[None][feat] Add layer wise benchmarks #8777
Conversation
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
|
/bot run |
📝 WalkthroughWalkthroughThis PR introduces layer-wise benchmarking infrastructure for DeepSeek models, including configuration files, MPI/Slurm launch scripts, a Python runner implementation with customizable MoE routing strategies, a standalone benchmark runner script, and corresponding test cases. Changes
Sequence DiagramsequenceDiagram
participant User
participant run_single.sh
participant run_single.py
participant DeepSeekV3Runner
participant KVCacheManager
participant Profiler
User->>run_single.sh: Execute with config
run_single.sh->>run_single.sh: Setup MPI/OpenMPI env
run_single.sh->>run_single.sh: Enable nsys profiling (optional)
run_single.sh->>run_single.py: Execute benchmark script
run_single.py->>run_single.py: Parse YAML config + CLI args
run_single.py->>run_single.py: Initialize MPI context (rank, world_size)
run_single.py->>run_single.py: Set CUDA device
run_single.py->>DeepSeekV3Runner: Create instance
DeepSeekV3Runner->>DeepSeekV3Runner: Load model with custom RoutingMethod
DeepSeekV3Runner->>DeepSeekV3Runner: Apply MoE routing balance strategy
run_single.py->>KVCacheManager: Create KV cache manager
run_single.py->>DeepSeekV3Runner: Create run_pack (callable)
rect rgba(100, 200, 100, 0.3)
Note over run_single.py,Profiler: Warmup Phase
run_single.py->>Profiler: Start CUDA events
run_single.py->>DeepSeekV3Runner: Execute warmup iterations
run_single.py->>Profiler: Stop events (no timing)
end
rect rgba(100, 150, 255, 0.3)
Note over run_single.py,Profiler: Timed Profiling Phase
run_single.py->>Profiler: Enable CUDA profiler
run_single.py->>Profiler: Record CUDA events (timed runs)
run_single.py->>DeepSeekV3Runner: Execute benchmark iterations
opt CUDA Graph Enabled
run_single.py->>run_single.py: Capture CUDA graph
run_single.py->>run_single.py: Replay graph
end
run_single.py->>Profiler: Stop CUDA profiler
end
run_single.py->>run_single.py: Compute stats (min, max, mean, median, P90)
run_single.py->>User: Print timing statistics per rank
Estimated code review effort🎯 4 (Complex) | ⏱️ ~60 minutes Areas requiring extra attention:
Pre-merge checks and finishing touches❌ Failed checks (2 warnings)
✅ Passed checks (1 passed)
✨ Finishing touches
🧪 Generate unit tests (beta)
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: 7
🧹 Nitpick comments (3)
examples/layer_wise_benchmarks/mpi_launch.sh (1)
6-7: Consider quoting command substitution to prevent word splitting issues.The shellcheck warnings (SC2046) suggest quoting the command substitution. While word splitting is intentional here (unset needs multiple arguments), the current approach could fail if environment variable names contain special characters.
A more robust approach using a while-read loop:
-# Clear slurm envs -unset $(env | grep -i slurm | awk -F'=' '{print $1}') -unset $(env | grep MPI | awk -F'=' '{print $1}') +# Clear slurm envs +while IFS='=' read -r name _; do + unset "$name" +done < <(env | grep -i slurm) +while IFS='=' read -r name _; do + unset "$name" +done < <(env | grep MPI)tests/unittest/tools/test_layer_wise_benchmarks.py (1)
20-20: Remove unnecessary import.The
llm_rootimport on Line 20 is unnecessary becausellm_rootis a pytest fixture defined inconftest.pyand is automatically discovered by pytest. Thenoqadirective is flagged as unused (RUF100), and the import causes redefinition warnings (F811) whenllm_rootis used as a fixture parameter in the test functions.Apply this diff to remove the unnecessary import:
-from utils.cpp_paths import llm_root # noqa: F401examples/layer_wise_benchmarks/run_single.py (1)
148-149: Consider usingitertools.pairwise()for iterating over successive pairs.The current code uses
zip(events, events[1:])to iterate over successive pairs. Python 3.10+ providesitertools.pairwise()which is more explicit and readable for this pattern.Apply this diff:
