Skip to content

[https://nvbugs/6890897][test] Fix startup telemetry architecture expectation and unwaive test - #20015

Merged
Mgluhovskoi merged 1 commit into
NVIDIA:mainfrom
Mgluhovskoi:fix/nvbug-6890897-startup-telemetry
Oct 9, 2026
Merged

Mgluhovskoi merged 1 commit into
NVIDIA:mainfrom
Mgluhovskoi:fix/nvbug-6890897-startup-telemetry

Conversation

@Mgluhovskoi

@Mgluhovskoi Mgluhovskoi commented Oct 9, 2026 •

Copy link
Copy Markdown
Collaborator

Summary

Fix the stale architecture assertion in test_startup_failure_context_e2e[after_model_config] to expect Qwen3ForCausalLM, matching the Qwen3-0.6B model selected by #19178. Remove the temporary waiver added in #19945 to restore CI coverage. No production telemetry changes.

Fixes NVBug 6890897.

Testing

  • Python syntax, architecture-expectation consistency, waiver-removal checks, and git diff --check passed.
  • Local E2E execution is blocked by incompatible TRT-LLM Python/compiled bindings in the available container and a missing Qwen3-0.6B checkpoint. Both startup-failure cases need validation in CI.

Dev Engineer Review

The changes are limited to a test expectation and a waiver removal. The after_model_config case now expects Qwen3ForCausalLM, consistent with the Qwen3-0.6B model used by the test. No production code changes are included. The supplied context reports that local E2E execution was blocked; CI validation remains necessary.

QA Engineer Review

The test test_startup_failure_context_e2e covers configuration-validation and post-model-configuration startup failures, including telemetry context and schema-valid event delivery. The after_model_config case now checks for Qwen3ForCausalLM. The waiver for this test case was removed from waives.txt. Search results show no matching entry in the integration test lists. Both startup-failure cases need CI validation. Coverage verdict: needs follow-up.

Per-File QA Perspective

  • tests/unittest/usage/test_e2e_capture.py: The E2E test checks startup-failure telemetry for two failure paths; the architecture expectation changed for after_model_config. No matching test entry appeared in tests/integration/test_lists/test-db/ or tests/integration/test_lists/qa/.
  • tests/integration/test_lists/waives.txt: The waiver entry for test_startup_failure_context_e2e[after_model_config] was removed. This restores the case from the skip list; CI should confirm that it runs successfully.

…nd unwaive test

Signed-off-by: Maxim Gluhovskoi <mgluhovskoi@nvidia.com>
@Mgluhovskoi
Mgluhovskoi requested a review from a team as a code owner October 9, 2026 02:13
@Mgluhovskoi
Mgluhovskoi requested a review from arysef October 9, 2026 02:13
@Mgluhovskoi

Copy link
Copy Markdown
Collaborator Author

/bot run

@Mgluhovskoi Mgluhovskoi changed the title [TRTLLM-16815][test] Fix startup telemetry architecture expectation and unwaive test [https://nvbugs/6890897][test] Fix startup telemetry architecture expectation and unwaive test Oct 9, 2026
@coderabbitai

coderabbitai Bot commented Oct 9, 2026 •

Copy link
Copy Markdown
Contributor

Review in Change Stack →

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration
  • Configuration used: Repository: NVIDIA/TensorRT-LLM/.coderabbit.yaml
  • Review profile: CHILL
  • Plan: Enterprise
  • Run ID: ce064a7c-8a68-44e9-96b0-354ba14da347
📥 Commits

Reviewing files that changed from the base of the PR and between cc63e66 and ad3ae07.

📒 Files selected for processing (2)
  • tests/integration/test_lists/waives.txt
  • tests/unittest/usage/test_e2e_capture.py
💤 Files with no reviewable changes (1)
  • tests/integration/test_lists/waives.txt

Included review availability: This review used your included allowance. Your plan provides up to 12 included reviews per hour; 10 remain after this review.


Walkthrough

The startup-failure test now expects Qwen3ForCausalLM for the post-model-configuration case. Its skip-list entry and NVBUG reference were removed.

Changes

Startup failure test

Layer / File(s) Summary
Update test expectation and waiver
tests/unittest/usage/test_e2e_capture.py, tests/integration/test_lists/waives.txt
The test now expects Qwen3ForCausalLM instead of LlamaForCausalLM. The skip-list entry for this test case and its NVBUG reference were removed.

Priority: ⬇️ Low

Estimated code review effort: 1 (Trivial) | ~5 minutes

Change: Other

Suggested reviewers: brnguyen2, arysef, bowenfu

Merge Risk: ⚪ Minimal · up to ad3ae

No actionable merge-blocking issue is established. The startup-failure cases still need the planned CI validation.

🚥 Pre-merge checks | ✅ 5
✅ Passed checks (5 passed)
Check name Status Explanation
Docstring Coverage Passed Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%. Docstring coverage is scoped to functions touched by this diff. Analyzed 1 functions across 1 files.
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.
Title check Passed The title clearly identifies the NVBugs issue, test scope, and primary fix. It is concise and directly matches the changes.
Description check Passed The description explains the stale architecture assertion, waiver removal, expected behavior, test results, and CI limitations. It uses Summary and Testing headings instead of the template's Descripti…
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create a new PR
  • Autopilot · Keep fixing CodeRabbit findings and required CI, and resolving merge conflicts

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

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #76854 [ run ] triggered by Bot. Commit: ad3ae07 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #76854 [ run ] completed with state SUCCESS. Commit: ad3ae07
/LLM/main/L0_MergeRequest_PR pipeline #63362 completed with status: 'SUCCESS'

CI Report

Link to invocation

@github-actions

github-actions Bot commented Oct 9, 2026

Copy link
Copy Markdown

Automatically added "ci: full pre-merge approved" because this PR has satisfied the required GitHub review approvals. Unresolved review conversations and other required checks remain independent merge requirements.

@Mgluhovskoi
Mgluhovskoi merged commit cbde30d into NVIDIA:main Oct 9, 2026
20 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants