[None][chore] Restore asserts in pytorch flow LoRA tests #8227

amitz-nv · 2025-10-09T11:18:53Z

Description

Some pytorch flow LoRA tests had their asserts commented out when CUDA graphs became enabled by default, as CUDA graphs aren't supported with LoRA.

This PR explicitly disables CUDA graphs in those tests and uncomments the asserts.

Test Coverage

tests/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_lora_default_modules
tests/unittest/llmapi/test_llm_pytorch.py::test_llama_7b_lora

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 the stage-list parameter 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.md
and the scripts/test_to_stage_mapping.py helper.

kill

kill

Kill all running builds associated with pull request.

skip

skip --comment COMMENT

Skip 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-pipeline

Reuse 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

Tests
- Updated LLM PyTorch test suite to disable CUDA graph execution for consistent, deterministic results across environments.
- Replaced print-based checks with direct assertions, improving reliability and reducing noisy logs.
- No changes to runtime behavior or public APIs.
Chores
- Minor test harness cleanup to improve consistency.

…CUDA graph in those tests as it's not supported yet Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>

amitz-nv · 2025-10-09T11:19:04Z

/bot run

coderabbitai · 2025-10-09T11:22:22Z

📝 Walkthrough

Walkthrough

Tests in tests/unittest/llmapi/test_llm_pytorch.py were updated to explicitly disable CUDA graphs by passing cuda_graph_config=None when initializing LLM instances and to replace print/commented assertions with direct assertion checks. No public APIs changed; test flow and coverage remain otherwise the same.

Changes

Cohort / File(s)	Summary of Changes
LLM PyTorch tests adjustments `tests/unittest/llmapi/test_llm_pytorch.py`	- Initialize LLM with cuda_graph_config=None across relevant tests and harness - Replace print statements and commented-out assertions with active assertions comparing outputs to references - Preserve existing test flow and structure

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Pre-merge checks and finishing touches

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Docstring Coverage	⚠️ Warning	Docstring coverage is 0.00% which is insufficient. The required threshold is 80.00%.	You can run `@coderabbitai generate docstrings` to improve docstring coverage.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title Check	✅ Passed	The title clearly summarizes the primary change of restoring assertions in the PyTorch LoRA tests and follows the repository’s naming convention with the required ticket placeholder and the “chore” type.
Description Check	✅ Passed	The pull request description includes the required “Description”, “Test Coverage”, and “PR Checklist” sections as specified in the repository template, with each section clearly explaining the issue, the solution, and the relevant tests.

✨ Finishing touches

📝 Generate docstrings

🧪 Generate unit tests (beta)

Create PR with unit tests
Post copyable unit tests in a comment

📜 Recent review details

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

📥 Commits

Reviewing files that changed from the base of the PR and between e101213 and 0e4e542.

📒 Files selected for processing (1)

tests/unittest/llmapi/test_llm_pytorch.py (4 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:

tests/unittest/llmapi/test_llm_pytorch.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:

tests/unittest/llmapi/test_llm_pytorch.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:

tests/unittest/llmapi/test_llm_pytorch.py

🧠 Learnings (1)

📓 Common learnings

Learnt from: moraxu
PR: NVIDIA/TensorRT-LLM#6303
File: tests/integration/test_lists/qa/examples_test_list.txt:494-494
Timestamp: 2025-07-28T17:06:08.621Z
Learning: In TensorRT-LLM testing, it's common to have both CLI flow tests (test_cli_flow.py) and PyTorch API tests (test_llm_api_pytorch.py) for the same model. These serve different purposes: CLI flow tests validate the traditional command-line workflow, while PyTorch API tests validate the newer LLM API backend. Both are legitimate and should coexist.

🧬 Code graph analysis (1)

tests/unittest/llmapi/test_llm_pytorch.py (3)

tensorrt_llm/llmapi/llm.py (1)

LLM (1084-1100)

tests/integration/defs/conftest.py (1)

llm_models_root (78-92)

tests/unittest/utils/util.py (1)

similar (375-377)

⏰ 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 (9)

tests/unittest/llmapi/test_llm_pytorch.py (9)

271-277: LGTM! CUDA graph properly disabled for LoRA tests.

The expanded LLM initialization with cuda_graph_config=None correctly disables CUDA graphs, which are incompatible with LoRA. The TODO comment appropriately notes this is a workaround.

Consider making the TODO more specific by linking to a tracking issue (if one exists) to facilitate future resolution.

