KEMBAR78
[None][ci] Test waives for the main branch 09/15 by chzblych · Pull Request #7709 · NVIDIA/TensorRT-LLM · GitHub
Skip to content

Conversation

@chzblych
Copy link
Collaborator

@chzblych chzblych commented Sep 15, 2025

Summary by CodeRabbit

  • Tests
    • Added a 90-second timeout to a long-running integration test to reduce hangs.
    • Expanded test waivers to skip known-flaky MOE CUTLASS variants and adjust accuracy/latency coverage for large-model scenarios.
    • No changes to product functionality; improvements target CI reliability and signal quality.

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

  • 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

/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.

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)]

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. Examples: "A10-PyTorch-1, xxx". 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. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx".

--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.

For guidance on mapping tests to stage names, see docs/source/reference/ci-overview.md
and the scripts/test_to_stage_mapping.py helper.

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.

@chzblych
Copy link
Collaborator Author

/bot run --stage-list "RTXPro6000-4_GPUs-PyTorch-Post-Merge-1, RTXPro6000-4_GPUs-PyTorch-Post-Merge-2, DGX_B200-4_GPUs-PyTorch-Post-Merge-1"

@coderabbitai
Copy link
Contributor

coderabbitai bot commented Sep 15, 2025

📝 Walkthrough

Walkthrough

Adds a 90-second timeout for a specific test path in l0_b200.yml and updates test waivers in waives.txt by adding several SKIP entries and modifying one existing accuracy waiver.

Changes

Cohort / File(s) Summary
Test DB Timeout Update
tests/integration/test_lists/test-db/l0_b200.yml
Converted unittest/_torch/thop/parallel entry to a timed entry with TIMEOUT (90) in pre_merge tests; no other changes.
Test Waivers Adjustments
tests/integration/test_lists/waives.txt
Added four SKIP/accuracy waiver entries for MOE CUTLASS scenarios (DeepSeekV3 Lite variants and Qwen3 30B A3B), and updated an accuracy waiver to target test_latency_moe_cutlass for Qwen3 235B A22B.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

Suggested reviewers

  • niukuo
  • omera-nv

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)
Check name Status Explanation Resolution
Description Check ⚠️ Warning The PR body contains only the repository template and placeholders (including the @coderabbitai marker) but does not include a filled Description, explicit Test Coverage, or a concise summary of what and why changes were made, so reviewers cannot determine intent or required verification steps from the PR itself. Please replace the template placeholders with a clear Description summarizing the concrete changes (e.g., tests/integration/test_lists/waives.txt SKIP entries added/updated and tests/integration/test_lists/test-db/l0_b200.yml test timeout added), list the relevant tests that verify these changes in the Test Coverage section, and complete the PR Checklist before requesting review.
✅ Passed checks (2 passed)
Check name Status Explanation
Title Check ✅ Passed The PR title "[None][ci] Test waives for the main branch 09/15" follows the repository's ticket/type pattern and concisely indicates a CI-related change to test waivers on main; it accurately reflects the primary change in the diff (modifications to test waiver entries and a test timeout). Minor issues: "waives" appears to be a typo for "waivers" and the trailing date is optional/noisy, but the title is not misleading and conveys the main intent.
Docstring Coverage ✅ Passed No functions found in the changes. Docstring coverage check skipped.
✨ Finishing touches
🧪 Generate unit tests
  • Create PR with unit tests
  • Post copyable unit tests in a comment

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between ddfe032 and 4496036.

📒 Files selected for processing (2)
  • tests/integration/test_lists/test-db/l0_b200.yml (1 hunks)
  • tests/integration/test_lists/waives.txt (1 hunks)
🧰 Additional context used
🧠 Learnings (5)
📓 Common learnings
Learnt from: Funatiq
PR: NVIDIA/TensorRT-LLM#6754
File: tests/integration/test_lists/test-db/l0_a30.yml:41-47
Timestamp: 2025-08-13T11:07:11.772Z
Learning: In TensorRT-LLM test configuration files like tests/integration/test_lists/test-db/l0_a30.yml, TIMEOUT values are specified in minutes, not seconds.
📚 Learning: 2025-08-13T11:07:11.772Z
Learnt from: Funatiq
PR: NVIDIA/TensorRT-LLM#6754
File: tests/integration/test_lists/test-db/l0_a30.yml:41-47
Timestamp: 2025-08-13T11:07:11.772Z
Learning: In TensorRT-LLM test configuration files like tests/integration/test_lists/test-db/l0_a30.yml, TIMEOUT values are specified in minutes, not seconds.

