[None][infra] separate AutoDeploy tests into own stages #10634
Conversation
|
/bot run --add-multi-gpu-test --disable-fail-fast |
lucaslie
changed the title
📝 WalkthroughWalkthroughThis pull request adds AutoDeploy backend support to the test infrastructure. The Jenkins Groovy script is updated to detect AutoDeploy stages and inject the appropriate backend parameter. Test configurations across multiple GPU platforms are refactored to consolidate AutoDeploy tests from inline blocks into dedicated AutoDeploy Backend Stages sections with explicit hardware and OS conditions. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~22 minutes 🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. 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. Comment |
![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
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
jenkins/L0_Test.groovy (1)
3157-3176: Fix--backend-modefiltering: AutoDeploy stages are currently treated as “no backend”.
BecausechangeMapomits"-AutoDeploy-", passing--backend-modecan unintentionally keep AutoDeploy stages inparallelJobsNoBackendeven when filtering to other backends (and you also can’t explicitly filter to AutoDeploy).Proposed diff
def changeMap = [ "pytorch": "-PyTorch-", "tensorrt": "-TensorRT-", "cpp": "-CPP-", "triton": "-Triton-", "fmha": "-FMHA-", + "autodeploy": "-AutoDeploy-", ]Also applies to: 3228-3229, 3268-3273, 3658-3674
🧹 Nitpick comments (1)
tests/integration/test_lists/test-db/l0_b200.yml (1)
169-185: Consider pinningorchestrator: mpifor the AutoDeploy block (consistency + future-proofing).
Other AutoDeploy blocks in this PR useorchestrator: mpi; leaving it unspecified can make the selection rules less explicit if new orchestrators/stages are introduced.Proposed diff
terms: stage: pre_merge backend: autodeploy + orchestrator: mpi tests: - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[False-1] - accuracy/test_llm_api_autodeploy.py::TestNemotronMOE::test_fp8 - unittest/_torch/auto_deploy/unit/singlegpu
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (8)
jenkins/L0_Test.groovytests/integration/test_lists/test-db/l0_a30.ymltests/integration/test_lists/test-db/l0_b200.ymltests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_dgx_b300.ymltests/integration/test_lists/test-db/l0_dgx_h100.ymltests/integration/test_lists/test-db/l0_dgx_h200.ymltests/integration/test_lists/test-db/l0_h100.yml
💤 Files with no reviewable changes (1)
- tests/integration/test_lists/test-db/l0_dgx_b300.yml
🧰 Additional context used
🧠 Learnings (7)
📚 Learning: 2025-08-26T09:49:04.956Z
Learnt from: pengbowang-nv
Repo: NVIDIA/TensorRT-LLM PR: 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/test-db/l0_a30.ymltests/integration/test_lists/test-db/l0_b200.ymltests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_h100.ymltests/integration/test_lists/test-db/l0_dgx_h200.ymltests/integration/test_lists/test-db/l0_dgx_h100.yml
📚 Learning: 2025-07-28T17:06:08.621Z
Learnt from: moraxu
Repo: NVIDIA/TensorRT-LLM PR: 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/test-db/l0_a30.ymltests/integration/test_lists/test-db/l0_b200.ymltests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_h100.ymltests/integration/test_lists/test-db/l0_dgx_h200.ymltests/integration/test_lists/test-db/l0_dgx_h100.yml
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
Repo: NVIDIA/TensorRT-LLM PR: 7645
File: tests/integration/test_lists/qa/llm_function_core.txt:648-648
Timestamp: 2025-09-09T09:40:45.658Z
Learning: In TensorRT-LLM test lists, it's common and intentional for the same test to appear in multiple test list files when they serve different purposes (e.g., llm_function_core.txt for comprehensive core functionality testing and llm_function_core_sanity.txt for quick sanity checks). This duplication allows tests to be run in different testing contexts.
Applied to files:
tests/integration/test_lists/test-db/l0_a30.ymltests/integration/test_lists/test-db/l0_b200.ymltests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/test-db/l0_h100.ymltests/integration/test_lists/test-db/l0_dgx_h200.ymltests/integration/test_lists/test-db/l0_dgx_h100.yml
📚 Learning: 2025-08-29T14:07:45.863Z
Learnt from: EmmaQiaoCh
Repo: NVIDIA/TensorRT-LLM PR: 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/test-db/l0_a30.yml
📚 Learning: 2025-09-17T02:48:52.732Z
Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 7781
File: tests/integration/test_lists/waives.txt:313-313
Timestamp: 2025-09-17T02:48:52.732Z
Learning: In TensorRT-LLM, `tests/integration/test_lists/waives.txt` is specifically for waiving/skipping tests, while other test list files like those in `test-db/` and `qa/` directories are for different test execution contexts (pre-merge, post-merge, QA tests). The same test appearing in both waives.txt and execution list files is intentional - the test is part of test suites but will be skipped due to the waiver.
Applied to files:
tests/integration/test_lists/test-db/l0_h100.ymltests/integration/test_lists/test-db/l0_dgx_h200.yml
📚 Learning: 2025-08-06T13:58:07.506Z
Learnt from: galagam
Repo: NVIDIA/TensorRT-LLM PR: 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/test-db/l0_h100.ymltests/integration/test_lists/test-db/l0_dgx_h200.yml
📚 Learning: 2025-11-14T11:22:03.729Z
Learnt from: nzmora-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 9163
File: tensorrt_llm/_torch/auto_deploy/custom_ops/quant.py:107-113
Timestamp: 2025-11-14T11:22:03.729Z
Learning: In TensorRT-LLM AutoDeploy custom ops, when adding hardware capability checks to select between kernel implementations (e.g., cuBLAS vs. CUDA kernel), use descriptive variable names that identify the specific GPU architectures or families being targeted (e.g., `is_blackwell_geforce_or_ada`) rather than generic names like `enable_cuda_core`. This makes it clear that the code is selecting an implementation path based on hardware capabilities, not enabling/disabling hardware features.