+import itertools + import argparse # ... rest of imports ... # Print statistics # Print before `cudaProfilerStop` to ensure messages are included in the profile -time_list = [ - start.elapsed_time(stop) for start, stop in zip(events, events[1:]) -] +time_list = [ + start.elapsed_time(stop) for start, stop in itertools.pairwise(events) +]
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (13)
.gitignore(1 hunks)examples/layer_wise_benchmarks/README.md(1 hunks)examples/layer_wise_benchmarks/config_ctx.yaml(1 hunks)examples/layer_wise_benchmarks/config_gen.yaml(1 hunks)examples/layer_wise_benchmarks/mpi_launch.sh(1 hunks)examples/layer_wise_benchmarks/run_single.py(1 hunks)examples/layer_wise_benchmarks/run_single.sh(1 hunks)examples/layer_wise_benchmarks/slurm_alloc.sh(1 hunks)examples/layer_wise_benchmarks/slurm_init_containers.sh(1 hunks)examples/layer_wise_benchmarks/slurm_launch.sh(1 hunks)tensorrt_llm/tools/layer_wise_benchmarks/deepseekv3_runner.py(1 hunks)tests/integration/test_lists/test-db/l0_dgx_b200.yml(1 hunks)tests/unittest/tools/test_layer_wise_benchmarks.py(1 hunks)
🧰 Additional context used
📓 Path-based instructions (3)
**/*.{h,hpp,hh,hxx,cpp,cxx,cc,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Use only spaces, no tabs; indent with 4 spaces.
Files:
examples/layer_wise_benchmarks/run_single.pytensorrt_llm/tools/layer_wise_benchmarks/deepseekv3_runner.pytests/unittest/tools/test_layer_wise_benchmarks.py
**/*.py
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
**/*.py: Python code must target Python 3.8+.
Indent Python code with 4 spaces; do not use tabs.
Maintain module namespace when importing; prefer 'from package.subpackage import foo' then 'foo.SomeClass()' instead of importing the class directly.
Python filenames should be snake_case (e.g., some_file.py).
Python classes use PascalCase names.
Functions and methods use snake_case names.
Local variables use snake_case; prefix 'k' for variables that start with a number (e.g., k_99th_percentile).
Global variables use upper SNAKE_CASE prefixed with 'G' (e.g., G_MY_GLOBAL).
Constants use upper SNAKE_CASE (e.g., MY_CONSTANT).
Avoid shadowing variables from an outer scope.
Initialize all externally visible members of a class in the constructor.
Prefer docstrings for interfaces that may be used outside a file; comments for in-function or file-local interfaces.
Use Google-style docstrings for classes and functions (Sphinx-parsable).
Document attributes and variables inline so they render under the class/function docstring.
Avoid reflection when a simpler, explicit approach suffices (e.g., avoid dict(**locals()) patterns).
In try/except, catch the most specific exceptions possible.
For duck-typing try/except, keep the try body minimal and use else for the main logic.
Files:
examples/layer_wise_benchmarks/run_single.pytensorrt_llm/tools/layer_wise_benchmarks/deepseekv3_runner.pytests/unittest/tools/test_layer_wise_benchmarks.py
**/*.{cpp,cxx,cc,h,hpp,hh,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
Prepend the NVIDIA Apache-2.0 copyright header with current year to the top of all source files (e.g., .cpp, .h, .cu, .py).
Files:
examples/layer_wise_benchmarks/run_single.pytensorrt_llm/tools/layer_wise_benchmarks/deepseekv3_runner.pytests/unittest/tools/test_layer_wise_benchmarks.py
🧠 Learnings (12)
📚 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:
examples/layer_wise_benchmarks/README.mdtests/integration/test_lists/test-db/l0_dgx_b200.ymlexamples/layer_wise_benchmarks/run_single.pytests/unittest/tools/test_layer_wise_benchmarks.py
📚 Learning: 2025-08-20T07:43:36.447Z
Learnt from: ChristinaZ
PR: NVIDIA/TensorRT-LLM#7068
File: cpp/tensorrt_llm/kernels/moeTopKFuncs.cuh:169-172
Timestamp: 2025-08-20T07:43:36.447Z
Learning: In TensorRT-LLM MOE kernels, when processing up to 128 experts across 32 threads, each thread handles at most 4 experts (N < 5 constraint), where N represents candidates per thread rather than total system capacity.
