[TRTLLM-6675][infra] Nixl test completion #6623
Conversation
|
Caution Review failedFailed to post review comments. Configuration used: .coderabbit.yaml 📒 Files selected for processing (17)
✅ Files skipped from review due to trivial changes (7)
🚧 Files skipped from review as they are similar to previous changes (6)
🧰 Additional context used📓 Path-based instructions (2)**/*.py📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Files:
**/*.{cpp,h,hpp,cc,cxx,cu,py}📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
Files:
🧠 Learnings (6)📓 Common learnings📚 Learning: 2025-07-28T17:06:08.621ZApplied to files:
📚 Learning: 2025-08-06T13:58:07.506ZApplied to files:
📚 Learning: 2025-08-06T03:47:16.802ZApplied to files:
📚 Learning: 2025-08-06T03:47:16.802ZApplied to files:
📚 Learning: 2025-08-01T15:14:45.673ZApplied to files:
🔇 Additional comments (6)
📝 WalkthroughWalkthroughThis change adds new benchmarking and accuracy tests for disaggregated serving with different backends and models, including DeepSeek and Llama variants. It introduces new test methods, fixtures, and helper functions to support benchmarking, updates test list configurations to include these tests, and improves error handling in benchmark metric extraction. Changes
Sequence Diagram(s)sequenceDiagram
participant TestRunner
participant Server
participant MPIWorkers
participant BenchmarkScript
TestRunner->>MPIWorkers: Launch MPI worker processes
TestRunner->>Server: Start server with config
TestRunner->>Server: Warm up with client script
TestRunner->>BenchmarkScript: Run benchmark with model/config
BenchmarkScript->>Server: Send benchmark requests
Server->>BenchmarkScript: Respond with metrics
BenchmarkScript-->>TestRunner: Output metrics (E2EL, TTFT)
TestRunner->>MPIWorkers: Terminate
TestRunner->>Server: Terminate
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~18 minutes Suggested labels
Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. ✨ 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 comments)
Other keywords and placeholders
Documentation and Community
|
bo-nv
changed the title
|
/bot run --add-multi-gpu-test |
|
PR_Github #14121 [ run ] triggered by Bot |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 4
🧹 Nitpick comments (3)
tests/integration/test_lists/qa/examples_test_list.txt (1)
547-548: Maintain alphabetical ordering of test entriesThe two newly-added NIXL entries appear underneath miscellaneous lines that are still alphabetically ordered. To keep the long list diff-friendly and minimise future merge conflicts, please insert the new items in the correct alphabetical position (the block is roughly sorted by module name).
tests/integration/test_lists/qa/llm_sanity_test.txt (1)
104-105: Keep the sanity list deterministically orderedLike the main QA list, the sanity list is intended to stay stable between PRs. Please reorder the two new
test_nixl_backendlines so the file remains alphabetically sorted — this prevents noisy diffs when multiple developers touch the list.tensorrt_llm/serve/scripts/benchmark_serving.py (1)
582-585: Good defensive fix – minor naming nitThe added
if k in resultsguard neatly avoidsKeyErrors – nice!
Tiny readability nit: the local list is calledmetrics, and you also pass a named argumentmetrics=. Renaming the list to something likemetric_keyswould avoid the double meaning.- metrics = [ + metric_keys = [ "median_ttft_ms", "mean_ttft_ms", "std_ttft_ms", "p99_ttft_ms", @@ - metrics={k: [results[k]] for k in metrics if k in results}, + metrics={k: [results[k]] for k in metric_keys if k in results}, - for k in results if k not in metrics and k not in ignored_metrics + for k in results if k not in metric_keys and k not in ignored_metrics
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
tensorrt_llm/serve/scripts/benchmark_serving.py(1 hunks)tests/integration/defs/accuracy/test_disaggregated_serving.py(2 hunks)tests/integration/defs/disaggregated/test_disaggregated.py(2 hunks)tests/integration/test_lists/qa/examples_test_list.txt(1 hunks)tests/integration/test_lists/qa/llm_sanity_test.txt(1 hunks)tests/integration/test_lists/test-db/l0_dgx_b200.yml(1 hunks)tests/integration/test_lists/test-db/l0_dgx_h100.yml(2 hunks)
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: The code developed for TensorRT-LLM should conform to Python 3.8+.