Applied to files:
tests/integration/test_lists/test-db/l0_dgx_h200.ymljenkins/L0_Test.groovy
⏰ 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). (2)
- GitHub Check: Check PR Checklist Resolution
- GitHub Check: Pre-commit Check
🔇 Additional comments (6)
tests/integration/test_lists/test-db/l0_dgx_h100.yml (1)
301-334: LGTM! AutoDeploy tests are cleanly separated into dedicated backend stages.The new
autodeploybackend sections correctly mirror the existing condition block structure, with appropriate GPU count ranges, wildcards, and orchestrator settings. The test paths (auto_deploy/,test_llm_api_autodeploy.py) are clearly AutoDeploy-specific, which aligns well with the PR objective of isolating these tests for faster triage.The Jenkins pipeline already properly handles the new
backend: autodeployvalue—the L0_Test.groovy script includes conditional logic (lines 2151-2154) that detects stage names containing "-AutoDeploy-" and addsbackend=autodeployto the Mako arguments, ensuring these tests are routed to the correct stages.tests/integration/test_lists/test-db/l0_a30.yml (1)
246-260: LGTM! New AutoDeploy backend stage follows existing patterns.The new section is well-structured with:
- Clear comment header separating AutoDeploy tests
- Condition block matching other single-GPU pre_merge configurations
- Appropriate
backend: autodeployterm for the new backend typeThe Jenkins pipeline is properly configured to detect and handle AutoDeploy stages—the L0_Test.groovy script checks for "-AutoDeploy-" in the stage name and injects
backend=autodeployto the mako arguments for test execution.tests/integration/test_lists/test-db/l0_dgx_h200.yml (1)
217-234: Add missingpre_mergeAutoDeploy Backend section for H200 consistency.The
post_mergeAutoDeploy Backend Stages block is well-structured and consistent with existing patterns. However, this file is missing thepre_mergeAutoDeploy configuration that exists in comparable GPU files (l0_dgx_h100.yml, l0_h100.yml, l0_dgx_b200.yml, l0_b200.yml, l0_a30.yml).Add a
pre_mergeAutoDeploy Backend section to maintain consistency with other GPU configurations and ensure H200-based pre-merge AutoDeploy tests are properly included.⛔ Skipped due to learnings
Learnt from: pengbowang-nv Repo: NVIDIA/TensorRT-LLM PR: 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*").tests/integration/test_lists/test-db/l0_dgx_b200.yml (1)
202-218: AutoDeploy tests correctly isolated into a dedicated pre_merge backend block.
This keeps PyTorch failures and AutoDeploy failures independently triageable, while preserving the same GPU/OS/CPU gating.tests/integration/test_lists/test-db/l0_h100.yml (1)
419-442: AutoDeploy block looks consistent with the intended stage split.
backend: autodeploy+orchestrator: mpiunder a dedicated “AutoDeploy Backend Stages” section matches the PR goal and avoids mixing results with the PyTorch stage.jenkins/L0_Test.groovy (1)
2151-2157: AutoDeploy backend inference from stageName is clear and matches the new stage naming.
This should ensurerenderTestDB()scopes tobackend=autodeployfor “-AutoDeploy-” stages.
|
I already ran a test run on a different PR and it looks good to me: https://nv/trt-llm-cicd/job/helpers/job/PR_Github/31671/ |
|
PR_Github #31795 [ run ] triggered by Bot. Commit: |
|
PR_Github #31795 [ run ] completed with state
|
lucaslie
force-pushed
the
ll/separate_ad_test_stages
branch
2 times, most recently
from
43af61b to
f4c5e5e
Compare
|
/bot run --add-multi-gpu-test --disable-fail-fast |
|
PR_Github #31824 [ run ] triggered by Bot. Commit: |
|
/bot run --add-multi-gpu-test --disable-fail-fast --disable-reuse-test |
|
PR_Github #31828 [ run ] triggered by Bot. Commit: |
|
PR_Github #31828 [ run ] completed with state
|
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
lucaslie
force-pushed
the
ll/separate_ad_test_stages
branch
from
3e5946b to
265cf81
Compare
|
/bot run --add-multi-gpu-test --disable-fail-fast --disable-reuse-test |
|
PR_Github #31981 [ run ] triggered by Bot. Commit: |
|
PR_Github #31981 [ run ] completed with state
|
|
/bot run --add-multi-gpu-test --disable-fail-fast |
|
PR_Github #32018 [ run ] triggered by Bot. Commit: |
|
PR_Github #32018 [ run ] completed with state
|
|
/bot skip --comment "only updates test structure, all AutoDeploy tests are passing, no code changes" |
|
PR_Github #32060 [ skip ] triggered by Bot. Commit: |
|
PR_Github #32060 [ skip ] completed with state |
Signed-off-by: Lucas Liebenwein <11156568+lucaslie@users.noreply.github.com>
3 participants
@coderabbitai summary
Description
see title. Motivation: AutoDeploy failures are often unrelated to other failures and separating tests into its own stage should help isolate and triage issues faster. It also can help AutoDeploy developers to distinguish other CI failures from failures introduced in their PR.
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
/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)]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.