Applied to files:

  • tests/integration/test_lists/test-db/l0_b200.yml
📚 Learning: 2025-08-29T14:07:45.863Z
Learnt from: EmmaQiaoCh
PR: NVIDIA/TensorRT-LLM#7370
File: tests/unittest/trt/model_api/test_model_quantization.py:24-27
Timestamp: 2025-08-29T14:07:45.863Z
Learning: In TensorRT-LLM's CI infrastructure, pytest skip markers (pytest.mark.skip) are properly honored even when test files have __main__ blocks that call test functions directly. The testing system correctly skips tests without requiring modifications to the __main__ block execution pattern.

Applied to files:

  • tests/integration/test_lists/waives.txt
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.

Applied to files:

  • tests/integration/test_lists/waives.txt
📚 Learning: 2025-08-26T09:49:04.956Z
Learnt from: pengbowang-nv
PR: NVIDIA/TensorRT-LLM#7192
File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72
Timestamp: 2025-08-26T09:49:04.956Z
Learning: In TensorRT-LLM test configuration files, the test scheduling system handles wildcard matching with special rules that prevent duplicate test execution even when the same tests appear in multiple yaml files with overlapping GPU wildcards (e.g., "*b200*" and "*gb200*").

Applied to files:

  • tests/integration/test_lists/waives.txt
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (1)
  • GitHub Check: Pre-commit Check
🔇 Additional comments (4)
tests/integration/test_lists/waives.txt (3)

343-344: Approve — tp2pp2 waivers match parametrization

Verified: tp2pp2 appears in tests/integration/test_lists/waives.txt (lines 343–344) and in multiple test-db YAMLs (e.g. l0_rtx_pro_6000.yml, l0_gb200_multi_gpus.yml, l0_dgx_b200.yml); waives reference NVBUG 5512556.


349-349: Approve: Qwen3_30B_A3B CUTLASS waiver — bracketed params verified.
Bracketed params exactly match the test id (accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=True]); waiver present in tests/integration/test_lists/waives.txt:349 and test-db entry tests/integration/test_lists/test-db/l0_dgx_b200.yml:119.


351-351: Both TRTLLM and CUTLASS variants are now skipped — intentional?

tests/integration/test_lists/waives.txt — line 350 skips latency_moe_trtllm; line 351 skips latency_moe_cutlass (both reference https://nvbugs/5516666). If you meant to replace the TRTLLM entry with CUTLASS, remove the old entry; keep both only if intentional.

tests/integration/test_lists/test-db/l0_b200.yml (1)

59-59: TIMEOUT is in minutes — 90 = 90 minutes; confirm intent or change to 2 if you meant ~90s.

File: tests/integration/test_lists/test-db/l0_b200.yml:59

Repo scan shows many TIMEOUT entries use 90/180/240 (minutes) and the format "TIMEOUT (N)" with a space is common.

-  - unittest/_torch/thop/parallel TIMEOUT (90)
+  - unittest/_torch/thop/parallel TIMEOUT (2)

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

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

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18575 [ run ] triggered by Bot

@tensorrt-cicd
Copy link
Collaborator

PR_Github #18575 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #13946 (Partly Tested) completed with status: 'FAILURE'

Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
@chzblych chzblych merged commit 0c9430e into NVIDIA:main Sep 15, 2025
4 checks passed
@chzblych chzblych deleted the test-waive branch September 15, 2025 14:14
Wong4j pushed a commit to Wong4j/TensorRT-LLM that referenced this pull request Sep 20, 2025
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
MrGeva pushed a commit to nv-auto-deploy/TensorRT-LLM that referenced this pull request Sep 21, 2025
Signed-off-by: Yanchao Lu <yanchaol@nvidia.com>
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