left a comment

Choose a reason for hiding this comment

Uh oh!

tensorrt-cicd commented May 15, 2026

Uh oh!

dongfengy commented May 15, 2026

Uh oh!

tensorrt-cicd commented May 15, 2026

Uh oh!

dongfengy commented May 15, 2026

Uh oh!

tensorrt-cicd commented May 15, 2026

Uh oh!

tensorrt-cicd commented May 15, 2026

Uh oh!

dongfengy commented May 16, 2026

Uh oh!

tensorrt-cicd commented May 16, 2026

Uh oh!

tensorrt-cicd commented May 16, 2026

Uh oh!

dongfengy commented May 17, 2026

Uh oh!

tensorrt-cicd commented May 17, 2026

Uh oh!

tensorrt-cicd commented May 17, 2026

Uh oh!

dongfengy commented May 17, 2026

Uh oh!

tensorrt-cicd commented May 17, 2026

Uh oh!

tensorrt-cicd commented May 17, 2026

Uh oh!

dongfengy commented May 17, 2026

Uh oh!

tensorrt-cicd commented May 17, 2026

Uh oh!

tensorrt-cicd commented May 17, 2026

Uh oh!

dongfengy commented May 17, 2026

Uh oh!

tensorrt-cicd commented May 17, 2026

Uh oh!

dongfengy commented May 14, 2026 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented May 14, 2026 •

edited

Loading