[None][doc] add stable label to all the un-labelled arguments in LLM class #7863
Conversation
|
Warning Rate limit exceeded@Superjomn has exceeded the limit for the number of commits or files that can be reviewed per hour. Please wait 3 minutes and 50 seconds before requesting another review. ⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. 📒 Files selected for processing (1)
📝 WalkthroughWalkthroughApiParamTagger now only processes classes named LlmArgs or TorchLlmArgs. During model processing, fields without a json_schema_extra.status are assigned a "stable" tag. Descriptions are prefixed with :tag: Changes
Sequence Diagram(s)sequenceDiagram
autonumber
actor Caller
participant Tagger as ApiParamTagger
participant Model as Pydantic Model
participant Fields as Model Fields
Caller->>Tagger: __call__(cls)
alt cls.__name__ == "LlmArgs" or "TorchLlmArgs"
Tagger->>Model: _process_pydantic_model(cls)
loop for each field
Model-->>Tagger: field.json_schema_extra.status?
alt status present
Tagger->>Fields: _amend_pydantic_field_description_with_tags(field_names, tag=status)
else missing status
Note right of Tagger #aee0d4: Default tag = "stable"
Tagger->>Fields: _amend_pydantic_field_description_with_tags(field_names, tag="stable")
end
end
Tagger->>Model: rebuild model (apply updated descriptions)
Model-->>Tagger: updated schema
else other classes
Tagger-->>Caller: skip processing
end
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Pre-merge checks and finishing touches❌ Failed checks (1 warning)
✅ Passed checks (2 passed)
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 |
|
/bot run --stage-list "A10-Build_Docs" |
|
PR_Github #19299 [ 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: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
tensorrt_llm/llmapi/utils.py (2)
571-582: Avoid duplicated :tag: in docs; set missing status in json_schema_extra and rebuild once.Prefixing descriptions while
generate_api_docs_as_docstring()also injects tags yields duplicates like “:tag:stable:tag:stable…”. Prefer settingstatuson fields lacking it, then rebuild once.Apply:
def _process_pydantic_model(self, cls: Type[BaseModel]) -> None: """Process the Pydantic model to add tags to the fields. """ - for field_name, field_info in cls.model_fields.items(): - if field_info.json_schema_extra and 'status' in field_info.json_schema_extra: - status = field_info.json_schema_extra['status'] - self._amend_pydantic_field_description_with_tags( - cls, [field_name], status) - else: - self._amend_pydantic_field_description_with_tags( - cls, [field_name], "stable") + updated = False + for _, field_info in cls.model_fields.items(): + extra = field_info.json_schema_extra or {} + status = extra.get('status') + if not status: + extra['status'] = 'stable' + field_info.json_schema_extra = extra + updated = True + if updated: + cls.model_rebuild(force=True)
583-599: Py3.8 typing regression (‘list[str]’) and null/duplicate tag handling; avoid per-field rebuilds.
list[str]is invalid on Python 3.8; useList[str].- Guard against
Nonedescriptions and double-prefixing.- Defer
model_rebuildto the caller (one rebuild per model).Apply:
-def _amend_pydantic_field_description_with_tags(self, cls: Type[BaseModel], - field_names: list[str], - tag: str) -> None: +def _amend_pydantic_field_description_with_tags(self, cls: Type[BaseModel], + field_names: List[str], + tag: str) -> None: @@ - assert field_names - for field_name in field_names: - field = cls.model_fields[field_name] - cls.model_fields[ - field_name].description = f":tag:`{tag}` {field.description}" - cls.model_rebuild(force=True) + assert field_names + for field_name in field_names: + field = cls.model_fields[field_name] + desc = (field.description or "").strip() + # Avoid double-tagging if already present + if not desc.startswith(":tag:`"): + cls.model_fields[field_name].description = ( + f":tag:`{tag}` {desc}".rstrip() + )
🧹 Nitpick comments (1)
tensorrt_llm/llmapi/utils.py (1)
567-569: Gating by class name is brittle — TorchLlmArgs is not being tagged.tag_llm_params() only calls ApiParamTagger()(LlmArgs) (tensorrt_llm/llmapi/utils.py:601–603). ApiParamTagger currently gates on cls.name in ["LlmArgs","TorchLlmArgs"] (tensorrt_llm/llmapi/utils.py:567–569), while TorchLlmArgs is defined separately (tensorrt_llm/llmapi/llm_args.py:1980) and is not passed to the tagger. Either call ApiParamTagger()(TorchLlmArgs) from tag_llm_params or change the gating to a robust check (e.g., issubclass(cls, BaseLlmArgs) or detect pydantic BaseModel) instead of string-matching.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/llmapi/utils.py(2 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:
tensorrt_llm/llmapi/utils.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:
tensorrt_llm/llmapi/utils.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:
tensorrt_llm/llmapi/utils.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
nv-guomingz
added
the
Release Blocker
|
PR_Github #19299 [ run ] completed with state |
Superjomn
force-pushed
the
doc.add-label-to-LlmArgs
branch
from
f03f19d to
c58b6cd
Compare
|
/bot run |
👎 Promotion blocked, new vulnerability foundVulnerability report
|
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (3)
tensorrt_llm/llmapi/utils.py (3)
1-1: Missing NVIDIA Apache-2.0 header (2025) at file top.Per repo guidelines, prepend the standard NVIDIA Apache-2.0 header.
567-569: Scope guard only processes LlmArgs/TorchLlmArgs — confirm intent.This aligns with the PR goal, but it’s a brittle name check. If aliases/subclasses are used, this will silently skip tagging. Consider an early return plus a more robust check when available, or document the limitation.
583-586: Use List[str] for Python 3.8 compatibility.Built-in generics list[str] are 3.9+. Switch to typing.List[str] (or add from future import annotations).
from typing import List def _amend_pydantic_field_description_with_tags( self, cls: Type[BaseModel], field_names: List[str], tag: str ) -> None: ...
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tensorrt_llm/llmapi/utils.py(2 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:
tensorrt_llm/llmapi/utils.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:
tensorrt_llm/llmapi/utils.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:
tensorrt_llm/llmapi/utils.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
|
/bot run |
👎 Promotion blocked, new vulnerability foundVulnerability report
|
chzblych
force-pushed
the
release/1.0
branch
from
d0519b4 to
af3ea37
Compare
Superjomn
force-pushed
the
doc.add-label-to-LlmArgs
branch
from
c58b6cd to
f7d12d3
Compare
|
/bot run |
|
PR_Github #19481 [ run ] triggered by Bot |
|
/bot skip --comment "doc related generic change, and passed x86 single gpu test, no need to run multi-gpu" |
|
PR_Github #19503 [ skip ] triggered by Bot |
|
PR_Github #19481 [ run ] completed with state |
|
PR_Github #19503 [ skip ] completed with state |
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (NVIDIA#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
…class (#7863) Signed-off-by: Yan Chunwei <328693+Superjomn@users.noreply.github.com> Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
4 participants
Summary by CodeRabbit
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.
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.