Indent Python code with 4 spaces. Do not use tabs.
Always maintain the namespace when importing in Python, even if only one class or function from a module is used.
Python filenames should use snake_case (e.g., some_file.py).
Python classes should use PascalCase (e.g., class SomeClass).
Python functions and methods should use snake_case (e.g., def my_awesome_function():).
Python local variables should use snake_case. Prefix k for variable names that start with a number (e.g., k_99th_percentile).
Python global variables should use upper snake_case and prefix G (e.g., G_MY_GLOBAL).
Python constants should use upper snake_case (e.g., MY_CONSTANT).
Avoid shadowing variables declared in an outer scope in Python.
Initialize all externally visible members of a Python class in the constructor.
For interfaces that may be used outside a file, prefer docstrings over comments in Python.
Comments in Python should be reserved for code within a function, or interfaces that are local to a file.
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx.
Attributes and variables in Python can be documented inline; attribute docstrings will be rendered under the docstring for the class.
Avoid using reflection in Python when functionality can be easily achieved without reflection.
When using try-except blocks in Python, limit the except to the smallest set of errors possible.
When using try-except blocks to handle multiple possible variable types in Python, keep the body of the try as small as possible, using the else block to implement the logic.
Files:
tensorrt_llm/serve/scripts/benchmark_serving.pytests/integration/defs/accuracy/test_disaggregated_serving.pytests/integration/defs/disaggregated/test_disaggregated.py
**/*.{cpp,h,cu,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. This includes .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.
Files:
tensorrt_llm/serve/scripts/benchmark_serving.pytests/integration/defs/accuracy/test_disaggregated_serving.pytests/integration/defs/disaggregated/test_disaggregated.py
🧠 Learnings (2)
📓 Common 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.
📚 Learning: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...
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_sanity_test.txttests/integration/test_lists/test-db/l0_dgx_h100.ymltests/integration/test_lists/test-db/l0_dgx_b200.ymltests/integration/test_lists/qa/examples_test_list.txttests/integration/defs/accuracy/test_disaggregated_serving.pytests/integration/defs/disaggregated/test_disaggregated.py
🧬 Code Graph Analysis (1)
tests/integration/defs/accuracy/test_disaggregated_serving.py (1)
tests/integration/defs/accuracy/accuracy_core.py (4)
MMLU(269-283)evaluate(146-199)evaluate(678-688)GSM8K(286-299)
⏰ 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 (8)
tests/integration/test_lists/test-db/l0_dgx_b200.yml (1)
73-78: LGTM! Good test coverage for NIXL backend.The new test entries properly extend the test suite with:
- Four parameterized benchmark tests covering different model configurations (DeepSeek-V3-Lite with bf16/fp8, llama models)
- Two accuracy tests validating NIXL backend functionality
This aligns well with the PR objective to verify NIXL backend performance parity with UCX.
tests/integration/test_lists/test-db/l0_dgx_h100.yml (2)
53-54: LGTM! Consistent NIXL backend test additions.The accuracy tests for NIXL backend are properly added to the PyTorch backend pre_merge stage.
111-114: LGTM! Benchmark tests properly added to deepseek trigger section.The four parameterized benchmark tests are appropriately placed under the deepseek auto_trigger condition, maintaining consistency with the B200 configuration.
tests/integration/defs/accuracy/test_disaggregated_serving.py (2)
262-283: LGTM! Test properly validates NIXL backend with accuracy tasks.The test correctly:
- Configures both context and generation servers to use the "nixl" backend
- Launches the disaggregated LLM with appropriate configuration
- Runs both MMLU and GSM8K evaluation tasks to verify accuracy
This provides comprehensive validation of the NIXL backend functionality.
481-504: LGTM! Test configuration appropriate for DeepSeek model.The test properly uses
tensor_parallel_size=4which is appropriate for the DeepSeek-V3-Lite model requirements. The test structure follows the same pattern as the Llama test, ensuring consistency.tests/integration/defs/disaggregated/test_disaggregated.py (3)
30-33: LGTM! Cleanup properly extended for new config files.The cleanup function now removes the UCX and NIXL config files created during benchmark tests.
