[None][test] Enhance performance tests by adding GPU availability check in test_perf.py by yufeiwu-nv · Pull Request #12535 · NVIDIA/TensorRT-LLM

yufeiwu-nv · Mar 25, 2026

Summary by CodeRabbit

Tests
- Added GPU availability validation to performance tests. Tests will skip automatically if configured GPU requirements exceed available hardware.

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

To see a list of available CI bot commands, please comment /bot help.

Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>

…rf.py. Skip tests if required GPUs exceed available devices. Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>

coderabbitai · Mar 25, 2026

📝 Walkthrough

Walkthrough

Adds GPU availability validation to performance test configuration. The PerfTestConfig.validate() method now queries available GPU count and skips the test if insufficient GPUs are configured relative to what's available.

Changes

Cohort / File(s)	Summary
GPU Availability Validation `tests/integration/defs/perf/test_perf.py`	Updated imports to include `get_device_count`. Added runtime check in `validate()` that skips test via `pytest.skip()` when configured `num_gpus` exceeds available GPU count.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~8 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is a blank template with only the PR Checklist checkbox marked complete, but no actual Description or Test Coverage sections filled in.	Complete the Description section explaining what the GPU availability check does and why it's needed. Complete the Test Coverage section listing relevant tests that safeguard these changes.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately describes the main change: adding a GPU availability check to performance tests that skips them when required GPUs exceed available devices.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

Create PR with unit tests

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

yufeiwu-nv · Mar 25, 2026

/bot --skip --comment "only test list modify"

github-actions · Mar 25, 2026

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) --high-priority]

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.

--high-priority (OPTIONAL) : Run the pipeline with high priority. This option is restricted to authorized users only and will route the job to a high-priority queue.

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.

coderabbitai

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against the current code and only fix it if needed.

Inline comments:
In `@tests/integration/defs/perf/test_perf.py`:
- Around line 978-982: Wrap the get_device_count() call in a try/except and
treat detection errors as zero GPUs so the guard cannot hard-fail; specifically,
call get_device_count() inside a try block, set available_gpus = 0 in the except
(optionally capture the exception string), then perform the check if
self.num_gpus > available_gpus and call pytest.skip(...) with a message that
includes self.num_gpus and available_gpus (this ensures tests requesting any
GPUs are skipped when detection fails or when available_gpus == 0).

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro

Run ID: 4458a8c0-eb69-49a0-8b5b-d73dfce0b9d7

📥 Commits

Reviewing files that changed from the base of the PR and between 2b5c434 and 1557d18.

📒 Files selected for processing (1)

tests/integration/defs/perf/test_perf.py

yufeiwu-nv · Mar 30, 2026

/bot skip --comment "only test list modify"

tensorrt-cicd · Mar 30, 2026

PR_Github #40664 [ skip ] triggered by Bot. Commit: 7dd5fce Link to invocation

Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>

tensorrt-cicd · Mar 30, 2026

PR_Github #40664 [ skip ] completed with state SUCCESS. Commit: 7dd5fce
Skipping testing for commit 7dd5fce

Link to invocation

yufeiwu-nv · Mar 30, 2026

/bot skip --comment "only test list modify"

tensorrt-cicd · Mar 30, 2026

PR_Github #40722 [ skip ] triggered by Bot. Commit: d21c08e Link to invocation

yufeiwu-nv · Mar 31, 2026

/bot skip --comment "only test list modify"

tensorrt-cicd · Mar 31, 2026

PR_Github #40831 [ skip ] triggered by Bot. Commit: 58d0d99 Link to invocation

tensorrt-cicd · Mar 31, 2026

PR_Github #40831 [ skip ] completed with state SUCCESS. Commit: 58d0d99
Skipping testing for commit 58d0d99

Link to invocation

yufeiwu-nv added 2 commits March 20, 2026 08:34

Fix lora config < required config number

716bfad

Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>

Merge branch 'main' into fix_testlist

51b536d

yufeiwu-nv requested a review from a team as a code owner March 25, 2026 09:35

github-actions Bot assigned yufeiwu-nv Mar 25, 2026

yufeiwu-nv added 2 commits March 25, 2026 09:36

Enhance performance tests by adding GPU availability check in test_pe…

a5d0e60

…rf.py. Skip tests if required GPUs exceed available devices. Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>

Merge branch 'main' into fix_testlist

1557d18

coderabbitai Bot reviewed Mar 25, 2026

View reviewed changes

Comment thread tests/integration/defs/perf/test_perf.py Outdated

LarryXFly approved these changes Mar 27, 2026

View reviewed changes

Merge branch 'main' into fix_testlist

7dd5fce

add robu

426c3a7

Signed-off-by: yufeiwu-nv <230315618+yufeiwu-nv@users.noreply.github.com>

yufeiwu-nv enabled auto-merge (squash) March 30, 2026 10:35

Merge branch 'main' into fix_testlist

d21c08e

Merge branch 'main' into fix_testlist

58d0d99

yufeiwu-nv merged commit bcf5368 into NVIDIA:main Mar 31, 2026
5 checks passed

Search code, repositories, users, issues, pull requests...

Conversation

yufeiwu-nv commented Mar 25, 2026 • edited by coderabbitai Bot Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary by CodeRabbit

Description

Test Coverage

PR Checklist

GitHub Bot Help

Uh oh!

coderabbitai Bot commented Mar 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Walkthrough

Changes

Estimated code review effort

❌ Failed checks (1 warning)

Uh oh!

yufeiwu-nv commented Mar 25, 2026

Uh oh!

github-actions Bot commented Mar 25, 2026

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

coderabbitai Bot left a comment

Choose a reason for hiding this comment

Uh oh!

Uh oh!

yufeiwu-nv commented Mar 30, 2026

Uh oh!

tensorrt-cicd commented Mar 30, 2026

Uh oh!

tensorrt-cicd commented Mar 30, 2026

Uh oh!

yufeiwu-nv commented Mar 30, 2026

Uh oh!

tensorrt-cicd commented Mar 30, 2026

Uh oh!

yufeiwu-nv commented Mar 31, 2026

Uh oh!

tensorrt-cicd commented Mar 31, 2026

Uh oh!

tensorrt-cicd commented Mar 31, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

yufeiwu-nv commented Mar 25, 2026 •

edited by coderabbitai Bot

Loading

coderabbitai Bot commented Mar 25, 2026 •

edited

Loading