[https://nvbugs/5630196] [fix] Prevent flaky failures in C++ test_e2e.py by using local cached datasets for benchmarking#10638
Conversation
…st_e2e.py Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
…dataset name Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
DomBrown
force-pushed
the
nvbug/5630196
branch
from
4dd784f to
09bdcc8
Compare
📝 WalkthroughWalkthroughThese changes introduce local dataset loading support alongside existing HuggingFace integration in the prepare_real_data utility, with a new Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 🚥 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: 5
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (1)
benchmarks/cpp/utils/prepare_real_data.py (1)
1-15: Add NVIDIA copyright header to this fileThe file is missing the required NVIDIA copyright header with the year of latest meaningful modification. Add a header at the top:
# SPDX-License-Identifier: Apache-2.0 # # NVIDIA TensorRT-LLM # Copyright (c) 2026 NVIDIA Corporation # # Licensed under the Apache License, Version 2.0 (the "License"); # ...
🤖 Fix all issues with AI agents
In `@benchmarks/cpp/utils/prepare_real_data.py`:
- Around line 253-255: The Click option help strings use unnecessary f-string
prefixes (e.g., in the click.option calls like click.option("--dataset-name",
type=str, help=f"...") and click.option("--dataset-config-name", ...)), causing
ruff F541; replace those help arguments with plain string literals (remove the
leading f) for all Click option help parameters in this file (including the
other occurrences around lines 274-280) so they read help="..." instead of
help=f"...".
- Around line 138-152: The wrapper _create_dataset_load_error currently builds
and returns a new ValueError which loses the original traceback; change it to
raise the new ValueError using exception chaining (raise ValueError(error_msg)
from e) so the original exception context is preserved, and apply the same
change to the other dataset-loading error wrappers in the same file (the similar
blocks around the other dataset-load error handlers) so each re-raised error
uses "from e" to chain the original exception.
In `@tests/integration/defs/cpp/test_e2e.py`:
- Around line 191-196: The subprocess call to _cpp.run_command currently
replaces the entire environment by passing env={'HF_DATASETS_OFFLINE': '1'},
which drops critical variables; change it to merge the current environment with
the override (e.g., base_env = os.environ.copy();
base_env.update({'HF_DATASETS_OFFLINE': '1'})) and pass that merged dict as the
env argument to _cpp.run_command when running prepare_dataset so
PATH/LD_LIBRARY_PATH and other variables are preserved.
🧹 Nitpick comments (1)
tests/integration/defs/cpp/test_e2e.py (1)
15-24: Useintformax_input_len/num_requeststo prevent accidental misuse
These are numeric values but stored as strings, which makes later arithmetic/validation easier to get wrong.Proposed fix
class DatasetConfig: @@ - max_input_len: str - num_requests: str + max_input_len: int + num_requests: int @@ DatasetConfig( @@ - max_input_len="256", - num_requests="50", + max_input_len=256, + num_requests=50, ), @@ - max_input_len="20", - num_requests="10", + max_input_len=20, + num_requests=10, ), @@ prepare_dataset = [ @@ - str(data_dir / config.token_file), "dataset", "--max-input-len", - config.max_input_len, "--num-requests", config.num_requests + str(data_dir / config.token_file), "dataset", "--max-input-len", + str(config.max_input_len), "--num-requests", str(config.num_requests) ]Also applies to: 63-76, 185-187
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
benchmarks/cpp/utils/prepare_real_data.pytests/integration/defs/cpp/test_e2e.py
🧰 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 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:
tests/integration/defs/cpp/test_e2e.pybenchmarks/cpp/utils/prepare_real_data.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:
tests/integration/defs/cpp/test_e2e.pybenchmarks/cpp/utils/prepare_real_data.py
🧬 Code graph analysis (2)
tests/integration/defs/cpp/test_e2e.py (2)
benchmarks/cpp/utils/prepare_real_data.py (1)
DatasetConfig(30-135)tests/integration/defs/test_e2e.py (1)
prepare_dataset(496-518)
benchmarks/cpp/utils/prepare_real_data.py (2)
tensorrt_llm/executor/request.py (1)
local_path(81-82)tests/integration/defs/cpp/test_e2e.py (1)
DatasetConfig(13-44)
🪛 Ruff (0.14.11)
benchmarks/cpp/utils/prepare_real_data.py
63-65: Avoid specifying long messages outside the exception class
(TRY003)
67-68: Avoid specifying long messages outside the exception class
(TRY003)
190-190: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
212-213: Avoid specifying long messages outside the exception class
(TRY003)
226-226: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
239-239: Avoid specifying long messages outside the exception class
(TRY003)
246-246: Within an except clause, raise exceptions with raise ... from err or raise ... from None to distinguish them from errors in exception handling
(B904)
254-254: f-string without any placeholders
Remove extraneous f prefix
(F541)
279-279: f-string without any placeholders
Remove extraneous f prefix
(F541)
⏰ 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 (2)
tests/integration/defs/cpp/test_e2e.py (1)
223-230: Conditional fix looks correct
if "IFB" in batching_types and "executor" in api_types:matches the intent (list membership) and avoids the previous single-value check pitfall.benchmarks/cpp/utils/prepare_real_data.py (1)
74-80: The code correctly usesdatasets.load_dataset()with local paths andconfig_name. The HuggingFace Datasets library supports passingconfig_nameas the second positional argument for both HF Hub datasets and local dataset scripts. Whenqueryis unpacked as*dataset_config.query, it properly expands toload_dataset(path_or_name, config_name, split=...), which is the documented API pattern.
✏️ Tip: You can disable this entire section by setting review_details to false in your review settings.
|
/bot run |
|
PR_Github #31972 [ run ] triggered by Bot. Commit: |
|
PR_Github #31972 [ run ] completed with state
|
|
/bot run |
|
PR_Github #31982 [ run ] triggered by Bot. Commit: |
|
PR_Github #31982 [ run ] completed with state
|
|
/bot run |
|
PR_Github #32001 [ run ] triggered by Bot. Commit: |
|
/bot run --disable-fail-fast |
|
PR_Github #32001 [ run ] completed with state
|
|
PR_Github #32011 [ run ] triggered by Bot. Commit: |
|
PR_Github #32011 [ run ] completed with state
|
|
/bot run |
|
PR_Github #32025 [ run ] triggered by Bot. Commit: |
|
PR_Github #32025 [ run ] completed with state |
….py by using local cached datasets for benchmarking (NVIDIA#10638) Signed-off-by: Dom Brown <3886319+DomBrown@users.noreply.github.com>
3 participants
Summary by CodeRabbit
New Features
--dataset-local-pathCLI option for offline and local data sources--dataset-nameis now optional when using local pathsBug Fixes
Tests
✏️ Tip: You can customize this high-level summary in your review settings.
Description
Tests were failing due to refused connections from HuggingFace. This PR switches the relevant tests to use a locally cached dataset instead.
Test Coverage
tests/integration/defs/cpp/test_e2e.py::test_benchmarks[t5-90]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.