[https://nvbugs/6435112][test] Unwaive Wan 2.2 I2V perf sanity test

[taianz-nv]

Summary

• Remove the waiver for the Wan 2.2 I2V A14B NVFP4 TRT-LLM Ulysses-4 VisualGen perf-sanity test.
• Keep the test enabled in the B200 VisualGen perf-sanity test list.
• Leave all other waivers associated with NVBug 6422339 unchanged.

Background

NVBug 6435112 tracks an NCCL ALLTOALL_BASE watchdog timeout in this exact test. The repair bot reran the test multiple times on B200 x8 against current main and all attempts passed, so this PR re-enables the test for full CI validation.

NVBug context

This test was initially waived under NVBug 6422339, which groups multiple failures from Post-Merge #2824. NVBug 6435112 tracks this specific Wan 2.2 I2V NCCL timeout, so this PR is titled under 6435112 while removing the existing waiver linked to 6422339. Other 6422339 waivers are unchanged.

Validation

• pre-commit run --files tests/integration/test_lists/waives.txt

CI

Please run DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1 to validate the previously flaky distributed test before closing NVBug 6435112.

Summary by CodeRabbit

• Tests
  • Removed an obsolete skip waiver for a visual generation performance sanity test, allowing the test case to run normally.

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[coderabbitai]

📝 Walkthrough

Walkthrough

Removes one SKIP waiver for a specific visual generation end-to-end performance test parameterization from the integration waiver list.

Changes

Visual generation waiver

Layer / File(s)	Summary
Remove visual generation SKIP waiver tests/integration/test_lists/waives.txt	Deletes the waiver for the targeted test_visual_gen_e2e parameterization.

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

Possibly related PRs

• NVIDIA/TensorRT-LLM#6795: Modifies the same integration waiver file with a different SKIP waiver.
• NVIDIA/TensorRT-LLM#16392: Removes a different waiver entry from the same manifest.
• NVIDIA/TensorRT-LLM#16400: Removes a different test waiver from the same file.

Suggested reviewers: bowenfu, brnguyen2

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
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.
Title check	✅ Passed	The title clearly matches the main change: removing a waiver for the Wan 2.2 I2V perf sanity test.
Description check	✅ Passed	The description explains the change, background, validation, and CI follow-up, though the template headings are not exact.

✨ 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 #59383 [ run ] triggered by Bot. Commit: d75d5f8 Link to invocation

[tensorrt-cicd]

PR_Github #59383 [ run ] completed with state SUCCESS. Commit: d75d5f8
/LLM/main/L0_MergeRequest_PR pipeline #47857 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

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[tensorrt-cicd]

PR_Github #59446 [ run ] triggered by Bot. Commit: d75d5f8 Link to invocation

[tensorrt-cicd]

PR_Github #59446 [ run ] completed with state SUCCESS. Commit: d75d5f8
/LLM/main/L0_MergeRequest_PR pipeline #47914 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

[fredricz-20070104]

Approved

[fredricz-20070104]

Quick question to confirm the bug attribution before this merges.

The line removed in this PR is tests/integration/test_lists/waives.txt line 433 (diff hunk @@ -430,7 +430,6 @@):

-perf/test_visual_gen_perf_sanity.py::test_visual_gen_e2e[vg_upload-wan22_i2v_a14b_blackwell-wan22_i2v_a14b_nvfp4_trtllm_cfg2_ulysses4] SKIP (https://nvbugs/6422339)

That waiver is tagged nvbugs/6422339, but the PR title/description says this un-waives the case tracked by nvbugs/6435112 (NCCL ALLTOALL_BASE watchdog timeout). Could you confirm which bug actually caused this specific case to be skipped?

If the case was originally waived under 6422339 (which covers several perf-sanity cases) and only the 6435112 NCCL timeout was fixed, removing this waiver may re-expose the 6422339 failure. If 6422339 is in fact resolved for this case, it would help to update the description (or the waiver's bug reference) so the attribution is consistent. Thanks!

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[taianz-nv]

As discussed in DM, 6422339 is the Post-Merge aggregation bug that originally carried this waiver, while 6435112 specifically tracks the Wan 2.2 NCCL timeout. I have also updated the PR description to clarify this. Thanks!

[BowenFu]

LGTM — single waiver removal (nvbugs/6435112, Wan 2.2 I2V perf sanity).

