[None][chore] Removing pybind11 bindings and references #10550
Conversation
|
/bot run |
|
PR_Github #31076 [ run ] triggered by Bot. Commit: |
|
PR_Github #31076 [ run ] completed with state |
Linda-Stadter
force-pushed
the
remove_pybind
branch
from
1d09db1 to
a03156a
Compare
|
/bot run |
|
PR_Github #31098 [ run ] triggered by Bot. Commit: |
|
PR_Github #31098 [ run ] completed with state
|
Signed-off-by: Linda-Stadter <[email protected]>
Linda-Stadter
force-pushed
the
remove_pybind
branch
from
a03156a to
39c405b
Compare
Linda-Stadter
changed the title
|
/bot run |
|
PR_Github #31289 [ run ] triggered by Bot. Commit: |
Signed-off-by: Linda-Stadter <[email protected]>
Signed-off-by: Linda-Stadter <[email protected]>
Linda-Stadter
force-pushed
the
remove_pybind
branch
from
39c405b to
de0e50d
Compare
|
/bot run |
Linda-Stadter
requested review from
QiJune,
kaiyux,
poweiw,
venkywonka and
yuanjingx87
|
PR_Github #31289 [ run ] completed with state
|
|
PR_Github #31290 [ run ] triggered by Bot. Commit: |
📝 WalkthroughWalkthroughThis PR removes all pybind11-based Python bindings and transitions the entire codebase to use nanobind exclusively. Changes include deleting ~80 pybind11 binding files, updating CMake to unconditionally build nanobind, removing pybind11 from build dependencies, and simplifying build scripts that previously supported multiple binding backends. Changes
Estimated code review effort🎯 5 (Critical) | ⏱️ ~90+ minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 2 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches
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: 1
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (55)
.github/CODEOWNERScpp/CMakeLists.txtcpp/tensorrt_llm/CMakeLists.txtcpp/tensorrt_llm/executor/cache_transmission/nixl_utils/CMakeLists.txtcpp/tensorrt_llm/executor/cache_transmission/nixl_utils/agentBindings.cppcpp/tensorrt_llm/executor/cache_transmission/nixl_utils/agentBindingsPybind.cppcpp/tensorrt_llm/nanobind/bindings.cppcpp/tensorrt_llm/pybind/CMakeLists.txtcpp/tensorrt_llm/pybind/batch_manager/algorithms.cppcpp/tensorrt_llm/pybind/batch_manager/algorithms.hcpp/tensorrt_llm/pybind/batch_manager/bindings.cppcpp/tensorrt_llm/pybind/batch_manager/bindings.hcpp/tensorrt_llm/pybind/batch_manager/buffers.cppcpp/tensorrt_llm/pybind/batch_manager/buffers.hcpp/tensorrt_llm/pybind/batch_manager/cacheTransceiver.cppcpp/tensorrt_llm/pybind/batch_manager/cacheTransceiver.hcpp/tensorrt_llm/pybind/batch_manager/kvCacheConnector.cppcpp/tensorrt_llm/pybind/batch_manager/kvCacheConnector.hcpp/tensorrt_llm/pybind/batch_manager/kvCacheManager.cppcpp/tensorrt_llm/pybind/batch_manager/kvCacheManager.hcpp/tensorrt_llm/pybind/batch_manager/llmRequest.cppcpp/tensorrt_llm/pybind/batch_manager/llmRequest.hcpp/tensorrt_llm/pybind/bindings.cppcpp/tensorrt_llm/pybind/common/bindTypes.hcpp/tensorrt_llm/pybind/common/customCasters.hcpp/tensorrt_llm/pybind/common/tllmExceptions.cppcpp/tensorrt_llm/pybind/common/tllmExceptions.hcpp/tensorrt_llm/pybind/executor/bindings.cppcpp/tensorrt_llm/pybind/executor/bindings.hcpp/tensorrt_llm/pybind/executor/executor.cppcpp/tensorrt_llm/pybind/executor/executor.hcpp/tensorrt_llm/pybind/executor/executorConfig.cppcpp/tensorrt_llm/pybind/executor/executorConfig.hcpp/tensorrt_llm/pybind/executor/request.cppcpp/tensorrt_llm/pybind/executor/request.hcpp/tensorrt_llm/pybind/process