Applied to files:
examples/layer_wise_benchmarks/README.md
📚 Learning: 2025-09-09T09:40:45.658Z
Learnt from: fredricz-20070104
PR: NVIDIA/TensorRT-LLM#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_dgx_b200.ymltests/unittest/tools/test_layer_wise_benchmarks.py
📚 Learning: 2025-09-17T02:48:52.732Z
Learnt from: tongyuantongyu
PR: NVIDIA/TensorRT-LLM#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_dgx_b200.ymltests/unittest/tools/test_layer_wise_benchmarks.py
📚 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/test-db/l0_dgx_b200.ymltests/unittest/tools/test_layer_wise_benchmarks.py
📚 Learning: 2025-08-22T19:08:10.822Z
Learnt from: yuanjingx87
PR: NVIDIA/TensorRT-LLM#7176
File: jenkins/L0_Test.groovy:361-389
Timestamp: 2025-08-22T19:08:10.822Z
Learning: In Slurm job monitoring scripts, when jobs have built-in timeouts configured (via --time parameter or partition/system timeouts), an additional timeout mechanism in the monitoring loop is typically unnecessary. When a Slurm job times out, it gets terminated and removed from the active queue, causing `squeue -j $jobId` to return non-zero and break monitoring loops naturally. The job's final status can then be checked via `sacct` to determine if it failed due to timeout.
Applied to files:
examples/layer_wise_benchmarks/slurm_alloc.sh
📚 Learning: 2025-08-20T15:04:42.885Z
Learnt from: dbari
PR: NVIDIA/TensorRT-LLM#7095
File: docker/Dockerfile.multi:168-168
Timestamp: 2025-08-20T15:04:42.885Z
Learning: In docker/Dockerfile.multi, wildcard COPY for benchmarks (${CPP_BUILD_DIR}/benchmarks/*Benchmark) is intentionally used instead of directory copy because the benchmarks directory contains various other build artifacts during C++ builds, and only specific benchmark executables should be copied to the final image.
Applied to files:
examples/layer_wise_benchmarks/slurm_launch.sh
📚 Learning: 2025-08-14T06:36:40.701Z
Learnt from: timlee0212
PR: NVIDIA/TensorRT-LLM#6886
File: tensorrt_llm/_torch/models/modeling_deepseekv3.py:0-0
Timestamp: 2025-08-14T06:36:40.701Z
Learning: In DeepSeek V3 model (tensorrt_llm/_torch/models/modeling_deepseekv3.py), the disagreement between AllReduce.__init__ guard and _compute_mlp_tp_size logic for MNNVL usage is expected by design. The AllReduce component and MLP TP-size computation intentionally use different criteria for MNNVL availability decisions.
Applied to files:
examples/layer_wise_benchmarks/config_gen.yaml
📚 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/unittest/tools/test_layer_wise_benchmarks.py
📚 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/unittest/tools/test_layer_wise_benchmarks.py
📚 Learning: 2025-08-11T20:09:24.389Z
Learnt from: achartier
PR: NVIDIA/TensorRT-LLM#6763
File: tests/integration/defs/triton_server/conftest.py:16-22
Timestamp: 2025-08-11T20:09:24.389Z
Learning: In the TensorRT-LLM test infrastructure, the team prefers simple, direct solutions (like hard-coding directory traversal counts) over more complex but robust approaches when dealing with stable directory structures. They accept the maintenance cost of updating tests if the layout changes.
Applied to files:
tests/unittest/tools/test_layer_wise_benchmarks.py
📚 Learning: 2025-08-01T15:14:45.673Z
Learnt from: yibinl-nvidia
PR: NVIDIA/TensorRT-LLM#6506
File: examples/models/core/mixtral/requirements.txt:3-3
Timestamp: 2025-08-01T15:14:45.673Z
Learning: In TensorRT-LLM, examples directory can have different dependency versions than the root requirements.txt file. Version conflicts between root and examples dependencies are acceptable because examples are designed to be standalone and self-contained.
