[https://nvbugs/5768068][chore] improve disagg acc tests#10833
[https://nvbugs/5768068][chore] improve disagg acc tests#10833pcastonguay merged 6 commits intoNVIDIA:mainfrom
Conversation
Signed-off-by: Bo Deng <deemod@nvidia.com>
|
/bot run |
📝 WalkthroughWalkthroughA test file is refactored to introduce two new helper functions: Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes 🚥 Pre-merge checks | ✅ 1 | ❌ 2❌ Failed checks (2 warnings)
✅ Passed checks (1 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: 0
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (2)
tests/integration/defs/accuracy/test_disaggregated_serving.py (2)
13-13: Add missingUnionimport andelsebranch for class test sets.
Unionis used in type annotations (lines 113-115) but not imported, causing a NameError. Additionally, the loop at lines 119-123 lacks anelsebranch, leavingtest_set_clsuninitialized whentest_setis already a class instead of a string, which will cause a runtime error.🐛 Proposed fix
-from typing import Any, Dict, List, Optional +from typing import Any, Dict, List, Optional, Union @@ - for test_set in test_sets: - if isinstance(test_set, str): - test_set_cls = get_accuracy_task(test_set) - task = test_set_cls(model_name) + for test_set in test_sets: + if isinstance(test_set, str): + test_set_cls = get_accuracy_task(test_set) + else: + test_set_cls = test_set + task = test_set_cls(model_name)
342-349: Add a timeout and broader exception handling to health polling, with logging.
requests.getwithout a timeout can hang indefinitely, bypassingserver_waiting_timeout. Also catchRequestExceptioninstead of justConnectionErrorto handle all request failures. Add logging on error to match the pattern used elsewhere in the file.- response = requests.get(f"http://localhost:{serve_port}/health") + response = requests.get( + f"http://localhost:{serve_port}/health", timeout=5) if response.status_code == 200: server_is_ready = True break - except requests.exceptions.ConnectionError: + except requests.exceptions.RequestException as e: + print(f"Health check failed: {e}") continue
🧹 Nitpick comments (2)
tests/integration/defs/accuracy/test_disaggregated_serving.py (2)
29-30: Keep module namespace onaccuracy_coreimports.The guideline requires preserving module namespaces; importing individual symbols hides their origin and complicates grep-based tracing. Prefer a module import and reference symbols via the module. As per coding guidelines, maintain namespaces for Python module imports.
♻️ Suggested change (update references accordingly)
-from .accuracy_core import (GSM8K, MMLU, LlmapiAccuracyTestHarness, - get_accuracy_task) +from . import accuracy_core
111-117: Avoid mutable defaults and reuse the timeout constant.A mutable list default is easy to trip over later, and the timeout constant is already defined. Consider normalizing both for maintainability.
♻️ Proposed refactor
-def run_accuracy_test(llm: "DuckLLM", - model_name: str, - test_sets: List[Union[str, type]] = ["MMLU", "GSM8K"], - extra_evaluator_kwargs: Optional[Dict[Union[str, type], - Dict[str, - Any]]] = None, - timeout: int = 1200): +def run_accuracy_test( + llm: "DuckLLM", + model_name: str, + test_sets: Optional[List[Union[str, type]]] = None, + extra_evaluator_kwargs: Optional[Dict[Union[str, type], + Dict[str, Any]]] = None, + timeout: int = DEFAULT_ACC_EVALUATION_TIMEOUT): + if test_sets is None: + test_sets = ["MMLU", "GSM8K"]
|
PR_Github #32714 [ run ] triggered by Bot. Commit: |
|
/bot run |
|
/bot run |
|
PR_Github #32718 [ run ] triggered by Bot. Commit: |
|
PR_Github #32720 [ run ] triggered by Bot. Commit: |
|
PR_Github #32718 [ run ] completed with state |
|
PR_Github #32720 [ run ] completed with state
|
|
/bot run |
|
PR_Github #32739 [ run ] triggered by Bot. Commit: |
|
PR_Github #32739 [ run ] completed with state
|
Signed-off-by: Bo Deng <deemod@nvidia.com>
|
/bot run |
|
PR_Github #32831 [ run ] triggered by Bot. Commit: |
|
PR_Github #32831 [ run ] completed with state
|
|
/bot run --disable-fail-fast |
|
PR_Github #32957 [ run ] triggered by Bot. Commit: |
|
PR_Github #32957 [ run ] completed with state
|
|
@bo-nv can you take a look, the CI tests are failing with |
|
/bot run --disable-fail-fast |
|
PR_Github #33032 [ run ] triggered by Bot. Commit: |
|
PR_Github #33032 [ run ] completed with state
|
|
/bot run |
|
PR_Github #33115 [ run ] triggered by Bot. Commit: |
|
PR_Github #33115 [ run ] completed with state |
Signed-off-by: Bo Deng <deemod@nvidia.com>
4 participants
Summary by CodeRabbit
Tests
Chores
✏️ Tip: You can customize this high-level summary in your review settings.
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
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.