[None][chore] Update Gemma3 closeness check to mitigate flakiness #6591
Conversation
📝 WalkthroughWalkthroughA new helper method, Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~7 minutes Suggested reviewers
Note ⚡️ Unit Test Generation is now available in beta!Learn more here, or try it out under "Finishing Touches" below. 📜 Recent review detailsConfiguration used: .coderabbit.yaml 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
⏰ 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)
✨ 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
|
brb-nv
force-pushed
the
user/brb/relax-gemma3-constraints
branch
from
1fd5a2f to
7f5fdb8
Compare
![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
🧹 Nitpick comments (1)
tests/unittest/_torch/modeling/test_modeling_gemma3.py (1)
234-241: Good implementation but consider adding type hints and docstring.The logic correctly addresses the flakiness issue by allowing a small fraction of elements to fail the closeness check. The error message is clear and informative.
Consider these improvements to align with coding guidelines:
- # Allow room for small fraction of elements to fail. This is to mitigate flakiness. - def _assert_most_elems_close(self, actual_value, ref_value, atol, rtol, - max_failed_fraction): + def _assert_most_elems_close(self, actual_value: torch.Tensor, ref_value: torch.Tensor, + atol: float, rtol: float, max_failed_fraction: float) -> None: + """ + Assert that most elements of two tensors are close within given tolerances. + + Allows a small fraction of elements to fail the closeness check to mitigate test flakiness. + + Args: + actual_value: Tensor to compare + ref_value: Reference tensor + atol: Absolute tolerance + rtol: Relative tolerance + max_failed_fraction: Maximum fraction of elements allowed to fail (0-1) + """ + assert 0 <= max_failed_fraction <= 1, "max_failed_fraction must be between 0 and 1"
📜 Review details
Configuration used: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (1)
tests/unittest/_torch/modeling/test_modeling_gemma3.py(3 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 classes and functions in Python, 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 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/unittest/_torch/modeling/test_modeling_gemma3.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/unittest/_torch/modeling/test_modeling_gemma3.py
🔇 Additional comments (2)
tests/unittest/_torch/modeling/test_modeling_gemma3.py (2)
355-359: LGTM! Proper replacement maintains same tolerances while adding flakiness mitigation.The change correctly replaces the strict assertion with the new helper method, keeping the same tolerance values (atol=0.4, rtol=0.4) while allowing 0.1% of elements to fail. This should address the reported flakiness where individual elements occasionally exceed the threshold.
396-400: LGTM! Consistent application of flakiness mitigation in generation phase.The change mirrors the context phase update with identical parameters, ensuring consistent tolerance for flakiness across both test phases.
|
/bot run |
|
This PR relaxes the test condition because the Gemma3 unit test has started failing on exactly one element after a recent dependency update. |
|
PR_Github #13927 [ run ] triggered by Bot |
|
PR_Github #13927 [ run ] completed with state |
brb-nv
force-pushed
the
user/brb/relax-gemma3-constraints
branch
from
7f5fdb8 to
0fecbff
Compare
|
/bot run |
|
PR_Github #13935 [ run ] triggered by Bot |
|
PR_Github #13935 [ run ] completed with state |
|
/bot run |
|
PR_Github #13950 [ run ] triggered by Bot |
|
PR_Github #13950 [ run ] completed with state |
Signed-off-by: Balaram Buddharaju <[email protected]>
chzblych
force-pushed
the
user/brb/relax-gemma3-constraints
branch
from
0fecbff to
63eac2e
Compare
|
/bot run --stage-list "H100_PCIe-PyTorch-3" |
|
PR_Github #13991 [ run ] triggered by Bot |
|
PR_Github #13991 [ run ] completed with state |
|
/bot skip --comment "Passed the failed test/test stage" |
|
PR_Github #14007 [ skip ] triggered by Bot |
|
PR_Github #14007 [ skip ] completed with state |
…IDIA#6591) Signed-off-by: Balaram Buddharaju <[email protected]> Signed-off-by: Lanyu Liao <[email protected]>
…IDIA#6591) Signed-off-by: Balaram Buddharaju <[email protected]>
Description
Gemma3 tests seem to be failing with a single element not meeting the threshold criterion after a dependency update. This MR keeps threshold the same but allows for a small fraction of elements to fail.
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.
Summary by CodeRabbit