Applied to files:
tests/unittest/tools/test_layer_wise_benchmarks.py
🧬 Code graph analysis (4)
examples/layer_wise_benchmarks/mpi_launch.sh (1)
tests/unittest/llmapi/apps/_test_disagg_serving_multi_nodes.py (1)
env(61-68)
examples/layer_wise_benchmarks/run_single.py (4)
tensorrt_llm/_torch/autotuner.py (2)
AutoTuner(514-959)autotune(213-245)tensorrt_llm/_torch/modules/multi_stream_utils.py (1)
with_multi_stream(26-32)tensorrt_llm/_utils.py (2)
local_mpi_rank(553-554)mpi_world_size(549-550)tensorrt_llm/tools/layer_wise_benchmarks/deepseekv3_runner.py (7)
BalanceMethod(30-34)DeepSeekV3Runner(140-413)create_mapping(396-413)create_kv_cache_manager(355-393)run_pack(331-338)create_run_pack(274-340)replace_routing_method(342-352)
tensorrt_llm/tools/layer_wise_benchmarks/deepseekv3_runner.py (9)
tensorrt_llm/_torch/attention_backend/utils.py (1)
get_attention_backend(15-37)tensorrt_llm/_torch/metadata.py (1)
KVCacheParams(9-31)tensorrt_llm/_torch/models/modeling_deepseekv3.py (2)
DeepseekV3DecoderLayer(930-1270)DeepseekV3Gate(651-717)tensorrt_llm/_torch/modules/fused_moe/fused_moe_wide_ep.py (1)
WideEPMoE(28-1073)tensorrt_llm/_torch/modules/linear.py (2)
Linear(1831-2056)WeightMode(35-41)tensorrt_llm/_torch/pyexecutor/_util.py (1)
get_kv_cache_manager_cls(48-56)tensorrt_llm/_torch/utils.py (2)
get_model_extra_attrs(64-65)model_extra_attrs(69-75)tensorrt_llm/_utils.py (3)
local_mpi_size(557-558)mpi_world_size(549-550)torch_dtype_to_binding(417-420)tensorrt_llm/models/modeling_utils.py (2)
QuantConfig(131-271)is_module_excluded_from_quantization(237-250)
tests/unittest/tools/test_layer_wise_benchmarks.py (2)
tests/integration/defs/trt_test_alternative.py (1)
check_call(250-258)tests/integration/defs/conftest.py (1)
llm_root(192-193)
🪛 Ruff (0.14.2)
examples/layer_wise_benchmarks/run_single.py
148-148: zip() without an explicit strict= parameter
Add explicit value for parameter strict=
(B905)
148-148: Prefer itertools.pairwise() over zip() when iterating over successive pairs
Replace zip() with itertools.pairwise()
(RUF007)
tensorrt_llm/tools/layer_wise_benchmarks/deepseekv3_runner.py
190-190: Unused function argument: cls
(ARG001)
256-256: Loop control variable name not used within loop body
(B007)
260-260: Loop control variable name not used within loop body
(B007)
265-265: zip() without an explicit strict= parameter
Add explicit value for parameter strict=
(B905)
265-265: Prefer itertools.pairwise() over zip() when iterating over successive pairs
Replace zip() with itertools.pairwise()
(RUF007)
283-284: Avoid specifying long messages outside the exception class
(TRY003)
tests/unittest/tools/test_layer_wise_benchmarks.py
20-20: Unused noqa directive (non-enabled: F401)
Remove unused noqa directive
(RUF100)
25-25: Redefinition of unused llm_root from line 20
(F811)
43-43: Redefinition of unused llm_root from line 20
(F811)
61-61: Redefinition of unused llm_root from line 20
(F811)
🪛 Shellcheck (0.11.0)
examples/layer_wise_benchmarks/mpi_launch.sh
[warning] 6-6: Quote this to prevent word splitting.
(SC2046)
[warning] 7-7: Quote this to prevent word splitting.
(SC2046)
Signed-off-by: Tailing Yuan <yuantailing@gmail.com>
yuantailing
force-pushed
the
layer_wise_benchmarks
branch
from
2692888 to
84f5eee
Compare
|
PR_Github #22998 [ run ] triggered by Bot. Commit: |
|
PR_Github #22998 [ run ] completed with state |
|
This is a very useful tool to simplify performance benchmarking/profiling complexities to benefit the team. Thanks |
Signed-off-by: Tailing Yuan <yuantailing@gmail.com> Signed-off-by: FredricZ-2007 <226039983+fredricz-20070104@users.noreply.github.com>
3 participants
Summary by CodeRabbit
New Features
Documentation
Tests
Chores
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.
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.