[None][chore] Unwaive flaky accuracy tests

[bobboli]

Description

Remove the waivers for two flaky accuracy tests associated with NVBugs 6458213, 6523809, and 6530221:

• Qwen3 skip-softmax attention with four GPUs (6458213 and 6523809)
• DeepSeekR1 FP8 blockscale throughput (6530221; the current waiver references duplicate report 6561775)

This PR intentionally contains no runtime code change or claimed fix. It re-enables the tests so current failures can be observed and diagnosed in CI.

Test Coverage

The unwaived tests are:

• accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention_4gpus[target_sparsity_0.9-fp8kv=False]
• accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput]

Pre-commit hooks passed, including test-list validation. GPU coverage is delegated to CI on the applicable H100, B200, and GB200 stages.

PR Checklist

• Please check this after reviewing the above items as appropriate for this PR.

Dev Engineer Review

• Removed two entries from tests/integration/test_lists/waives.txt.
• Removed the intended DeepSeek-R1 throughput waiver and H100 Qwen3.5 attention waiver.
• No runtime code, API, or performance changes are included.
• Test-list formatting remains valid.
• No duplicate or unrelated entries were introduced.

QA Engineer Review

• Modified tests/integration/test_lists/waives.txt.
• Removed one DeepSeek-R1 throughput waiver and one H100 Qwen3.5 attention waiver.
• No test-db/ or qa/ files were modified.
• CBTS coverage data is unavailable. Verdict: needs follow-up.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: b2f5373e-d5b1-4288-a3e5-70c5c1806c0b

📥 Commits

Reviewing files that changed from the base of the PR and between 359cb30 and 8be625b.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

🚧 Files skipped from review as they are similar to previous changes (1)

• tests/integration/test_lists/waives.txt

---

Walkthrough

The change removes two skipped integration-test entries from tests/integration/test_lists/waives.txt: the DeepSeek-R1 FP8 blockscale throughput test and the H100 Qwen3.5 attention test.

Changes

Integration test waiver cleanup

Layer / File(s)	Summary
Remove obsolete test waivers tests/integration/test_lists/waives.txt	Removed waivers for TestDeepSeekR1::test_fp8_blockscale[throughput] and TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention_4gpus on H100.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Merge Risk: ⚪ Minimal · up to 8be62

This PR only re-enables two previously waived accuracy tests so their current behavior is visible in CI; it introduces no runtime code change, and no actionable merge-blocking risk remains after normal checks and review.

Possibly related PRs

• NVIDIA/TensorRT-LLM#17472: Removes skipped or waived entries from the same waiver list, including a Qwen3.5 attention test.
• NVIDIA/TensorRT-LLM#17614: Modifies the same waiver list for different test cases.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly summarizes the removal of waivers for flaky accuracy tests and follows the required ticket and type format.
Description check	✅ Passed	The description explains the scope, affected tests, intent, test coverage, and checklist status for the waiver removal.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

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

[bobboli]

/bot run --disable-fail-fast --post-merge

[tensorrt-cicd]

PR_Github #65836 [ run ] triggered by Bot. Commit: 359cb30 Link to invocation

[tensorrt-cicd]

PR_Github #65836 Bot args parsing error: CI requested by --post-merge or an approval-gated stage selector (*, *Post-Merge*, or *PerfSanity*) requires the ci: post-merge approved PR label. Ask a member of NVIDIA/trt-llm-ci-approvers to apply it.

Link to invocation

[github-actions]

Removed the "ci: post-merge approved" label because @bobboli could not be verified as an active member of NVIDIA/trt-llm-ci-approvers. Ask a member of that team to apply it.

[bobboli]

/bot run --disable-fail-fast --post-merge

[tensorrt-cicd]

PR_Github #65842 [ run ] triggered by Bot. Commit: 359cb30 Link to invocation

[tensorrt-cicd]

PR_Github #65842 Bot args parsing error: CI requested by --post-merge or an approval-gated stage selector (*, *Post-Merge*, or *PerfSanity*) requires the ci: post-merge approved PR label. Ask a member of NVIDIA/trt-llm-ci-approvers to apply it.

Link to invocation

[xxi-nv]

/bot run --disable-fail-fast --post-merge

[tensorrt-cicd]

PR_Github #65880 [ run ] triggered by Bot. Commit: 359cb30 Link to invocation

[tensorrt-cicd]

PR_Github #65880 [ run ] completed with state SUCCESS. Commit: 359cb30
/LLM/main/L0_MergeRequest_PR pipeline #53573 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

CI Agent Failure Analysis

Link to invocation

[bobboli]

/bot run --disable-fail-fast --post-merge --reuse-test

[tensorrt-cicd]

PR_Github #65969 [ run ] triggered by Bot. Commit: 359cb30 Link to invocation

[tensorrt-cicd]

PR_Github #65969 [ run ] completed with state FAILURE. Commit: 359cb30
/LLM/main/L0_MergeRequest_PR pipeline #53658 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

CI Agent Failure Analysis

Link to invocation

[bobboli]

/bot run --disable-fail-fast --post-merge --reuse-test

[tensorrt-cicd]

PR_Github #66161 [ run ] triggered by Bot. Commit: 359cb30 Link to invocation

[tensorrt-cicd]

PR_Github #66161 [ run ] completed with state FAILURE. Commit: 359cb30
/LLM/main/L0_MergeRequest_PR pipeline #53835 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

CI Agent Failure Analysis

Link to invocation

[bobboli]

/bot run --disable-fail-fast --post-merge --reuse-test

[tensorrt-cicd]

PR_Github #66219 [ run ] triggered by Bot. Commit: 8be625b Link to invocation

[tensorrt-cicd]

PR_Github #66219 [ run ] completed with state FAILURE. Commit: 8be625b
/LLM/main/L0_MergeRequest_PR pipeline #53889 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

CI Agent Failure Analysis

Link to invocation