[https://nvbugs/6676844][test] Unwaive test_wan_t2v_example after CI checkpoint storage fix

[chang-l]

Dev Engineer Review

• Removed the waiver for examples/visual_gen/test_visual_gen_wan.py::test_wan_t2v_example from tests/integration/test_lists/waives.txt.
• The change does not modify production code, public APIs, or test behavior.
• The scope is limited to restoring normal execution of the Wan integration test.

QA Engineer Review

• Modified tests/integration/test_lists/waives.txt.
• Removed the waiver for examples/visual_gen/test_visual_gen_wan.py::test_wan_t2v_example.
• The test is listed in the CI files test-db/l0_dgx_b200.yml and test-db/l0_b200.yml.
• The test passed on B200 when the waiver was removed. Later collection failures were unrelated main-branch import errors.
• Coverage verdict: sufficient.

Per-File QA Perspective

• tests/integration/test_lists/waives.txt: Removes the waiver for the Wan T2V integration test. The test remains listed in the appropriate B200 CI test lists.

Description

Unwaive examples/visual_gen/test_visual_gen_wan.py::test_wan_t2v_example, waived in #18303 for https://nvbugs/6676844.

The failure was not a code regression. The example died during weight loading with Error while deserializing header: header too large on Wan2.2-T2V-A14B-Diffusers-NVFP4/transformer/diffusion_pytorch_model-00002-of-00002.safetensors on the CI model share (/scratch.trt_llm_data/llm-models). The share's disk filled up on 2026-08-26 and the shard was left corrupt: every other test in the same DGX_B200-PyTorch-4 stage passed (28 passed / 1 skipped / this 1 failure), the Qwen-Image example loaded fine through the same loader, and no visual_gen source changed between the last good commit (ca939b7) and the first bad one (128950d). The infra owner cleaned and repaired the share on 2026-08-27.

This PR only removes the waiver line. The test is in the pre-merge DGX_B200-PyTorch stage (l0_b200.yml), so this PR's CI verifies the NVFP4 checkpoint loads again.

Test Coverage

• examples/visual_gen/test_visual_gen_wan.py::test_wan_t2v_example (l0_b200.yml pre_merge; also listed in l0_dgx_b200.yml post_merge)

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)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• 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.

[chang-l]

/bot run

[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: 87c2931f-1d8b-4210-a98f-e40d31221a57

📥 Commits

Reviewing files that changed from the base of the PR and between 0369d45 and b5635e2.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

• tests/integration/test_lists/waives.txt

Included review availability: Your plan provides up to 12 included reviews per hour; 11 remain after this review.

---

Walkthrough

The integration waiver list no longer skips test_wan_t2v_example in examples/visual_gen/test_visual_gen_wan.py.

Changes

Wan test execution

Layer / File(s)	Summary
Remove Wan waiver tests/integration/test_lists/waives.txt	Removed the waiver and associated bug reference for the Wan text-to-video example test.

Priority: ⬇️ Low — Defer this one-line test-waiver removal because it is a narrow validation change for the Wan text-to-video example after checkpoint storage repair.

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

Merge Risk: ⚪ Minimal · up to b5635

The change re-enables the Wan text-to-video example test in the integration waiver list. No current merge-blocking risk remains.

Suggested reviewers: sylvesterkaczmarek

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly identifies the NVBugs ticket, test-related change, specific test, and reason for removing the waiver.
Description check	✅ Passed	The description explains the failure cause, infrastructure resolution, scope of the change, and relevant pre-merge test coverage. It includes the required sections and checklist.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check. Docstring coverage is scoped to functions touched by this diff. Analyzed 0 functions across 0…
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.}

[tensorrt-cicd]

PR_Github #71566 [ run ] triggered by Bot. Commit: e47637f Link to invocation

[tensorrt-cicd]

PR_Github #71566 [ run ] completed with state SUCCESS. Commit: e47637f
/LLM/main/L0_MergeRequest_PR pipeline #58652 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

[chang-l]

CI status note for L0 #58652 (this PR's first run):

• The unwaived test passed on B200: CBTS narrowed the DGX_B200-PyTorch stage to exactly examples/visual_gen/test_visual_gen_wan.py::test_wan_t2v_example and it reported 1 passed (call 511 s, exit code 0). So the Wan2.2 NVFP4 checkpoint on the CI share is restored and the waiver can go.
• The pipeline FAILURE comes from CPU-Generic-x86-1, unrelated to this change: unittest/others (test_time_breakdown.TestRequestTimeBreakdown::test_parse_records_matches_parse_json_file, Lists differ) and unittest/llmapi/apps/test_request_metrics.py. Both tests were added by [None][feat] perf-sanity: upload per-request disagg lifecycle spans to OpenSearch #18445 (737af47, merged a few hours before this branch), and the same two failures show up today in every other PR run whose base includes that commit, so this is a main-branch breakage. I'll rebase and re-run once a fix or waiver for those lands on main.

[sylvesterkaczmarek]

Removing the waiver is the right recovery test because the original failure was attributed to corrupted shared checkpoint storage rather than a source regression. Since this PR changes only test admission, I would treat the exact pre-merge B200 execution of test_wan_t2v_example as the merge gate; that proves the repaired checkpoint path actually loads under the same environment that failed before. No code-path risk beyond that validation.

[coderabbitai]

Note

GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer.

[chang-l]

/bot run

[tensorrt-cicd]

PR_Github #71779 [ run ] triggered by Bot. Commit: ffe25c2 Link to invocation

[chang-l]

Rebased onto main (70feda6395, includes the #18445 revert) and re-ran: L0 #58858 now fails before any test stage, in Check Test List (15 pytest collection errors under tests/integration/defs). This is the main-wide import breakage tracked by #18771 (kv_cache_manager_v2 moved by #17899 while #17399 still imports the old path, so tensorrt_llm._torch.attention.backends cannot import). Every single-GPU sub-job started after ~14:00 UTC today fails the same way. Will rebase and re-run once that fix lands; the target test itself already passed in the first run (L0 #58652).

[tensorrt-cicd]

PR_Github #71779 [ run ] completed with state SUCCESS. Commit: ffe25c2
/LLM/main/L0_MergeRequest_PR pipeline #58858 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

[sylvesterkaczmarek]

Thanks for tracing this. Since test_wan_t2v_example passed in the earlier run and the current rerun is failing during collection because of the main-wide import break tracked in #18771, I agree this does not point to a regression in this waiver removal. Happy to recheck once the upstream collection issue is fixed and the target test can run again on the rebased head.

[chang-l]

/bot run

[coderabbitai]

Note

GitHub couldn't provide a complete incremental comparison for this pull request, so CodeRabbit is performing a full review instead. This review may take a little longer.

[tensorrt-cicd]

PR_Github #72190 [ run ] triggered by Bot. Commit: b5635e2 Link to invocation

[tensorrt-cicd]

PR_Github #72190 [ run ] completed with state SUCCESS. Commit: b5635e2
/LLM/main/L0_MergeRequest_PR pipeline #59232 completed with status: 'SUCCESS'

CI Report

Link to invocation

[chang-l]

@sylvesterkaczmarek the rebased head (b5635e20f5, on top of main with #18771) is now green end to end: L0 #59232 completed with status SUCCESS. Check Test List passed, and the CBTS-narrowed DGX_B200-PyTorch-1-cbts stage again ran exactly examples/visual_gen/test_visual_gen_wan.py::test_wan_t2v_example → 1 passed (call 516 s, exit code 0), matching the first run. So the repaired checkpoint has now loaded twice in the same pre-merge B200 environment that failed before. Ready for review.

[karljang]

LGTM;