Skip to content

[https://nvbugs/6305404][chore] Unwaive DeepSeek V3 Lite L0 test - #16975

Open
Mgluhovskoi wants to merge 1 commit into
NVIDIA:mainfrom
Mgluhovskoi:agent/unwaive-nvbug-6305404
Open

[https://nvbugs/6305404][chore] Unwaive DeepSeek V3 Lite L0 test#16975
Mgluhovskoi wants to merge 1 commit into
NVIDIA:mainfrom
Mgluhovskoi:agent/unwaive-nvbug-6305404

Conversation

@Mgluhovskoi

@Mgluhovskoi Mgluhovskoi commented Jul 29, 2026

Copy link
Copy Markdown
Collaborator

Description

Remove the remaining waiver for NVBug 6305404:

accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=True-cuda_graph=False-overlap_scheduler=False-torch_compile=True-enable_chunked_prefill=False-v2_kv_cache=True]

The original failure reported an mpi4py _manager_spawn thread surviving test teardown. A review of the surviving dependency-upgrade CI reports did not find the same thread-leak signature in multiple runs. The overlapping stale piecewise CUDA Graph teardown issue was fixed by commit 211482b36ac94820465df1791e5e1bc20d61624e.

Unwaiving the test restores L0 coverage and lets current main determine whether any residual failure remains.

Dev Engineer Review

  • Updated tests/integration/test_lists/waives.txt to remove the mtp_nextn=0 waiver and add the corresponding mtp_nextn=2 waiver for DeepSeek V3 Lite bfloat16.
  • Change is limited in scope and preserves the existing test path, SKIP format, and NVBug reference.
  • No public API or code changes.

QA Engineer Review

  • No test-db/ or qa/ files were modified; only the waiver list changed.
  • The mtp_nextn=0 entry was removed and the mtp_nextn=2 entry was added.
  • Given the mixed CI results and unavailable definitive CBTS coverage data, verdict: needs follow-up.

Signed-off-by: Maxim Gluhovskoi <mgluhovskoi@nvidia.com>

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "DGX_H100-PyTorch-Post-Merge-1, DGX_H100-PyTorch-Post-Merge-2" --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62348 [ run ] triggered by Bot. Commit: 79e87b7 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62348 [ run ] completed with state FAILURE. Commit: 79e87b7
/LLM/main/L0_MergeRequest_PR pipeline #50515 (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

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "DGX_H100-PyTorch-Post-Merge-1" --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62556 [ run ] triggered by Bot. Commit: 79e87b7 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62556 [ run ] completed with state SUCCESS. Commit: 79e87b7
/LLM/main/L0_MergeRequest_PR pipeline #50700 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62591 [ run ] triggered by Bot. Commit: 79e87b7 Link to invocation

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "DGX_B200-PyTorch-1-cbts" --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62591 [ run ] completed with state SUCCESS. Commit: 79e87b7
/LLM/main/L0_MergeRequest_PR pipeline #50731 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

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62610 [ run ] triggered by Bot. Commit: 79e87b7 Link to invocation

Copy link
Copy Markdown
Collaborator Author

/bot run --stage-list "DGX_B200-PyTorch-1" --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62610 [ run ] completed with state FAILURE. Commit: 79e87b7
/LLM/main/L0_MergeRequest_PR pipeline #50751 (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

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62616 [ run ] triggered by Bot. Commit: 79e87b7 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62616 [ run ] completed with state SUCCESS. Commit: 79e87b7
/LLM/main/L0_MergeRequest_PR pipeline #50756 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

Copy link
Copy Markdown
Collaborator Author

/bot run --disable-fail-fast

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62629 [ run ] triggered by Bot. Commit: 79e87b7 Link to invocation

@tensorrt-cicd

Copy link
Copy Markdown
Collaborator

PR_Github #62629 [ run ] completed with state SUCCESS. Commit: 79e87b7
/LLM/main/L0_MergeRequest_PR pipeline #50769 completed with status: 'SUCCESS'

CI Report

Link to invocation

@Mgluhovskoi
Mgluhovskoi marked this pull request as ready for review July 30, 2026 17:10
@Mgluhovskoi
Mgluhovskoi requested review from a team as code owners July 30, 2026 17:10
@coderabbitai

coderabbitai Bot commented Jul 30, 2026

Copy link
Copy Markdown
Contributor

Review Change Stack

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: ac64fff2-389e-4a0d-a3ae-73f588c89cdb

📥 Commits

Reviewing files that changed from the base of the PR and between 4235bef and 79e87b7.

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

Walkthrough

The integration waiver for TestDeepSeekV3Lite::test_bfloat16 now skips the mtp_nextn=2 configuration instead of mtp_nextn=0.

Changes

Integration test waiver update

Layer / File(s) Summary
Adjust DeepSeek bfloat16 waiver
tests/integration/test_lists/waives.txt
The SKIP entry changes from mtp_nextn=0 to mtp_nextn=2, retaining the existing test name and NV bug reference.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Possibly related PRs

Suggested reviewers: dongxuy04

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name Status Explanation Resolution
Description check ⚠️ Warning The description explains the issue and fix, but it omits the template's Test Coverage and PR Checklist sections. Add a Test Coverage section and complete the PR Checklist, or state why they are not applicable.
✅ Passed checks (4 passed)
Check name Status Explanation
Title check ✅ Passed The title matches the change and follows the required NVBugs/type pattern.
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.
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests

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

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.

2 participants