_group/bindings.cppcpp/tensorrt_llm/pybind/process_group/bindings.hcpp/tensorrt_llm/pybind/runtime/bindings.cppcpp/tensorrt_llm/pybind/runtime/bindings.hcpp/tensorrt_llm/pybind/runtime/hostfunc.cppcpp/tensorrt_llm/pybind/runtime/hostfunc.hcpp/tensorrt_llm/pybind/runtime/moeBindings.cppcpp/tensorrt_llm/pybind/runtime/moeBindings.hcpp/tensorrt_llm/pybind/testing/modelSpecBinding.cppcpp/tensorrt_llm/pybind/testing/modelSpecBinding.hcpp/tensorrt_llm/pybind/thop/bindings.cppcpp/tensorrt_llm/pybind/thop/bindings.hcpp/tensorrt_llm/pybind/userbuffers/bindings.cppcpp/tensorrt_llm/pybind/userbuffers/bindings.hdocs/source/legacy/advanced/executor.mdjenkins/Build.groovyjenkins/L0_MergeRequest.groovyjenkins/L0_Test.groovyscripts/build_wheel.pytests/integration/test_lists/test-db/l0_a10.yml
💤 Files with no reviewable changes (48)
- tests/integration/test_lists/test-db/l0_a10.yml
- cpp/tensorrt_llm/nanobind/bindings.cpp
- .github/CODEOWNERS
- cpp/tensorrt_llm/pybind/batch_manager/cacheTransceiver.h
- cpp/tensorrt_llm/pybind/runtime/moeBindings.h
- jenkins/Build.groovy
- cpp/tensorrt_llm/pybind/common/tllmExceptions.h
- cpp/tensorrt_llm/pybind/batch_manager/bindings.h
- cpp/tensorrt_llm/pybind/batch_manager/kvCacheConnector.h
- cpp/tensorrt_llm/pybind/common/bindTypes.h
- cpp/tensorrt_llm/pybind/executor/executorConfig.h
- cpp/tensorrt_llm/pybind/executor/request.h
- cpp/tensorrt_llm/pybind/runtime/bindings.h
- cpp/tensorrt_llm/pybind/testing/modelSpecBinding.h
- cpp/tensorrt_llm/pybind/thop/bindings.h
- cpp/tensorrt_llm/pybind/userbuffers/bindings.cpp
- cpp/tensorrt_llm/pybind/process_group/bindings.cpp
- cpp/tensorrt_llm/pybind/common/customCasters.h
- cpp/tensorrt_llm/pybind/batch_manager/llmRequest.cpp
- cpp/tensorrt_llm/pybind/batch_manager/algorithms.cpp
- cpp/tensorrt_llm/pybind/common/tllmExceptions.cpp
- cpp/tensorrt_llm/pybind/batch_manager/kvCacheConnector.cpp
- cpp/tensorrt_llm/pybind/runtime/hostfunc.h
- cpp/tensorrt_llm/pybind/executor/bindings.h
- cpp/tensorrt_llm/executor/cache_transmission/nixl_utils/agentBindingsPybind.cpp
- cpp/tensorrt_llm/pybind/runtime/hostfunc.cpp
- cpp/tensorrt_llm/pybind/batch_manager/llmRequest.h
- cpp/tensorrt_llm/pybind/runtime/bindings.cpp
- cpp/tensorrt_llm/pybind/batch_manager/algorithms.h
- cpp/tensorrt_llm/pybind/executor/executor.cpp
- cpp/tensorrt_llm/pybind/batch_manager/cacheTransceiver.cpp
- cpp/tensorrt_llm/pybind/batch_manager/buffers.cpp
- cpp/tensorrt_llm/pybind/userbuffers/bindings.h
- cpp/tensorrt_llm/pybind/batch_manager/buffers.h
- cpp/tensorrt_llm/pybind/batch_manager/kvCacheManager.cpp
- cpp/tensorrt_llm/pybind/bindings.cpp
- cpp/tensorrt_llm/pybind/executor/executorConfig.cpp
- cpp/tensorrt_llm/pybind/thop/bindings.cpp
- cpp/tensorrt_llm/pybind/executor/executor.h
- cpp/tensorrt_llm/pybind/batch_manager/kvCacheManager.h
- cpp/tensorrt_llm/pybind/testing/modelSpecBinding.cpp
- cpp/tensorrt_llm/pybind/process_group/bindings.h
- cpp/tensorrt_llm/pybind/CMakeLists.txt
- cpp/tensorrt_llm/pybind/runtime/moeBindings.cpp
- cpp/tensorrt_llm/pybind/batch_manager/bindings.cpp
- cpp/tensorrt_llm/pybind/executor/bindings.cpp
- jenkins/L0_Test.groovy
- cpp/tensorrt_llm/pybind/executor/request.cpp
🧰 Additional context used
📓 Path-based instructions (3)
**/*.{md,rst}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
When documenting CLI commands for TensorRT-LLM tools like
