[https://nvbugs/6044213][chore] unwaive and reduce free mem ratio in AutoDeploy's perf test: deepseek_r1_distill_qwen_32b by MrGeva · Pull Request #12965 · NVIDIA/TensorRT-LLM

MrGeva · 2026-04-12T08:32:38Z

Summary by CodeRabbit

Tests
- Updated performance test configuration parameters to enhance benchmark optimization testing
- Re-enabled a previously skipped performance validation test for improved test coverage

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.

MrGeva · 2026-04-12T08:33:09Z

/bot --help

github-actions · 2026-04-12T08:33:17Z

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.

MrGeva · 2026-04-12T08:33:58Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1"

MrGeva · 2026-04-12T08:35:28Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1"

tensorrt-cicd · 2026-04-12T08:42:21Z

PR_Github #42860 [ run ] triggered by Bot. Commit: c980fd7 Link to invocation

tensorrt-cicd · 2026-04-12T09:52:57Z

PR_Github #42860 [ run ] completed with state SUCCESS. Commit: c980fd7
/LLM/main/L0_MergeRequest_PR pipeline #33526 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

MrGeva · 2026-04-12T13:47:46Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

tensorrt-cicd · 2026-04-12T13:53:41Z

PR_Github #42876 [ run ] triggered by Bot. Commit: c980fd7 Link to invocation

tensorrt-cicd · 2026-04-12T17:08:53Z

PR_Github #42876 [ run ] completed with state FAILURE. Commit: c980fd7
/LLM/main/L0_MergeRequest_PR pipeline #33540 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

MrGeva · 2026-04-13T06:27:04Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

MrGeva · 2026-04-13T06:27:42Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

tensorrt-cicd · 2026-04-13T06:33:45Z

PR_Github #42971 [ run ] triggered by Bot. Commit: 69b21e2 Link to invocation

tensorrt-cicd · 2026-04-13T07:16:49Z

PR_Github #42971 [ run ] completed with state FAILURE. Commit: 69b21e2
/LLM/main/L0_MergeRequest_PR pipeline #33628 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

MrGeva · 2026-04-13T13:04:45Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

tensorrt-cicd · 2026-04-13T13:11:36Z

PR_Github #43043 [ run ] triggered by Bot. Commit: 69b21e2 Link to invocation

tensorrt-cicd · 2026-04-13T13:53:28Z

PR_Github #43043 [ run ] completed with state FAILURE. Commit: 69b21e2
/LLM/main/L0_MergeRequest_PR pipeline #33689 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

MrGeva · 2026-04-13T13:55:29Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

tensorrt-cicd · 2026-04-13T14:02:06Z

PR_Github #43053 [ run ] triggered by Bot. Commit: 21c8ebf Link to invocation

MrGeva · 2026-04-13T15:48:59Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

tensorrt-cicd · 2026-04-13T15:56:03Z

PR_Github #43073 [ run ] triggered by Bot. Commit: 21c8ebf Link to invocation

tensorrt-cicd · 2026-04-13T19:31:16Z

PR_Github #43073 [ run ] completed with state FAILURE. Commit: 21c8ebf
/LLM/main/L0_MergeRequest_PR pipeline #33714 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

MrGeva · 2026-04-14T05:11:51Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

tensorrt-cicd · 2026-04-14T05:18:18Z

PR_Github #43182 [ run ] triggered by Bot. Commit: 21c8ebf Link to invocation

tensorrt-cicd · 2026-04-14T05:18:19Z

PR_Github #43182 [ run ] completed with state DISABLED
Freeze main and open the PR merge only after CI is back to healthy https://nvidia.slack.com/archives/C059LSY62BT/p1776141760843319?thread_ts=1775985925.442509&cid=C059LSY62BT

Link to invocation

MrGeva · 2026-04-15T04:27:01Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

tensorrt-cicd · 2026-04-15T04:32:32Z

PR_Github #43383 [ run ] triggered by Bot. Commit: 6d2c27e Link to invocation

MrGeva · 2026-04-15T07:21:54Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1" --debug

tensorrt-cicd · 2026-04-15T07:24:18Z

PR_Github #43383 [ run ] completed with state SUCCESS. Commit: 6d2c27e
/LLM/main/L0_MergeRequest_PR pipeline #33918 (Partly Tested) completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

tensorrt-cicd · 2026-04-15T07:27:51Z

PR_Github #43424 [ run ] triggered by Bot. Commit: 6d2c27e Link to invocation

MrGeva · 2026-04-15T13:39:38Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1"

tensorrt-cicd · 2026-04-15T13:45:14Z

PR_Github #43502 [ run ] triggered by Bot. Commit: b188273 Link to invocation

tensorrt-cicd · 2026-04-15T15:18:43Z

PR_Github #43502 [ run ] completed with state SUCCESS. Commit: b188273
/LLM/main/L0_MergeRequest_PR pipeline #34017 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

