Skip to content

[None][chore] Fix failing KV Cache Transceiver Tests from #11574#12554

Merged
pcastonguay merged 6 commits into
NVIDIA:mainfrom
ekou24:kv_test_fix
Apr 13, 2026
Merged

[None][chore] Fix failing KV Cache Transceiver Tests from #11574#12554
pcastonguay merged 6 commits into
NVIDIA:mainfrom
ekou24:kv_test_fix

Conversation

@ekou24
Copy link
Copy Markdown
Contributor

@ekou24 ekou24 commented Mar 26, 2026

Fixing failing KV Cache Transceiver tests (python + cpp) that were added in PR #11574

Summary by CodeRabbit

  • Tests

    • Enhanced test coverage for distributed execution and resource management features
    • Updated test validation to align with improved internal component structures
  • Chores

    • Restructured internal test infrastructure for better maintainability and consistency

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)

  • 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.

@ekou24
Copy link
Copy Markdown
Contributor Author

ekou24 commented Mar 26, 2026

/bot run --disable-fail-fast

@ekou24 ekou24 changed the title [None][Chore] Fix failing KV Cache Transceiver Tests from #11574 [None][chore] Fix failing KV Cache Transceiver Tests from #11574 Mar 26, 2026
@coderabbitai
Copy link
Copy Markdown
Contributor

coderabbitai Bot commented Mar 26, 2026

📝 Walkthrough

Walkthrough

This PR updates test files across the disaggregated module to reflect API changes: imports are adjusted to new module structure, slot allocation expectations shift from raw integers to AuxSlot objects, pool descriptor tests migrate to resource/page abstraction validation, and RankInfo tests simplify with reduced constructor parameters.

Changes

Cohort / File(s) Summary
Test List Configuration
tests/integration/test_lists/test-db/l0_h100.yml
Added seven new test targets to the l0_h100 PyTorch/MPI test list under unittest/disaggregated/region and unittest/disaggregated modules.
Disaggregated Module Tests
tests/unittest/disaggregated/region/test_aux.py, tests/unittest/disaggregated/region/test_page.py, tests/unittest/disaggregated/test_rank_info.py
Updated imports to match new module structure; modified slot allocation tests to use AuxSlot objects instead of raw integers; transitioned test_page.py from PoolDescriptor validation to resource/page abstraction serialization roundtrip checks; simplified RankInfo constructor expectations and removed deprecated fields like kv_ptrs, aux_ptrs, and device parameters.

Estimated code review effort

🎯 3 (Moderate) | ⏱️ ~25 minutes

🚥 Pre-merge checks | ✅ 1 | ❌ 2

❌ Failed checks (2 warnings)

Check name Status Explanation Resolution
Docstring Coverage ⚠️ Warning Docstring coverage is 6.67% which is insufficient. The required threshold is 80.00%. Write docstrings for the functions missing them to satisfy the coverage threshold.
Description check ⚠️ Warning The pull request description lacks substantive content and consists primarily of the template with empty sections. Complete the Description section explaining what tests are being fixed and why; fill Test Coverage section with specific test references; provide concrete details beyond the PR title.
✅ Passed checks (1 passed)
Check name Status Explanation
Title check ✅ Passed The title clearly identifies the main change as fixing failing KV Cache Transceiver Tests referenced in #11574, directly matching the changeset which updates test files and test lists.

✏️ 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.

@ekou24
Copy link
Copy Markdown
Contributor Author

ekou24 commented Mar 26, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #40434 [ run ] triggered by Bot. Commit: 2542d70 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #40434 [ run ] completed with state SUCCESS. Commit: 2542d70
/LLM/main/L0_MergeRequest_PR pipeline #31526 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

Link to invocation

@ekou24
Copy link
Copy Markdown
Contributor Author

ekou24 commented Mar 26, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #40463 [ run ] triggered by Bot. Commit: 2542d70 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #40463 [ run ] completed with state FAILURE. Commit: 2542d70
/LLM/main/L0_MergeRequest_PR pipeline #31552 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