1061-1090: LGTM! Well-structured fixtures for benchmarking.The fixtures properly:
- Locate benchmark scripts and datasets
- Map model names to their paths with support for multiple model variants
- Follow the existing fixture patterns in the codebase
1206-1249: Well-implemented benchmark comparison test.The test effectively:
- Covers multiple model configurations through parameterization
- Creates appropriate config files for both backends
- Runs benchmarks and compares performance metrics
- Uses a reasonable 5% tolerance for performance parity validation
This provides comprehensive validation that NIXL backend achieves comparable performance to UCX as intended.
|
/bot run --add-multi-gpu-test |
|
PR_Github #14125 [ run ] triggered by Bot |
|
PR_Github #14121 [ run ] completed with state |
|
PR_Github #14125 [ run ] completed with state |
bo-nv
force-pushed
the
user/bo/add-more-nixl-tests
branch
from
c73f67d to
2b696f6
Compare
|
/bot run --add-multi-gpu-test |
|
PR_Github #14196 [ run ] triggered by Bot |
|
PR_Github #14196 [ run ] completed with state |
|
/bot run --add-multi-gpu-test |
|
PR_Github #14204 [ run ] triggered by Bot |
|
PR_Github #14204 [ run ] completed with state |
|
/bot run --add-multi-gpu-test |
1 similar comment
|
/bot run --add-multi-gpu-test |
|
PR_Github #14257 [ run ] triggered by Bot |
bo-nv
force-pushed
the
user/bo/add-more-nixl-tests
branch
from
2b696f6 to
f7345bf
Compare
|
/bot run --add-multi-gpu-test |
|
PR_Github #14295 [ run ] triggered by Bot |
|
PR_Github #14257 [ run ] completed with state |
|
PR_Github #14295 [ run ] completed with state |
bo-nv
force-pushed
the
user/bo/add-more-nixl-tests
branch
from
18c2bba to
078cd12
Compare
|
/bot run --add-multi-gpu-test |
There was a problem hiding this comment.
Actionable comments posted: 0
♻️ Duplicate comments (2)
tests/integration/defs/disaggregated/test_disaggregated.py (2)
1176-1185: Consider more robust metric parsing.The regex patterns assume a specific output format. Consider adding error handling for unexpected formats or logging the full output on parsing failure for debugging.
1279-1280: Improve assertion messages for better debugging.The assertions should provide more context when they fail to help with debugging performance regressions.
🧹 Nitpick comments (1)
tests/integration/defs/disaggregated/test_disaggregated.py (1)
1100-1100: Consider making number of ranks configurable.The hard-coded
num_rank = 2could be made configurable through a parameter to support different test configurations.-def run_disaggregated_benchmark(example_dir, - config_file, - benchmark_root, - benchmark_model_root, - shared_gpt_path, - env=None, - cwd=None): +def run_disaggregated_benchmark(example_dir, + config_file, + benchmark_root, + benchmark_model_root, + shared_gpt_path, + env=None, + cwd=None, + num_ranks=2):
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (7)
tensorrt_llm/serve/scripts/benchmark_serving.py(1 hunks)tests/integration/defs/accuracy/test_disaggregated_serving.py(2 hunks)tests/integration/defs/disaggregated/test_disaggregated.py(2 hunks)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/test-db/l0_dgx_b200.yml(1 hunks)tests/integration/test_lists/test-db/l0_dgx_h100.yml(2 hunks)
✅ Files skipped from review due to trivial changes (2)
- tests/integration/test_lists/qa/llm_function_full.txt
- tests/integration/test_lists/qa/llm_function_sanity.txt
🚧 Files skipped from review as they are similar to previous changes (4)
- tensorrt_llm/serve/scripts/benchmark_serving.py
- tests/integration/test_lists/test-db/l0_dgx_h100.yml
- tests/integration/test_lists/test-db/l0_dgx_b200.yml
- tests/integration/defs/accuracy/test_disaggregated_serving.py
🧰 Additional context used
📓 Path-based instructions (2)
**/*.py
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
**/*.py: Python code should conform to Python 3.8+.
Indent Python code with 4 spaces. Do not use tabs.
Always maintain the namespace when importing in Python, even if only one class or function from a module is used.
Python filenames should use snake_case (e.g., some_file.py).
Python classes should use PascalCase (e.g., class SomeClass).
Python functions and methods should use snake_case (e.g., def my_awesome_function():).
