[TRTLLM-12358][chore] Dedup multimodal unit tests on B200

[QiJune]

Summary

• tests/integration/test_lists/test-db/l0_b200.yml schedules 6 files under unittest/_torch/multimodal/ on the DGX_B200 stage. Five of them are pure Python plumbing with no SM-specific code path (test_multimodal_runtime, test_find_num_image_tokens, test_fuse_input_embeds, test_external_embedding, test_share_multiparams) and test_mm_encoder_standalone.py's model_dir fixture has 4 parametrize values, of which only qwen3_30b_a3b_fp8 exercises a Blackwell-only path (FP8 MoE + DEEPGEMM backend, gated by _get_moe_config_for_blackwell() → get_sm_version() >= 100). The other three (llava_7b, qwen2.5_3b, qwen3_2b) are dense bf16 and run identical kernels on Hopper.

• Replace the six entries with one line that filters the encoder test to unittest/_torch/multimodal/test_mm_encoder_standalone.py -k "qwen3_30b_a3b_fp8".

• Coverage is preserved on Hopper: l0_h100.yml:44 runs the whole unittest/_torch/multimodal directory, so the five dropped files and the dense bf16 parametrize variants are still exercised.

• Savings on the DGX_B200 single-GPU PyTorch stage (90-day OS averages): before ≈ 40.4 min/run (37.1 + 0.4 + 1.8 + 0.4 + 0.4 + 0.4); after ≈ 5.9 min/run (3 FP8 tests). ~33 min/PR saved on this stage.

@coderabbitai summary

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]

📝 Walkthrough

Walkthrough

The l0_b200.yml test configuration is updated to reduce multimodal test coverage: five multimodal test modules are removed, one is retained with a specific test case filter, and inline comments are added to document the hardware and test scope decisions.

Changes

Cohort / File(s)	Summary
Test Configuration Updates tests/integration/test_lists/test-db/l0_b200.yml	Removes five multimodal test modules from B-tier coverage, retains test_mm_encoder_standalone.py with -k qwen3_30b_a3b_fp8 filter, and adds documentation comments regarding hardware and test-scope split.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	The PR description includes a detailed technical summary explaining the rationale for test deduplication and projected savings, but the required template sections (Description, Test Coverage, PR Checklist details) are empty.	Fill in the 'Description' and 'Test Coverage' template sections to clarify how this change aligns with repository guidelines, and confirm all PR checklist items have been reviewed.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly summarizes the main change: deduplication of multimodal unit tests on B200 hardware, and includes proper JIRA ticket and chore type.
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

---

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

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@tests/integration/test_lists/test-db/l0_b200.yml`:
- Around line 121-123: Add an explicit QA-list impact sentence to the B200
multimodal comment clarifying whether the QA schedule must be updated: state
that the B-tier reduction only removes dense bf16 coverage on B200 because FP8
MoE is run (DEEPGEMM is SM100-only via _get_moe_config_for_blackwell) and that
dense bf16 remains covered on Hopper, so no change to the QA list is required;
if instead you intend a QA change, add a brief note specifying an entry for the
B200 FP8-MoE exclusion in the qa list.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 34b29247-0f2a-458d-ba3e-c48b8360bcfe

📥 Commits

Reviewing files that changed from the base of the PR and between b5c41f2 and 915e2d0.

📒 Files selected for processing (1)

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

[chang-l]

LGTM

[QiJune]

/bot help

[github-actions]

GitHub Bot Help

/bot [-h] ['run', 'kill', 'skip', 'reuse-pipeline'] ...

Provide a user friendly way for developers to interact with a Jenkins server.

Run /bot [-h|--help] to print this help message.

See details below for each supported subcommand.

Details

run [--reuse-test (optional)pipeline-id --disable-fail-fast --skip-test --stage-list "A10-PyTorch-1, xxx" --gpu-type "A30, H100_PCIe" --test-backend "pytorch, cpp" --add-multi-gpu-test --only-multi-gpu-test --disable-multi-gpu-test --post-merge --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" --detailed-log --debug(experimental) --high-priority]

Launch build/test pipelines. All previously running jobs will be killed.

--reuse-test (optional)pipeline-id (OPTIONAL) : Allow the new pipeline to reuse build artifacts and skip successful test stages from a specified pipeline or the last pipeline if no pipeline-id is indicated. If the Git commit ID has changed, this option will be always ignored. The DEFAULT behavior of the bot is to reuse build artifacts and successful test results from the last pipeline.

--disable-reuse-test (OPTIONAL) : Explicitly prevent the pipeline from reusing build artifacts and skipping successful test stages from a previous pipeline. Ensure that all builds and tests are run regardless of previous successes.

--disable-fail-fast (OPTIONAL) : Disable fail fast on build/tests/infra failures.

--skip-test (OPTIONAL) : Skip all test stages, but still run build stages, package stages and sanity check stages. Note: Does NOT update GitHub check status.

--stage-list "A10-PyTorch-1, xxx" (OPTIONAL) : Only run the specified test stages. Supports wildcard * for pattern matching (e.g., "*PerfSanity*" matches all stages containing PerfSanity). Examples: "A10-PyTorch-1, xxx", "PerfSanity". Note: Does NOT update GitHub check status.

--gpu-type "A30, H100_PCIe" (OPTIONAL) : Only run the test stages on the specified GPU types. Examples: "A30, H100_PCIe". Note: Does NOT update GitHub check status.

--test-backend "pytorch, cpp" (OPTIONAL) : Skip test stages which don't match the specified backends. Only support [pytorch, cpp, tensorrt, triton]. Examples: "pytorch, cpp" (does not run test stages with tensorrt or triton backend). Note: Does NOT update GitHub pipeline status.

--only-multi-gpu-test (OPTIONAL) : Only run the multi-GPU tests. Note: Does NOT update GitHub check status.

--disable-multi-gpu-test (OPTIONAL) : Disable the multi-GPU tests. Note: Does NOT update GitHub check status.

--add-multi-gpu-test (OPTIONAL) : Force run the multi-GPU tests in addition to running L0 pre-merge pipeline.

--post-merge (OPTIONAL) : Run the L0 post-merge pipeline instead of the ordinary L0 pre-merge pipeline.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Supports wildcard * for pattern matching. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx", --extra-stage "Post-Merge".

--detailed-log (OPTIONAL) : Enable flushing out all logs to the Jenkins console. This will significantly increase the log volume and may slow down the job.

--debug (OPTIONAL) : Experimental feature. Enable access to the CI container for debugging purpose. Note: Specify exactly one stage in the stage-list parameter to access the appropriate container environment. Note: Does NOT update GitHub check status.

--high-priority (OPTIONAL) : Run the pipeline with high priority. This option is restricted to authorized users only and will route the job to a high-priority queue.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip testing for latest commit on pull request. --comment "Reason for skipping build/test" is required. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

reuse-pipeline

reuse-pipeline

Reuse a previous pipeline to validate current commit. This action will also kill all currently running builds associated with the pull request. IMPORTANT NOTE: This is dangerous since lack of user care and validation can cause top of tree to break.

[QiJune]

/bot skip --comment "trivial changes"

[tensorrt-cicd]

PR_Github #46044 [ skip ] triggered by Bot. Commit: 915e2d0 Link to invocation

[tensorrt-cicd]

PR_Github #46044 [ skip ] completed with state SUCCESS. Commit: 915e2d0
Skipping testing for commit 915e2d0

Link to invocation