[TRTLLM-7250][fix] waive failed cases #7292
Conversation
Signed-off-by: Xin He (SW-GPU) <[email protected]>
📝 WalkthroughWalkthroughAdds class-level skip decorators and a device-memory skip to TestGPTOSS; marks the "TRTLLM" moe_backend parameter as conditionally skipped pre-Blackwell. Updates integration waiver and QA test-list files to change which tests are waived and to normalize backend identifiers in manifests. Changes
Sequence Diagram(s)sequenceDiagram
autonumber
participant Runner as Test Runner
participant Class as TestGPTOSS
participant Param as ParamSet (moe_backend)
Note right of Class #DDEBF7: Class-level decorators: skip_pre_hopper, skip_less_device_memory
Runner->>Class: discover tests
alt class decorators decide SKIP
Class--)Runner: mark tests as SKIPPED (pre-hopper or low-memory)
else run tests
Class->>Param: iterate moe_backend values
alt moe_backend == "TRTLLM" and pre-blackwell
Param--)Class: pytest.param marked skip_pre_blackwell -> SKIP
else
Param->>Class: execute test case
Class--)Runner: report PASS/FAIL
end
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
Suggested reviewers
✨ Finishing Touches🧪 Generate unit tests
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. 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
SupportNeed help? Create a ticket on our support page for assistance with any issues or questions. CodeRabbit Commands (Invoked using PR/Issue comments)Type Other keywords and placeholders
Status, Documentation and Community
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
tests/integration/defs/accuracy/test_llm_api_pytorch.py (1)
2700-2701: Class-level gating for GPT-OSS is appropriate.Pre-Hopper skip and 100 GB/device memory guard align with the 120B model footprint.
If CI still OOMs at collect time, consider also guarding host RAM, mirroring other large-model tests:
@skip_pre_hopper @pytest.mark.skip_less_device_memory(100000) +@pytest.mark.skip_less_host_memory(1000000) class TestGPTOSS(LlmapiAccuracyTestHarness):
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (2)
tests/integration/defs/accuracy/test_llm_api_pytorch.py(3 hunks)tests/integration/test_lists/waives.txt(1 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Code must target Python 3.8+
Indent Python code with 4 spaces; do not use tabs
Preserve module namespaces when importing; import modules/packages and access members via the module (e.g., from package.subpackage import foo; foo.SomeClass())
Python file names should be snake_case
Python class names should be PascalCase
Python functions/methods and local variables should be snake_case; variables beginning with a number should be prefixed with k_ (e.g., k_99th_percentile)
Global variables should be UPPER_SNAKE_CASE prefixed with G_ (e.g., G_MY_GLOBAL); constants should be UPPER_SNAKE_CASE
Avoid shadowing variables from outer scopes; initialize all externally visible members in init
Prefer docstrings for interfaces used outside a file; comments should be reserved for in-function or file-local interfaces
Use Google-style docstrings for classes and functions; attributes and variables may be documented inline with trailing string literals
Avoid reflection when simpler, explicit code suffices (e.g., avoid dict(**locals()) patterns)
In try/except, catch the narrowest exceptions possible
For duck-typing patterns, keep the try body minimal and move logic to else to avoid masking unrelated failures
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
**/*.{c,cc,cpp,cxx,h,hh,hpp,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend the NVIDIA copyright header (current year) to all source files (.cpp, .h, .cu, .py, etc.)
Files:
tests/integration/defs/accuracy/test_llm_api_pytorch.py
🧠 Learnings (3)
📚 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/defs/accuracy/test_llm_api_pytorch.pytests/integration/test_lists/waives.txt
📚 Learning: 2025-07-22T08:33:49.109Z
Learnt from: yiqingy0
PR: NVIDIA/TensorRT-LLM#5198
File: jenkins/mergeWaiveList.py:0-0
Timestamp: 2025-07-22T08:33:49.109Z
Learning: In the TensorRT-LLM waive list merging system, removed lines are always located at the end of the merge waive lists, which is why the mergeWaiveList.py script uses reverse traversal - it's an optimization for this specific domain constraint.
Applied to files:
tests/integration/test_lists/waives.txt
📚 Learning: 2025-08-26T09:49:04.938Z
Learnt from: pengbowang-nv
PR: NVIDIA/TensorRT-LLM#7192
File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72
Timestamp: 2025-08-26T09:49:04.938Z
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 (2)
348-351: Targeted waives for Llama4-EAGLE3 and Nixl backend look good.Entries match existing test node ids (tp8 + torch_compile variants; disaggregated nixl backend) and are appended at file end, consistent with our waive-list merge convention.
348-351: Sanity Check Passed: No stale TRTLLM waives foundThe verification script confirms that there are no remaining uppercase
TRTLLMor lowercasetrtllmwaives intests/integration/test_lists/waives.txt. No further changes are needed here.tests/integration/defs/accuracy/test_llm_api_pytorch.py (2)
2745-2750: Same gating applied to 4-GPU path: looks consistent.Keeps TRTLLM only on SM100+; aligns with waiver removals.