MrGeva · 2026-04-15T15:20:51Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1"

tensorrt-cicd · 2026-04-15T15:27:21Z

PR_Github #43521 [ run ] triggered by Bot. Commit: b188273 Link to invocation

tensorrt-cicd · 2026-04-15T15:54:15Z

PR_Github #43521 [ run ] completed with state SUCCESS. Commit: b188273
/LLM/main/L0_MergeRequest_PR pipeline #34034 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

MrGeva · 2026-04-15T19:14:15Z

/bot run --stage-list "H100_PCIe-PyTorch-Perf-1"

tensorrt-cicd · 2026-04-15T19:20:26Z

PR_Github #43566 [ run ] triggered by Bot. Commit: b188273 Link to invocation

tensorrt-cicd · 2026-04-15T19:48:42Z

PR_Github #43566 [ run ] completed with state SUCCESS. Commit: b188273
/LLM/main/L0_MergeRequest_PR pipeline #34065 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

MrGeva · 2026-04-16T07:02:17Z

/bot run

coderabbitai · 2026-04-16T07:05:18Z

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: f93686a5-5d83-44b7-8e80-2442d523aa47

📥 Commits

Reviewing files that changed from the base of the PR and between 0d5c9ff and b188273.

⛔ Files ignored due to path filters (1)

tests/integration/defs/perf/base_perf_pytorch.csv is excluded by !**/*.csv

📒 Files selected for processing (2)

tests/integration/test_lists/test-db/l0_perf.yml
tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

tests/integration/test_lists/waives.txt

📝 Walkthrough

Walkthrough

This change updates a PyTorch performance test configuration by modifying the test parameters for deepseek_r1_distill_qwen_32b to include a kv_frac:0.8 parameter and removes the corresponding skip waiver entry, enabling the test to run under the new configuration.

Changes

Cohort / File(s)	Summary
Performance Test Configuration Updates `tests/integration/test_lists/test-db/l0_perf.yml`, `tests/integration/test_lists/waives.txt`	Modified the `deepseek_r1_distill_qwen_32b` performance test selector to include `kv_frac:0.8` parameter and removed the associated skip waiver entry, making the test active under the updated configuration.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The PR description is a template with placeholder sections that were not filled out. The Description, Test Coverage sections are empty, and the PR Checklist items remain unchecked except for one item marked.	Fill in the Description section explaining the issue and solution, the Test Coverage section listing relevant tests, and ensure all applicable checklist items are properly reviewed.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title check	✅ Passed	The PR title accurately reflects the main changes: unwaiving a perf test and reducing the KV cache free GPU memory fraction for deepseek_r1_distill_qwen_32b. It includes the NVBugs ticket reference and chore type as required.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.

_{✏️ 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.}

tensorrt-cicd · 2026-04-16T07:11:10Z

PR_Github #43683 [ run ] triggered by Bot. Commit: b188273 Link to invocation

tensorrt-cicd · 2026-04-16T07:23:55Z

PR_Github #43683 [ run ] completed with state FAILURE. Commit: b188273
/LLM/main/L0_MergeRequest_PR pipeline #34168 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

MrGeva · 2026-04-16T07:27:25Z

/bot run

tensorrt-cicd · 2026-04-16T07:32:54Z

PR_Github #43701 [ run ] triggered by Bot. Commit: b188273 Link to invocation

tensorrt-cicd · 2026-04-16T10:42:50Z

PR_Github #43701 [ run ] completed with state SUCCESS. Commit: b188273
/LLM/main/L0_MergeRequest_PR pipeline #34185 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

MrGeva · 2026-04-16T11:56:00Z

/bot run

tensorrt-cicd · 2026-04-16T12:02:27Z

PR_Github #43769 [ run ] triggered by Bot. Commit: b188273 Link to invocation

tensorrt-cicd · 2026-04-16T23:54:01Z

PR_Github #43769 [ run ] completed with state SUCCESS. Commit: b188273
/LLM/main/L0_MergeRequest_PR pipeline #34250 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