trtllm-serve,trtllm-bench, ortrtllm-eval, prefer using--configover--extra_llm_api_optionsfor specifying configuration files
Files:
docs/source/legacy/advanced/executor.md
**/*.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 Python modules, 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, with prefixkfor variable names that start with a number (e.g.,k_99th_percentile)
Python global variables should use upper snake_case with prefixG(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 Python interfaces that may be used outside a file, prefer docstrings over comments
Use comments in Python 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
Python attributes and variables can be documented inline with the format"""<type>: Description"""
Avoid using reflection in Python when functionality can be easily achieved without reflection
When using try-except blocks in Python, limit the except clause to the smallest set of errors possible
When using try-except blocks in Python to handle multiple possible variable types (duck-typing), keep the body of the try as small as possible and use the else block for the main logic
Files:
scripts/build_wheel.py
**/*.{cpp,cc,cxx,h,hpp,hxx,cu,cuh,py}
📄 CodeRabbit inference engine (CODING_GUIDELINES.md)
All TensorRT-LLM source files (.cpp, .h, .cu, .py, and other source files) should contain an NVIDIA copyright header with the year of latest meaningful modification
Files:
scripts/build_wheel.py
🧠 Learnings (11)
📚 Learning: 2025-09-23T15:01:00.070Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/kernels/nccl_device/config.cu:15-17
Timestamp: 2025-09-23T15:01:00.070Z
Learning: In TensorRT-LLM NCCL device kernels, the <sstream> header is not needed as an explicit include in config.cu because it's provided transitively through other headers. Local compilation testing confirms this works without the explicit include.
Applied to files:
cpp/tensorrt_llm/CMakeLists.txtcpp/tensorrt_llm/executor/cache_transmission/nixl_utils/CMakeLists.txtjenkins/L0_MergeRequest.groovy
📚 Learning: 2025-08-18T09:08:07.687Z
Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 6984
File: cpp/tensorrt_llm/CMakeLists.txt:297-299
Timestamp: 2025-08-18T09:08:07.687Z
Learning: In the TensorRT-LLM project, artifacts are manually copied rather than installed via `cmake --install`, so INSTALL_RPATH properties are not needed - only BUILD_RPATH affects the final artifacts.
Applied to files:
cpp/tensorrt_llm/CMakeLists.txtcpp/CMakeLists.txtcpp/tensorrt_llm/executor/cache_transmission/nixl_utils/CMakeLists.txt
📚 Learning: 2025-09-23T15:13:48.819Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/kernels/nccl_device/multimem.h:20-30
Timestamp: 2025-09-23T15:13:48.819Z
Learning: TRT-LLM targets modern CUDA toolkits that support FP8 datatypes, so cuda_fp8.h can be included unconditionally without version guards in TRT-LLM code.
Applied to files:
cpp/tensorrt_llm/CMakeLists.txtcpp/CMakeLists.txt
📚 Learning: 2025-09-16T09:30:09.716Z
Learnt from: tongyuantongyu
Repo: NVIDIA/TensorRT-LLM PR: 7763
File: cpp/tensorrt_llm/CMakeLists.txt:297-301
Timestamp: 2025-09-16T09:30:09.716Z
Learning: In the TensorRT-LLM project, NCCL libraries are loaded earlier by PyTorch libraries or the bindings library, so the main shared library doesn't need NCCL paths in its RPATH - the libraries will already be available in the process address space when needed.