293-293: LGTM! Assertion properly restored.

The assertion correctly validates the generated text output against the expected reference using the similar() helper function with appropriate threshold checking.

309-314: LGTM! Consistent CUDA graph disabling.

The change mirrors the pattern established in llama_7b_lora_from_dir_test_harness, correctly disabling CUDA graphs for LoRA testing with appropriate TODO comment.

333-333: LGTM! Assertion properly restored.

The assertion follows the same correct pattern as line 293, validating output text against the expected reference.

354-356: LGTM! CUDA graph config correctly propagated.

The cuda_graph_config=None is correctly passed through to the helper function, ensuring CUDA graphs are disabled in all multi-LoRA eviction tests.

440-442: LGTM! CUDA graphs disabled in error test cases.

Both error validation paths correctly include cuda_graph_config=None, ensuring CUDA graphs are disabled even when testing PeftCacheConfig failures.

Also applies to: 450-452

470-472: LGTM! Consistent configuration in override test.

The CUDA graph disabling is correctly applied to the cache override test, maintaining consistency across all LoRA test scenarios.

605-607: LGTM! CUDA graphs properly disabled for Bielik LoRA test.

The change consistently applies the CUDA graph workaround to this test, maintaining the same pattern used throughout the PR.

625-678: No additional LoRA tests require explicit disabling of CUDA graphs.

Search found only skip markers for GPU memory constraints (NVBUGS links), with no references to CUDA-graph issues. No changes needed.

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.

❤️ Share

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

tensorrt-cicd · 2025-10-09T11:25:03Z

PR_Github #20892 [ run ] triggered by Bot

shaharmor98

lol LGTM

tensorrt-cicd · 2025-10-09T14:08:21Z

PR_Github #20892 [ run ] completed with state SUCCESS
/LLM/main/L0_MergeRequest_PR pipeline #15804 completed with status: 'SUCCESS'
Pipeline passed with automatic retried tests. Check the rerun report for details.

Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>

Uncomment 'assert' in pytorch flow LoRA tests and explicitly disable …

0e4e542

…CUDA graph in those tests as it's not supported yet Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>

amitz-nv requested a review from shaharmor98 October 9, 2025 11:18

amitz-nv self-assigned this Oct 9, 2025

shaharmor98 approved these changes Oct 9, 2025

View reviewed changes

amitz-nv merged commit d560054 into NVIDIA:main Oct 9, 2025
8 of 9 checks passed

amitz-nv added a commit to amitz-nv/TensorRT-LLM that referenced this pull request Oct 13, 2025

[None][chore] Restore asserts in pytorch flow LoRA tests (NVIDIA#8227)

7cf1712

Signed-off-by: Amit Zuker <203509407+amitz-nv@users.noreply.github.com>

amitz-nv mentioned this pull request Oct 13, 2025

[None][fix] LoRA test fixes #8314

Closed

1 task

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

[None][chore] Restore asserts in pytorch flow LoRA tests #8227

[None][chore] Restore asserts in pytorch flow LoRA tests #8227

Uh oh!

amitz-nv commented Oct 9, 2025 •

edited by coderabbitai bot

Loading

Uh oh!

amitz-nv commented Oct 9, 2025

Uh oh!

coderabbitai bot commented Oct 9, 2025

Walkthrough

Changes

Estimated code review effort

Uh oh!

tensorrt-cicd commented Oct 9, 2025

Uh oh!

shaharmor98 left a comment

Uh oh!

tensorrt-cicd commented Oct 9, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

[None][chore] Restore asserts in pytorch flow LoRA tests #8227

[None][chore] Restore asserts in pytorch flow LoRA tests #8227

Uh oh!

Conversation

amitz-nv commented Oct 9, 2025 • edited by coderabbitai bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Description

Test Coverage

PR Checklist

GitHub Bot Help

kill

skip

reuse-pipeline

Summary by CodeRabbit

Uh oh!

amitz-nv commented Oct 9, 2025

Uh oh!

coderabbitai bot commented Oct 9, 2025

Walkthrough

Changes

Estimated code review effort

Pre-merge checks and finishing touches

Uh oh!

tensorrt-cicd commented Oct 9, 2025

Uh oh!

shaharmor98 left a comment

Choose a reason for hiding this comment

Uh oh!

tensorrt-cicd commented Oct 9, 2025

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

amitz-nv commented Oct 9, 2025 •

edited by coderabbitai bot

Loading