Python local variables should use snake_case. Prefix k for variable names that start with a number (e.g., k_99th_percentile).
Python global variables should use upper snake_case and prefix G (e.g., G_MY_GLOBAL).
Python constants should use upper snake_case (e.g., MY_CONSTANT).
Avoid shadowing variables declared in an outer scope in Python.
Initialize all externally visible members of a Python class in the constructor.
For interfaces that may be used outside a Python file, prefer docstrings over comments.
Comments in Python should be reserved for code within a function, or interfaces that are local to a file.
Use Google style docstrings for Python classes and functions, which can be parsed by Sphinx.
Attributes and variables in Python can be documented inline; attribute docstrings will be rendered under the class docstring.
Avoid using reflection in Python when functionality can be easily achieved without it.
When using try-except blocks in Python, limit the except to the smallest set of errors possible.
When using try-except blocks to handle multiple possible variable types in Python, keep the body of the try as small as possible, using the else block to implement the logic.
Files:
tests/integration/defs/disaggregated/test_disaggregated.py
**/*.{cpp,h,hpp,cc,cxx,cu,py}
📄 CodeRabbit Inference Engine (CODING_GUIDELINES.md)
All TensorRT-LLM Open Source Software code should contain an NVIDIA copyright header that includes the current year. This includes .cpp, .h, .cu, .py, and any other source files which are compiled or interpreted.
Files:
tests/integration/defs/disaggregated/test_disaggregated.py
🧠 Learnings (3)
📓 Common 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: 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.
📚 Learning: in tensorrt-llm testing, it's common to have both cli flow tests (test_cli_flow.py) and pytorch api ...
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/disaggregated/test_disaggregated.py
📚 Learning: in tensorrt-llm, test files (files under tests/ directories) do not require nvidia copyright headers...
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/defs/disaggregated/test_disaggregated.py
⏰ 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 (6)
tests/integration/defs/disaggregated/test_disaggregated.py (6)
17-17: LGTM on new imports.The new imports (
re,tempfile,yaml) and additional test utilities are appropriate for the benchmarking functionality being added.Also applies to: 19-19, 22-24
1059-1087: Well-structured fixtures for benchmarking.The fixtures properly scope resources and handle parameterization. The error handling in
benchmark_model_rootis appropriate for invalid model parameters.
1187-1202: Excellent error handling with detailed logging.The exception handling properly logs both worker and server outputs, which will be valuable for debugging benchmark failures.
1204-1238: Clean configuration generation function.The function properly parameterizes the backend and provides appropriate defaults for benchmarking scenarios.
1241-1257: Well-structured parameterized benchmark test.The test properly handles multiple model configurations and creates temporary config files for different backends.
1276-1278: Good performance metrics logging.The print statements provide useful visibility into the benchmark results for both backends.
|
PR_Github #14367 [ run ] triggered by Bot |
|
PR_Github #14367 [ run ] completed with state |
|
/bot run --add-multi-gpu-test |
|
PR_Github #14383 [ run ] triggered by Bot |
|
PR_Github #14383 [ run ] completed with state |
|
/bot run --add-multi-gpu-test |
|
PR_Github #14401 [ run ] triggered by Bot |
|
PR_Github #14401 [ run ] completed with state |
|
@bo-nv could we update the PR to target |
Signed-off-by: Bo Deng <[email protected]>
Signed-off-by: Bo Deng <[email protected]>
Signed-off-by: Bo Deng <[email protected]>
Signed-off-by: Bo Deng <[email protected]>
Signed-off-by: Bo Deng <[email protected]>
Signed-off-by: Bo Deng <[email protected]>
Signed-off-by: Bo Deng <[email protected]>
bo-nv
force-pushed
the
user/bo/add-more-nixl-tests
branch
from
e575080 to
b53bafa
Compare
|
/bot run --add-multi-gpu-test |
|
PR_Github #14496 [ run ] triggered by Bot |
|
PR_Github #14496 [ run ] completed with state |
Summary by CodeRabbit
Bug Fixes
New Features
Tests
Documentation
Chores
Description
The NIXL backend is introduced in https://github.com/NVIDIA/TensorRT-LLM/tree/ed801ff74b4b5bbfc3e381aa635624f0573cc68d/examples/disaggregated, this PR adds some tests to ensure nixl has similar perf with UCX and no accuracy issues.
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.