Please check the failed tests and fix your PR
If you cannot view the failures, ask the CI triggerer to share details
Once fixed, request an NVIDIA team member to trigger CI again

Link to invocation

MrGeva · 2026-04-17T04:02:49Z

/bot run

tensorrt-cicd · 2026-04-17T04:12:40Z

PR_Github #43947 [ run ] triggered by Bot. Commit: b188273 Link to invocation

tensorrt-cicd · 2026-04-17T08:04:54Z

PR_Github #43947 [ run ] completed with state SUCCESS. Commit: b188273
/LLM/main/L0_MergeRequest_PR pipeline #34393 completed with status: 'SUCCESS'

CI Report

Link to invocation

github-actions Bot assigned MrGeva Apr 12, 2026

MrGeva force-pushed the eg/unwaive_perf_test branch from 25ff2c9 to b188273 Compare April 15, 2026 13:39

MrGeva changed the title ~~[https://nvbugs/6044213][chore] unwaive AutoDeploy perf test: deepseek_r1_distill_qwen_32b~~ [https://nvbugs/6044213][chore] unwaive and reduce free mem ratio in AutoDeploy's perf test: deepseek_r1_distill_qwen_32b Apr 16, 2026

MrGeva marked this pull request as ready for review April 16, 2026 07:03

MrGeva requested a review from a team as a code owner April 16, 2026 07:03

MrGeva enabled auto-merge (squash) April 16, 2026 07:12

yufeiwu-nv approved these changes Apr 16, 2026

View reviewed changes

MrGeva merged commit 070cb05 into NVIDIA:main Apr 17, 2026
9 checks passed

MrGeva deleted the eg/unwaive_perf_test branch April 17, 2026 10:19

Conversation

MrGeva commented Apr 12, 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!

MrGeva commented Apr 12, 2026

Uh oh!

github-actions Bot commented Apr 12, 2026

GitHub Bot Help

kill

skip

reuse-pipeline

Uh oh!

MrGeva commented Apr 12, 2026

Uh oh!

MrGeva commented Apr 12, 2026

Uh oh!

tensorrt-cicd commented Apr 12, 2026

Uh oh!

tensorrt-cicd commented Apr 12, 2026

Uh oh!

MrGeva commented Apr 12, 2026

Uh oh!

tensorrt-cicd commented Apr 12, 2026

Uh oh!

tensorrt-cicd commented Apr 12, 2026

Uh oh!

MrGeva commented Apr 13, 2026

Uh oh!

MrGeva commented Apr 13, 2026

Uh oh!

tensorrt-cicd commented Apr 13, 2026

Uh oh!

tensorrt-cicd commented Apr 13, 2026

Uh oh!

MrGeva commented Apr 13, 2026

Uh oh!

tensorrt-cicd commented Apr 13, 2026

Uh oh!

tensorrt-cicd commented Apr 13, 2026

Uh oh!

MrGeva commented Apr 13, 2026

Uh oh!

tensorrt-cicd commented Apr 13, 2026

Uh oh!

MrGeva commented Apr 13, 2026

Uh oh!

tensorrt-cicd commented Apr 13, 2026

Uh oh!

tensorrt-cicd commented Apr 13, 2026

Uh oh!

MrGeva commented Apr 14, 2026

Uh oh!

tensorrt-cicd commented Apr 14, 2026

Uh oh!

tensorrt-cicd commented Apr 14, 2026

Uh oh!

MrGeva commented Apr 15, 2026

Uh oh!

tensorrt-cicd commented Apr 15, 2026

Uh oh!

MrGeva commented Apr 15, 2026

Uh oh!

tensorrt-cicd commented Apr 15, 2026

Uh oh!

tensorrt-cicd commented Apr 15, 2026

Uh oh!

MrGeva commented Apr 15, 2026

Uh oh!

tensorrt-cicd commented Apr 15, 2026

Uh oh!

tensorrt-cicd commented Apr 15, 2026

Uh oh!

MrGeva commented Apr 15, 2026

Uh oh!

tensorrt-cicd commented Apr 15, 2026

MrGeva commented Apr 12, 2026 •

edited by coderabbitai Bot

Loading