[TRTLLM-12659][ci] move 3 python_scheduler chunked_prefill cases to post merge

[QiJune]

Move the following 3 single-GPU BF16 TestDeepSeekV3Lite::test_bfloat16_python_scheduler cases in l0_b200.yml from pre-merge to post-merge:

• [mtp_nextn=2-attention_dp=True-cuda_graph=True-overlap_scheduler=True-enable_chunked_prefill=True]
• [mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-enable_chunked_prefill=True]
• [mtp_nextn=0-attention_dp=True-cuda_graph=True-overlap_scheduler=True-enable_chunked_prefill=True]

Rationale:

• All three rank near the top of DGX_B200 PyTorch single-GPU pre-merge wall-time over the last 4 weeks (per-run average ≈ 20+ min, cumulative ≈ 1500+ min), slowing pre-merge turnaround.
• python_scheduler is an off-by-default, non-recommended path (the main path uses the C++ scheduler), so an exhaustive matrix is not warranted on every PR. The 4 sibling enable_chunked_prefill=False cases plus one mtp_nextn=2-attention_dp=False-enable_chunked_prefill=True remain in pre-merge as a smoke signal for python_scheduler + chunked_prefill.
• The full matrix continues to run in post-merge, so regressions are still caught.

Summary by CodeRabbit

• Tests
  • Adjusted test configurations, reorganizing parameterizations for specific test scenarios to a different test stage within the test suite.

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.

[coderabbitai]

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: dcb9d1b6-a41f-417a-a1ae-6eac1c82ed10

📥 Commits

Reviewing files that changed from the base of the PR and between 44d0b01 and 3e9aced.

📒 Files selected for processing (1)

• tests/integration/test_lists/test-db/l0_b200.yml

---

📝 Walkthrough

Walkthrough

The test plan file l0_b200.yml is adjusted by relocating DeepSeekV3Lite test_bfloat16_python_scheduler test cases with enable_chunked_prefill=True from one PyTorch conditional block to a later one, while three mtp_nextn=2 parameterizations remain in the earlier block.

Changes

Test Configuration Reorganization

Layer / File(s)	Summary
DeepSeekV3Lite chunked-prefill test relocation tests/integration/test_lists/test-db/l0_b200.yml	Test parameterization for DeepSeekV3Lite bfloat16 scheduler is reorganized: chunked-prefill=True cases (mtp_nextn=0 with both attention_dp variants, and mtp_nextn=2 with attention_dp=True) are moved from an earlier PyTorch block to a subsequent block, while mtp_nextn=2 cases without chunked prefill remain in the original position.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~5 minutes

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the specific change (moving 3 python_scheduler chunked_prefill test cases) and the target (post-merge), with the JIRA ticket [TRTLLM-12659] and type [ci] appropriately included.
Description check	✅ Passed	The description clearly explains what is being changed (3 specific test cases) and why (they consume excessive pre-merge time while being for non-recommended paths), with rationale and mitigation strategy documented.
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.

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

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

Tip

💬 Introducing Slack Agent: The best way for teams to turn conversations into code.

Slack Agent is built on CodeRabbit's deep understanding of your code, so your team can collaborate across the entire SDLC without losing context.

• Generate code and open pull requests
• Plan features and break down work
• Investigate incidents and troubleshoot customer tickets together
• Automate recurring tasks and respond to alerts with triggers
• Summarize progress and report instantly

Built for teams:

• Shared memory across your entire org—no repeating context
• Per-thread sandboxes to safely plan and execute work
• Governance built-in—scoped access, auditability, and budget controls

One agent for your entire SDLC. Right inside Slack.

👉 Get started

---

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

[lancelly]

LGTM~ Thx

[QiJune]

/bot skip --comment "trivial changes"

[tensorrt-cicd]

PR_Github #48145 [ skip ] triggered by Bot. Commit: 3e9aced Link to invocation

[tensorrt-cicd]

PR_Github #48145 [ skip ] completed with state SUCCESS. Commit: 3e9aced
Skipping testing for commit 3e9aced

Link to invocation