Skip to content

[https://nvbugs/6306936][test] Re-enable AutoDeploy disagg tests#15325

Merged
govind-ramnarayan merged 6 commits into
NVIDIA:mainfrom
nv-auto-deploy:gramnarayan/undo-disagg-waives
Jun 23, 2026
Merged

[https://nvbugs/6306936][test] Re-enable AutoDeploy disagg tests#15325
govind-ramnarayan merged 6 commits into
NVIDIA:mainfrom
nv-auto-deploy:gramnarayan/undo-disagg-waives

Conversation

@govind-ramnarayan

@govind-ramnarayan govind-ramnarayan commented Jun 12, 2026

Copy link
Copy Markdown
Collaborator

#15260 should fix all AutoDeploy disagg tests by resolving a merge-time conflict between tests.

This follow up is to unwaive all disagg tests and smoke tests waived due to the above-mentioned AutoDeploy disagg failure.

Additionally, re-enabling the tests may cause issues on GB300 according to the nvbug filed here: https://nvbugspro.nvidia.com/bug/6301621 so we are disabling these tests on GB300 until we are able to test manually and debug.

@coderabbitai summary

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.

@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@coderabbitai

coderabbitai Bot commented Jun 12, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

📝 Walkthrough

Walkthrough

This PR consolidates B300/GB300 test skip logic from the waives configuration file into pytest autouse fixtures within the test modules themselves. Two disaggregated AutoDeploy test files gain skip_b300 fixtures, and corresponding waiver entries are removed from the waives list.

Changes

B300/GB300 test skip consolidation

Layer / File(s) Summary
B300/GB300 skip fixture in test_ad_disagg.py
tests/integration/defs/disaggregated/test_ad_disagg.py
Imports check_device_contain utility and adds autouse fixture skip_b300 that conditionally skips tests when B300/GB300 is detected.
B300/GB300 skip fixture in test_ad_disagg_trtllm_serve.py
tests/integration/defs/disaggregated/test_ad_disagg_trtllm_serve.py
Consolidates imports from defs.conftest and adds autouse fixture skip_b300 with the same B300/GB300 skip logic.
Remove obsolete waivers from waives.txt
tests/integration/test_lists/waives.txt
Removes now-redundant waiver entries for disaggregated and smoke test files, as skip logic is now handled by pytest fixtures.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

  • NVIDIA/TensorRT-LLM#15282: Modifies waives.txt and disaggregated test files, directly related to B300/GB300 test skip management.
  • NVIDIA/TensorRT-LLM#15275: Adds waiver entries for unittest/auto_deploy/singlegpu/smoke/test_disagg.py with bug reference 6307525, which conflicts with the removal of the same entries in this PR.
  • NVIDIA/TensorRT-LLM#15273: Modifies waives.txt for disaggregated/test_ad_disagg.py with bug reference 6306936, overlapping with the same waiver cleanup area as this PR.

Suggested reviewers

  • tburt-nv
  • nvchenghaoz
  • bmarimuthu-nv
  • 2ez4bz
🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%. Write docstrings for the functions missing them to satisfy the coverage threshold.
✅ Passed checks (4 passed)
Check name Status Explanation
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.
Description check ✅ Passed The PR description contains a meaningful explanation of the changes, references related PRs and bug tickets, and explains the rationale for skipping tests on GB300, but includes template boilerplate that was not filled out.
Title check ✅ Passed The title clearly describes the main change: re-enabling AutoDeploy disaggregated tests by removing waivers and adding conditional skip logic for B300/GB300 devices.

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

✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

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

@coderabbitai coderabbitai Bot left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

🧹 Nitpick comments (1)
tests/integration/defs/disaggregated/test_ad_disagg.py (1)

45-46: 📐 Maintainability & Code Quality | ⚡ Quick win

Add explicit -> None to the new autouse fixtures.

Both new fixture definitions (Line 45 in tests/integration/defs/disaggregated/test_ad_disagg.py and Line 38 in tests/integration/defs/disaggregated/test_ad_disagg_trtllm_serve.py) should declare -> None to match the repository’s Python typing guideline for function annotations.

As per coding guidelines, “Always annotate functions. Make the return type None if the function does not return anything.”

🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@tests/integration/defs/disaggregated/test_ad_disagg.py` around lines 45 - 46,
The autouse fixture definitions need explicit return annotations; update the
fixture signature for skip_b300 (def skip_b300()) to include -> None (def
skip_b300() -> None:) and do the same for the other new autouse fixture in
tests/integration/defs/disaggregated/test_ad_disagg_trtllm_serve.py so both
functions are annotated with return type None to comply with the repository
typing guideline.

Source: Coding guidelines

🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Nitpick comments:
In `@tests/integration/defs/disaggregated/test_ad_disagg.py`:
- Around line 45-46: The autouse fixture definitions need explicit return
annotations; update the fixture signature for skip_b300 (def skip_b300()) to
include -> None (def skip_b300() -> None:) and do the same for the other new
autouse fixture in
tests/integration/defs/disaggregated/test_ad_disagg_trtllm_serve.py so both
functions are annotated with return type None to comply with the repository
typing guideline.

ℹ️ Review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 94aa4fd5-8a7a-44df-b36f-12d97a4e85c4

📥 Commits

Reviewing files that changed from the base of the PR and between 19ae053 and 7cf68cb.