Applied to files:
cpp/tensorrt_llm/CMakeLists.txtcpp/CMakeLists.txtcpp/tensorrt_llm/executor/cache_transmission/nixl_utils/CMakeLists.txtjenkins/L0_MergeRequest.groovy
📚 Learning: 2025-09-23T15:01:00.070Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/kernels/nccl_device/config.cu:15-17
Timestamp: 2025-09-23T15:01:00.070Z
Learning: In TensorRT-LLM NCCL device kernels (cpp/tensorrt_llm/kernels/nccl_device/config.cu), std::ostringstream is used but <sstream> doesn't need to be explicitly included because it's provided transitively through other headers like tensorrt_llm/common/cudaUtils.h or config.h. Local compilation testing confirms this works without the explicit include.
Applied to files:
cpp/tensorrt_llm/CMakeLists.txtjenkins/L0_MergeRequest.groovy
📚 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:
cpp/tensorrt_llm/CMakeLists.txtjenkins/L0_MergeRequest.groovy
📚 Learning: 2025-08-08T05:06:31.596Z
Learnt from: sklevtsov-nvidia
Repo: NVIDIA/TensorRT-LLM PR: 3294
File: cpp/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/epilogue/fusion/sm90_visitor_scatter.hpp:36-36
Timestamp: 2025-08-08T05:06:31.596Z
Learning: CUTLASS extension files (under cpp/tensorrt_llm/cutlass_extensions/) follow CUTLASS coding style conventions, including using #pragma once instead of TRTLLM_ prefixed header guards, even though they are .hpp files.
Applied to files:
cpp/tensorrt_llm/CMakeLists.txtcpp/tensorrt_llm/executor/cache_transmission/nixl_utils/CMakeLists.txtjenkins/L0_MergeRequest.groovy
📚 Learning: 2026-01-06T03:07:15.754Z
Learnt from: CR
Repo: NVIDIA/TensorRT-LLM PR: 0
File: CODING_GUIDELINES.md:0-0
Timestamp: 2026-01-06T03:07:15.754Z
Learning: Applies to **/*.{cpp,cc,cxx,h,hpp,hxx,cu,cuh,py} : All TensorRT-LLM source files (.cpp, .h, .cu, .py, and other source files) should contain an NVIDIA copyright header with the year of latest meaningful modification
Applied to files:
cpp/tensorrt_llm/CMakeLists.txtjenkins/L0_MergeRequest.groovy
📚 Learning: 2025-09-23T15:12:38.312Z
Learnt from: nv-lschneider
Repo: NVIDIA/TensorRT-LLM PR: 7910
File: cpp/tensorrt_llm/thop/allreduceOp.cpp:352-446
Timestamp: 2025-09-23T15:12:38.312Z
Learning: In TensorRT-LLM NCCL device implementation, NCCL version 2.28+ requirements are handled at runtime in the nccl_device/config layer rather than with compile-time guards. This allows the allreduceOp to remain version-agnostic and delegates version compatibility validation to the appropriate lower-level components that can gracefully handle unsupported configurations.
Applied to files:
cpp/tensorrt_llm/CMakeLists.txtjenkins/L0_MergeRequest.groovy
📚 Learning: 2025-10-22T06:53:47.017Z
Learnt from: xinhe-nv
Repo: NVIDIA/TensorRT-LLM PR: 8534
File: scripts/format_test_list.py:1-6
Timestamp: 2025-10-22T06:53:47.017Z
Learning: The file `scripts/format_test_list.py` in the TensorRT-LLM repository does not require the NVIDIA Apache-2.0 copyright header.
Applied to files:
jenkins/L0_MergeRequest.groovy
📚 Learning: 2025-08-21T21:48:35.135Z
Learnt from: djns99
Repo: NVIDIA/TensorRT-LLM PR: 7104
File: cpp/tensorrt_llm/cutlass_extensions/include/cutlass_extensions/epilogue/fusion/sm90_visitor_scatter.hpp:399-417
Timestamp: 2025-08-21T21:48:35.135Z
Learning: CUTLASS extensions in TensorRT-LLM (located under cpp/tensorrt_llm/cutlass_extensions/) are designed to integrate with and extend functionality in the external CUTLASS repository. When analyzing these extensions, their consumers and functionality wiring may exist in the CUTLASS codebase rather than within TensorRT-LLM itself.
