[None][test] Unwaive qwen3.5 test cases - #17472
Conversation
Signed-off-by: nv-guomingz <137257613+nv-guomingz@users.noreply.github.com>
WalkthroughThe integration waiver list removes obsolete Qwen3.5 397B NVFP4 and GB200 online EPLB skip entries. ADP4 TRTLLM and TEP4 entries remain. ChangesIntegration waiver cleanup
Estimated code review effort: 1 (Trivial) | ~2 minutes Possibly related PRs
Suggested reviewers: 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✨ Finishing Touches 💡 1🛠️ Fix failing CI checks 💡
🧪 Generate unit tests (beta)
Comment |
brnguyen2
left a comment
There was a problem hiding this comment.
Approving — the comments below are optional touch-ups, not blockers.
Two of the three bugs (6418830, 6462928) were never root-caused — they're moving to verify-to-close on "can't reproduce" rather than on a landed fix, so these unwaives are a bet that the flakiness is gone. Please confirm with a targeted CI run before merging: these cases live in post-merge / GB200 / B200 multi-GPU stages that a plain /bot run doesn't cover, so use /bot run --stage-list "DGX_B200-4_GPUs-PyTorch-3, GB200-4_GPUs-PyTorch-2" (adjust to the actual stages) and paste the result. Re-waiving one week later is worse than one extra pipeline now.
Notes on lines outside the diff:
- tests/integration/test_lists/waives.txt:84: https://nvbugs/6535767 is also the reason for this line (
TestNemotronV3Ultra::test_nvfp4_4gpus_static_eplb[moe_backend=CUTLASS]). If that bug is resolved enough to unwaiveTestQwen3_5_397B_A17B::test_nvfp4[adp4_cutedsl], this entry is stale too — either remove it in the same PR or re-file it under a distinct bug so the remaining waive has an accurate owner.
|
/bot run --disable-fail-fast |
|
PR_Github #65180 [ run ] triggered by Bot. Commit: |
Dev Engineer Review
tests/integration/test_lists/waives.txt.adp4_cutedslQA Engineer Review
test-db/orqa/files were modified.tests/integration/test_lists/waives.txt.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-compatibleorapi-breaking. Forapi-breaking, includeBREAKINGin 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.