Link to invocation

@ekou24
Copy link
Copy Markdown
Contributor Author

ekou24 commented Mar 26, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #40467 [ run ] triggered by Bot. Commit: 2542d70 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #40467 [ run ] completed with state SUCCESS. Commit: 2542d70
/LLM/main/L0_MergeRequest_PR pipeline #31556 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

Link to invocation

@ekou24
Copy link
Copy Markdown
Contributor Author

ekou24 commented Mar 27, 2026

/bot run --disable-fail-fast

@ekou24 ekou24 requested a review from Shixiaowei02 March 27, 2026 19:54
@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #40514 [ run ] triggered by Bot. Commit: 2542d70 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #40514 [ run ] completed with state SUCCESS. Commit: 2542d70
/LLM/main/L0_MergeRequest_PR pipeline #31600 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

Link to invocation

@pcastonguay
Copy link
Copy Markdown
Collaborator

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42145 [ run ] triggered by Bot. Commit: 2542d70 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42145 [ run ] completed with state SUCCESS. Commit: 2542d70
/LLM/main/L0_MergeRequest_PR pipeline #32979 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

Link to invocation

@ekou24
Copy link
Copy Markdown
Contributor Author

ekou24 commented Apr 8, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42375 [ run ] triggered by Bot. Commit: 06b74be Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42375 [ run ] completed with state SUCCESS. Commit: 06b74be
/LLM/main/L0_MergeRequest_PR pipeline #33156 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

Link to invocation

Ethan Kou and others added 2 commits April 9, 2026 11:33
Signed-off-by: Ethan Kou <[email protected]>
@ekou24
Copy link
Copy Markdown
Contributor Author

ekou24 commented Apr 9, 2026

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42568 [ run ] triggered by Bot. Commit: 6df3876 Link to invocation

@ekou24
Copy link
Copy Markdown
Contributor Author

ekou24 commented Apr 10, 2026

/bot run --disable-fail-fast

@pcastonguay
Copy link
Copy Markdown
Collaborator

/bot kill

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42719 [ run ] triggered by Bot. Commit: 38c81b9 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42728 [ kill ] triggered by Bot. Commit: 38c81b9 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42719 [ run ] completed with state ABORTED. Commit: 38c81b9

Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42728 [ kill ] completed with state SUCCESS. Commit: 38c81b9
Successfully killed previous jobs for commit 38c81b9

Link to invocation

@pcastonguay
Copy link
Copy Markdown
Collaborator

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42739 [ run ] triggered by Bot. Commit: 38c81b9 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #42739 [ run ] completed with state SUCCESS. Commit: 38c81b9
/LLM/main/L0_MergeRequest_PR pipeline #33421 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

Link to invocation

@pcastonguay
Copy link
Copy Markdown
Collaborator

/bot run --disable-fail-fast

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #43030 [ run ] triggered by Bot. Commit: 38c81b9 Link to invocation

@pcastonguay pcastonguay enabled auto-merge (squash) April 13, 2026 12:33
@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #43030 [ run ] completed with state FAILURE. Commit: 38c81b9
/LLM/main/L0_MergeRequest_PR pipeline #33678 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

Link to invocation

@pcastonguay
Copy link
Copy Markdown
Collaborator

/bot skip --comment "Flaky SBSA tests"

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #43106 [ skip ] triggered by Bot. Commit: 38c81b9 Link to invocation

@tensorrt-cicd
Copy link
Copy Markdown
Collaborator

PR_Github #43106 [ skip ] completed with state SUCCESS. Commit: 38c81b9
Skipping testing for commit 38c81b9

Link to invocation

@pcastonguay pcastonguay merged commit a2557ad into NVIDIA:main Apr 13, 2026
5 checks passed
chienchunhung pushed a commit to chienchunhung/TensorRT-LLM that referenced this pull request Apr 16, 2026
NVIDIA#12554)

Signed-off-by: Ethan Kou <[email protected]>
Signed-off-by: Ethan Kou <[email protected]>
Signed-off-by: Ethan Kou <[email protected]>
Co-authored-by: Ethan Kou <[email protected]>
Co-authored-by: Ethan Kou <[email protected]>
Co-authored-by: Ethan Kou <[email protected]>
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.

3 participants