Applied to files:
jenkins/L0_MergeRequest.groovy
🪛 Ruff (0.14.10)
scripts/build_wheel.py
417-417: Unused function argument: venv_python
(ARG001)
417-417: Unused function argument: pkg_dir
(ARG001)
418-418: Unused function argument: lib_dir
(ARG001)
🔇 Additional comments (9)
jenkins/L0_MergeRequest.groovy (1)
697-697: LGTM! Path correctly updated to reflect nanobind migration.The directory path change from
pybind/tonanobind/correctly aligns with the PR's removal of pybind11 bindings. This ensures that changes to the nanobind binding files will continue to trigger multi-GPU tests as intended.cpp/tensorrt_llm/CMakeLists.txt (1)
296-296: LGTM! Nanobind is now the exclusive binding backend.The unconditional inclusion of the nanobind subdirectory correctly reflects the removal of pybind11 as an alternative binding option.
cpp/tensorrt_llm/executor/cache_transmission/nixl_utils/CMakeLists.txt (1)
68-71: LGTM! Transfer agent binding now exclusively uses nanobind.The simplified binding configuration correctly removes the pybind11 code path and uses nanobind unconditionally.
cpp/CMakeLists.txt (1)
244-252: LGTM! Binding library loading correctly updated.The changes correctly:
- Remove the
BINDING_TYPEcache variable- Fetch nanobind unconditionally for the main bindings
- Retain pybind11 fetching only when BUILD_DEEP_EP, BUILD_DEEP_GEMM, or BUILD_FLASH_MLA are enabled (these modules maintain their own pybind11-based interfaces)
This aligns with the PR's goal to transition the main TensorRT-LLM bindings to nanobind while allowing specialized modules to retain pybind11 temporarily.
docs/source/legacy/advanced/executor.md (1)
144-144: LGTM! Documentation updated to reflect nanobind path.The binding source reference is correctly updated from the pybind to nanobind directory.
scripts/build_wheel.py (4)
370-373: LGTM! Stub generation function signature updated to remove binding_type.The function signature correctly removes the
binding_typeparameter and unconditionally installs nanobind for stub generation.
392-410: LGTM! Stub generation now uses nanobind exclusively.The code correctly:
- Uses
nanobind.stubgenfor the main bindings module (lines 392-393)- Uses
nanobind.stubgenfor the transfer agent binding (lines 408-410)- Retains
pybind11_stubgenfor modules that still use pybind11 (deep_gemm, flash_mla, deep_ep)
842-842: LGTM! Binding library hardcoded to nanobind.The
get_binding_libcall correctly uses the "nanobind" subdirectory, completing the transition from pybind11.
890-896: LGTM! Stub generation calls updated correctly.The calls to stub generation functions have been updated to:
- Remove the
binding_typeparameter- Pass the correct parameters for nanobind-based stub generation
| def generate_python_stubs_windows(venv_python: Path, pkg_dir: Path, | ||
| lib_dir: Path): | ||
|
|
||
| print("Windows not supported for nanobind stubs") | ||
| exit(1) |
There was a problem hiding this comment.
Windows stub generation for nanobind is not implemented.
The function now exits with an error message for Windows. This is a regression from the previous implementation that attempted stub generation for pybind11 on Windows.
If Windows support is important for your users, consider implementing nanobind stub generation for Windows (similar to the Linux implementation). Would you like me to help generate a Windows-compatible implementation based on the Linux version?
Note: The unused parameter warnings from static analysis (lines 417-418) are expected given this implementation.
🧰 Tools
🪛 Ruff (0.14.10)
417-417: Unused function argument: venv_python
(ARG001)
417-417: Unused function argument: pkg_dir
(ARG001)
418-418: Unused function argument: lib_dir
(ARG001)
2 participants
Summary by CodeRabbit
Release Notes
Build Changes
Testing Updates
Documentation
✏️ Tip: You can customize this high-level summary in your review settings.
Description
This PR removes all tensorrt_llm pybind11 C++/Python bindings. From now on, we will only support nanobind and can exclusively focus on nanobind bindings. 🎉
Removing all pybind bindings was structured into 3 steps (separate commits):
cpp/tensorrt_llm/pybindand its contentTest 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.