2713-2718: Tests correctly gate TRTLLM on pre-Blackwell and no stale waives remain
- Parametrize block in tests/integration/defs/accuracy/test_llm_api_pytorch.py at lines 2716 and 2748 uses ids=["cutlass","trtllm","triton"], confirming lower-case “trtllm” and proper skip_pre_blackwell marks.
- Searched waives list (tests/integration/test_lists/waives.txt) and found no entries referencing uppercase “TRTLLM”; all waives use lower-case segments and remain valid.
Signed-off-by: Xin He (SW-GPU) <[email protected]>
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (2)
tests/integration/test_lists/qa/llm_function_sanity.txt (1)
51-59: Normalize backend ordering to match other lists.Here it’s [cutlass, triton, trtllm], while llm_function_full.txt uses [cutlass, trtllm, triton]. Aligning order cuts diff churn.
-accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-cutlass] -accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-triton] -accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-trtllm] -accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-cutlass] -accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-triton] -accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-trtllm] -accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-cutlass] -accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-triton] -accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-trtllm] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-cutlass] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-trtllm] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[dp4-triton] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-cutlass] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-trtllm] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-triton] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-cutlass] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-trtllm] +accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-triton]tests/integration/test_lists/waives.txt (1)
348-351: No duplicate waiver entries foundI ran the duplicate-scan script against
tests/integration/test_lists/waives.txtand found no conflicting SKIP entries. The immediate issue is resolved. To prevent future duplicates (e.g. with or without"full:"prefixes), consider adding this guard into your CI pipeline:
- Add a CI job that runs:
sed -E 's/[[:space:]]+SKIP.*$//' tests/integration/test_lists/waives.txt \ | sort | uniq -d \ && { echo "Duplicate waiver entries detected"; exit 1; } || exit 0
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
💡 Knowledge Base configuration:
- MCP integration is disabled by default for public repositories
- Jira integration is disabled by default for public repositories
- Linear integration is disabled by default for public repositories
You can enable these sources in your CodeRabbit configuration.
📒 Files selected for processing (3)
tests/integration/test_lists/qa/llm_function_full.txt(1 hunks)tests/integration/test_lists/qa/llm_function_sanity.txt(1 hunks)tests/integration/test_lists/waives.txt(1 hunks)
🧰 Additional context used
🧠 Learnings (3)
📚 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/qa/llm_function_sanity.txttests/integration/test_lists/qa/llm_function_full.txttests/integration/test_lists/waives.txt
📚 Learning: 2025-08-06T13:58:07.506Z
Learnt from: galagam
PR: NVIDIA/TensorRT-LLM#6487
File: tests/unittest/_torch/auto_deploy/unit/singlegpu/test_ad_trtllm_bench.py:1-12
Timestamp: 2025-08-06T13:58:07.506Z
Learning: In TensorRT-LLM, test files (files under tests/ directories) do not require NVIDIA copyright headers, unlike production source code files. Test files typically start directly with imports, docstrings, or code.
Applied to files:
tests/integration/test_lists/qa/llm_function_full.txt
📚 Learning: 2025-08-26T09:49:04.938Z
Learnt from: pengbowang-nv
PR: NVIDIA/TensorRT-LLM#7192
File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72
Timestamp: 2025-08-26T09:49:04.938Z
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/qa/llm_function_full.txttests/integration/test_lists/waives.txt
🔇 Additional comments (3)
tests/integration/test_lists/qa/llm_function_full.txt (2)
542-550: Lowercasing backend identifiers is good; reduces case-sensitive dup hazards.The tp4/ep4/dp4 backends normalized to lowercase look consistent with waives and should prevent accidental duplicates in dashboards.
542-550: Remove remaining uppercase backend tokensThe repo-wide grep still finds uppercase CUTLASS, TRTLLM, and TRITON tokens in several test-list files; these must be converted to their lowercase equivalents (cutlass, trtllm, triton) to match the new naming convention and prevent CI failures.
• tests/integration/test_lists/waives.txt: line 318
• tests/integration/test_lists/test-db/**/.yml (multiple l0_ configurations)Please update all of these entries and integrate the provided grep script into your CI pipeline to catch any future regressions.
⛔ Skipped due to learnings
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.Learnt from: pengbowang-nv PR: NVIDIA/TensorRT-LLM#7192 File: tests/integration/test_lists/test-db/l0_dgx_b200.yml:56-72 Timestamp: 2025-08-26T09:49:04.938Z 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*").tests/integration/test_lists/waives.txt (1)
340-342: Confirm intent: waive only CUTLASS for GPTOSS w4_4gpus.Given class-level skips conditionally cover TRTLLM/TRITON pre-Blackwell, waiving only cutlass may be intentional. Please confirm this aligns with the new gating in accuracy/test_llm_api_pytorch.py.
xinhe-nv
changed the title
xinhe-nv
changed the title
2 participants
Summary by CodeRabbit
Description
https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/DEBUG_LLM_FUNCTION_TEST/1670/console
Test Coverage
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 thestage-listparameter 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.mdand the
scripts/test_to_stage_mapping.pyhelper.kill
killKill all running builds associated with pull request.
skip
skip --comment COMMENTSkip 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-pipelineReuse 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.