[https://nvbugs/6088149][chore] Unwaive perf sanity tests for bug 6088149 by chenfeiz0326 · Pull Request #13176 · NVIDIA/TensorRT-LLM

chenfeiz0326 · 2026-04-18T14:31:04Z

Remove waives for three perf sanity test cases to re-enable them in CI:

disagg_upload-gen_only-gb200_deepseek-r1-fp4 dep8 eplb0 mtp0
disagg_upload-gen_only-gb200_deepseek-r1-fp4 dep32 eplb0 mtp3
aggr_upload-k25_thinking_fp4_2_nodes_grace_blackwell

Summary by CodeRabbit

Tests
- Removed previously skipped test entries from the test configuration to streamline the test suite.

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.

coderabbitai · 2026-04-18T14:31:51Z

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: 395b8eff-0018-4c01-9ba9-d62d6a520bcb

📥 Commits

Reviewing files that changed from the base of the PR and between ea117de and a9fc2f7.

📒 Files selected for processing (1)

tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

tests/integration/test_lists/waives.txt

📝 Walkthrough

Walkthrough

Three test skip entries were removed from the waives configuration file. These entries previously skipped perf/test_perf_sanity.py::test_e2e tests due to issue 6088149. The change represents a net reduction of 3 lines with no additions.

Changes

Cohort / File(s)	Summary
Test Waives Configuration `tests/integration/test_lists/waives.txt`	Removed 3 skip entries for `perf/test_perf_sanity.py::test_e2e[...]` tests that were previously marked `SKIP (https://nvbugs/6088149)`.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~2 minutes

🚥 Pre-merge checks | ✅ 2 | ❌ 1

❌ Failed checks (1 inconclusive)

Check name	Status	Explanation	Resolution
Description check	❓ Inconclusive	The PR description identifies the three specific test cases being unwaived but lacks detailed explanation of the issue, solution, and test coverage as required by the template.	Add sections explaining why the bug is fixed, what testing validates the changes, and provide context about bug 6088149 and the fix.

✅ Passed checks (2 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly matches the changeset, following the required format with bug ID and chore type, accurately describing the removal of test waivers.
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.}

chenfeiz0326 · 2026-04-18T15:26:22Z

/bot run --disable-fail-fast --stage-list "GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge,GB200-36_GPUs-9_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE8-GPU32-Post-Merge,GB200-8_GPUs-2_Nodes-PyTorch-PerfSanity-Node2-GPU8-Post-Merge"

tensorrt-cicd · 2026-04-18T15:32:15Z

PR_Github #44120 [ run ] triggered by Bot. Commit: eb12461 Link to invocation

tensorrt-cicd · 2026-04-18T16:12:11Z

PR_Github #44120 [ run ] completed with state FAILURE. Commit: eb12461
/LLM/main/L0_MergeRequest_PR pipeline #34547 (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

chenfeiz0326 · 2026-04-19T01:56:37Z

/bot run --disable-fail-fast --stage-list "GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge,GB200-36_GPUs-9_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE8-GPU32-Post-Merge,GB200-8_GPUs-2_Nodes-PyTorch-PerfSanity-Node2-GPU8-Post-Merge"

tensorrt-cicd · 2026-04-19T02:02:26Z

PR_Github #44150 [ run ] triggered by Bot. Commit: eb12461 Link to invocation

tensorrt-cicd · 2026-04-19T02:38:03Z

PR_Github #44150 [ run ] completed with state FAILURE. Commit: eb12461
/LLM/main/L0_MergeRequest_PR pipeline #34577 (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

chenfeiz0326 · 2026-04-19T04:30:27Z

/bot run --disable-fail-fast --stage-list "GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-1,GB200-36_GPUs-9_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE8-GPU32-Post-Merge-1,GB200-8_GPUs-2_Nodes-PyTorch-PerfSanity-Node2-GPU8-Post-Merge-5"

tensorrt-cicd · 2026-04-19T04:37:02Z

PR_Github #44156 [ run ] triggered by Bot. Commit: eb12461 Link to invocation

tensorrt-cicd · 2026-04-19T07:06:22Z

PR_Github #44156 [ run ] completed with state SUCCESS. Commit: eb12461
/LLM/main/L0_MergeRequest_PR pipeline #34583 (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

chenfeiz0326 · 2026-04-19T07:49:05Z

/bot run --disable-fail-fast --stage-list "GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge-1"

tensorrt-cicd · 2026-04-19T07:55:02Z

PR_Github #44170 [ run ] triggered by Bot. Commit: eb12461 Link to invocation

tensorrt-cicd · 2026-04-19T10:03:32Z

PR_Github #44170 [ run ] completed with state SUCCESS. Commit: eb12461
/LLM/main/L0_MergeRequest_PR pipeline #34597 (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

Remove waives for three perf sanity test cases to re-enable them in CI: - disagg_upload-gen_only-gb200_deepseek-r1-fp4 dep8 eplb0 mtp0 - disagg_upload-gen_only-gb200_deepseek-r1-fp4 dep32 eplb0 mtp3 - aggr_upload-k25_thinking_fp4_2_nodes_grace_blackwell Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>

…fig match keys - Replace CUTLASS with CUTEDSL in 12 aggregated perf-sanity YAML configs - Remove 5 redundant keys from to_match_keys() in test_perf_sanity.py: b_disable_overlap_scheduler, b_enable_chunked_prefill, b_enable_lm_head_tp_in_adp, b_enable_cuda_graph, s_cache_transceiver_backend Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Chenfei Zhang <chenfeiz@nvidia.com>

github-actions bot assigned chenfeiz0326 Apr 18, 2026

chenfeiz0326 force-pushed the chenfeiz/fix-bug-6088149 branch from a9fc2f7 to eb12461 Compare April 18, 2026 15:22

chenfeiz0326 requested a review from a team as a code owner April 18, 2026 15:22

chenfeiz0326 and others added 2 commits April 20, 2026 04:13

chenfeiz0326 force-pushed the chenfeiz/fix-bug-6088149 branch from eb12461 to 7618504 Compare April 20, 2026 04:14

chenfeiz0326 requested a review from ruodil April 20, 2026 04:17

Conversation

chenfeiz0326 commented Apr 18, 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 Apr 18, 2026

Walkthrough

Changes

Estimated code review effort

❌ Failed checks (1 inconclusive)

Uh oh!

chenfeiz0326 commented Apr 18, 2026

Uh oh!

tensorrt-cicd commented Apr 18, 2026

Uh oh!

tensorrt-cicd commented Apr 18, 2026

Uh oh!

chenfeiz0326 commented Apr 19, 2026

Uh oh!

tensorrt-cicd commented Apr 19, 2026

Uh oh!

tensorrt-cicd commented Apr 19, 2026

Uh oh!

chenfeiz0326 commented Apr 19, 2026

Uh oh!

tensorrt-cicd commented Apr 19, 2026

Uh oh!

tensorrt-cicd commented Apr 19, 2026

Uh oh!

chenfeiz0326 commented Apr 19, 2026

Uh oh!

tensorrt-cicd commented Apr 19, 2026

Uh oh!

tensorrt-cicd commented Apr 19, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

chenfeiz0326 commented Apr 18, 2026 •

edited by coderabbitai bot

Loading