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[tensorrt-cicd]

PR_Github #59859 [ run ] triggered by Bot. Commit: 909295c Link to invocation

[tensorrt-cicd]

PR_Github #59859 [ run ] completed with state SUCCESS. Commit: 909295c
/LLM/main/L0_MergeRequest_PR pipeline #48264 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

[tensorrt-cicd]

PR_Github #59971 [ run ] triggered by Bot. Commit: b926dfb Link to invocation

[tensorrt-cicd]

PR_Github #59971 [ run ] completed with state FAILURE. Commit: b926dfb
/LLM/main/L0_MergeRequest_PR pipeline #48365 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

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[tensorrt-cicd]

PR_Github #60017 [ run ] triggered by Bot. Commit: 0d707c8 Link to invocation

[tensorrt-cicd]

PR_Github #60017 [ run ] completed with state FAILURE. Commit: 0d707c8
/LLM/main/L0_MergeRequest_PR pipeline #48408 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

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[tensorrt-cicd]

PR_Github #60339 [ run ] triggered by Bot. Commit: 662bd02 Link to invocation

[tensorrt-cicd]

PR_Github #60339 [ run ] completed with state SUCCESS. Commit: 662bd02
/LLM/main/L0_MergeRequest_PR pipeline #48683 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

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[tensorrt-cicd]

PR_Github #60634 [ run ] triggered by Bot. Commit: 179d460 Link to invocation

[tensorrt-cicd]

PR_Github #60634 [ run ] completed with state FAILURE. Commit: 179d460
/LLM/main/L0_MergeRequest_PR pipeline #48937 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

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[tensorrt-cicd]

PR_Github #60738 [ run ] triggered by Bot. Commit: 179d460 Link to invocation

[tensorrt-cicd]

PR_Github #60738 [ run ] completed with state FAILURE. Commit: 179d460
/LLM/main/L0_MergeRequest_PR pipeline #49025 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

[taianz-nv]

/bot run --extra-stage "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[tensorrt-cicd]

PR_Github #60934 [ run ] triggered by Bot. Commit: 2ceaa2a Link to invocation

[tensorrt-cicd]

PR_Github #60934 [ run ] completed with state FAILURE. Commit: 2ceaa2a
/LLM/main/L0_MergeRequest_PR pipeline #49199 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

[taianz-nv]

/bot help

[github-actions]

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. Supports wildcard * for pattern matching (e.g., "*PerfSanity*" matches all stages containing PerfSanity). Examples: "A10-PyTorch-1, xxx", "PerfSanity". The patterns "*", "*Post-Merge*", and "*PerfSanity*", including equivalent escaped or repeated-star forms and their use in comma-separated lists, require the ci: post-merge approved PR label. 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. Requires the ci: post-merge approved PR label applied by an active member of NVIDIA/trt-llm-ci-approvers. The approval label remains in place when new commits are pushed.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Supports wildcard * for pattern matching. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx", --extra-stage "Post-Merge". The patterns "*", "*Post-Merge*", and "*PerfSanity*", including equivalent escaped or repeated-star forms and their use in comma-separated lists, require the ci: post-merge approved PR label.

--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.

[taianz-nv]

/bot run --stage-list "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1"

[tensorrt-cicd]

PR_Github #61846 [ run ] triggered by Bot. Commit: 948672b Link to invocation

[tensorrt-cicd]

PR_Github #61846 [ run ] completed with state SUCCESS. Commit: 948672b
/LLM/main/L0_MergeRequest_PR pipeline #50038 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[taianz-nv]

/bot skip “There is only one unwaived change, and its corresponding stage has already passed. L0 has been consistently encountering infra issues.”

[github-actions]

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. Supports wildcard * for pattern matching (e.g., "*PerfSanity*" matches all stages containing PerfSanity). Examples: "A10-PyTorch-1, xxx", "PerfSanity". The patterns "*", "*Post-Merge*", and "*PerfSanity*", including equivalent escaped or repeated-star forms and their use in comma-separated lists, require the ci: post-merge approved PR label. 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. Requires the ci: post-merge approved PR label applied by an active member of NVIDIA/trt-llm-ci-approvers. The approval label remains in place when new commits are pushed.

--extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx" (OPTIONAL) : Run the ordinary L0 pre-merge pipeline and specified test stages. Supports wildcard * for pattern matching. Examples: --extra-stage "H100_PCIe-TensorRT-Post-Merge-1, xxx", --extra-stage "Post-Merge". The patterns "*", "*Post-Merge*", and "*PerfSanity*", including equivalent escaped or repeated-star forms and their use in comma-separated lists, require the ci: post-merge approved PR label.

--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.