📒 Files selected for processing (3)
  • tests/integration/defs/disaggregated/test_ad_disagg.py
  • tests/integration/defs/disaggregated/test_ad_disagg_trtllm_serve.py
  • tests/integration/test_lists/waives.txt
💤 Files with no reviewable changes (1)
  • tests/integration/test_lists/waives.txt

@govind-ramnarayan govind-ramnarayan changed the title [https://nvbugs/6301621][test] Re-enable AutoDeploy disagg tests [https://nvbugspro.nvidia.com/bug/6306936][test] Re-enable AutoDeploy disagg tests Jun 12, 2026
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53966 [ run ] triggered by Bot. Commit: 7cf68cb Link to invocation

@govind-ramnarayan govind-ramnarayan changed the title [https://nvbugspro.nvidia.com/bug/6306936][test] Re-enable AutoDeploy disagg tests [https://nvbugs/6306936][test] Re-enable AutoDeploy disagg tests Jun 12, 2026
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #53966 [ run ] completed with state FAILURE. Commit: 7cf68cb
/LLM/main/L0_MergeRequest_PR pipeline #43056 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

@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #54152 [ run ] triggered by Bot. Commit: 1a85402 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #54152 [ run ] completed with state SUCCESS. Commit: 1a85402
/LLM/main/L0_MergeRequest_PR pipeline #43235 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

@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "A30-AutoDeploy-1"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #54357 [ run ] triggered by Bot. Commit: accdbaf Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #54357 [ run ] completed with state FAILURE. Commit: accdbaf
/LLM/main/L0_MergeRequest_PR pipeline #43427 (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

@fredricz-20070104 fredricz-20070104 left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

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

Approved

@govind-ramnarayan govind-ramnarayan force-pushed the gramnarayan/undo-disagg-waives branch from accdbaf to d66f329 Compare June 16, 2026 20:41
@govind-ramnarayan govind-ramnarayan requested a review from a team as a code owner June 16, 2026 20:41
@govind-ramnarayan govind-ramnarayan requested a review from tfogal June 16, 2026 20:41
@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #54671 [ run ] triggered by Bot. Commit: d66f329 Link to invocation

@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #54681 [ run ] triggered by Bot. Commit: 2dee880 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #54671 [ run ] completed with state ABORTED. Commit: d66f329

Link to invocation

@govind-ramnarayan govind-ramnarayan enabled auto-merge (squash) June 17, 2026 00:43
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #54681 [ run ] completed with state FAILURE. Commit: 2dee880
/LLM/main/L0_MergeRequest_PR pipeline #43712 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

@galagam

galagam commented Jun 17, 2026

Copy link
Copy Markdown
Collaborator

/bot run

Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
@govind-ramnarayan govind-ramnarayan force-pushed the gramnarayan/undo-disagg-waives branch from fb3b06b to 3e2cc43 Compare June 22, 2026 18:07
@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55066 [ run ] triggered by Bot. Commit: 3e2cc43 Link to invocation

…m factory. Maybe we want better defaults in the future but production config files are agent-generated so they dont have this issue when they set max_seq_len

Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot kill

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55082 [ kill ] triggered by Bot. Commit: aa3f6a2 Link to invocation

@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "A30-AutoDeploy-1"

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55066 [ run ] completed with state ABORTED. Commit: 3e2cc43

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55082 [ kill ] completed with state SUCCESS. Commit: aa3f6a2
Successfully killed previous jobs for commit aa3f6a2

Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55083 [ run ] triggered by Bot. Commit: aa3f6a2 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55083 [ run ] completed with state SUCCESS. Commit: aa3f6a2
/LLM/main/L0_MergeRequest_PR pipeline #44069 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55092 [ run ] triggered by Bot. Commit: aa3f6a2 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55092 [ run ] completed with state SUCCESS. Commit: aa3f6a2
/LLM/main/L0_MergeRequest_PR pipeline #44078 completed with status: 'SUCCESS'

CI Report

Link to invocation

@govind-ramnarayan

Copy link
Copy Markdown
Collaborator Author

/bot run --post-merge

@govind-ramnarayan govind-ramnarayan enabled auto-merge (squash) June 23, 2026 05:29
@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55168 [ run ] triggered by Bot. Commit: aa3f6a2 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55168 [ run ] completed with state SUCCESS. Commit: aa3f6a2
/LLM/main/L0_MergeRequest_PR pipeline #44140 completed with status: 'SUCCESS'

CI Report

Link to invocation

Signed-off-by: Gal Hubara-Agam <96368689+galagam@users.noreply.github.com>
@galagam

galagam commented Jun 23, 2026

Copy link
Copy Markdown
Collaborator

/bot run --post-merge

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55208 [ run ] triggered by Bot. Commit: 24b0fd3 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #55208 [ run ] completed with state SUCCESS. Commit: 24b0fd3
/LLM/main/L0_MergeRequest_PR pipeline #44171 completed with status: 'SUCCESS'

CI Report

Link to invocation

@govind-ramnarayan govind-ramnarayan merged commit 2965eca into NVIDIA:main Jun 23, 2026
7 checks passed
xinhe-nv pushed a commit to tensorrt-cicd/TensorRT-LLM that referenced this pull request Jun 24, 2026
…DIA#15325)

Signed-off-by: Govind Ramnarayan <105831528+govind-ramnarayan@users.noreply.github.com>
Signed-off-by: Gal Hubara-Agam <96368689+galagam@users.noreply.github.com>
Co-authored-by: Gal Hubara-Agam <96368689+galagam@users.noreply.github.com>
Signed-off-by: GitLab CI Bot <gitlab-ci@nvidia.com>
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.

5 participants