[None][infra] Waive 15 failed cases for main in post-merge

[xinhe-nv]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by qa@nvidia.com)
Target branch: main
Bug(s): 5921674, 6094066, 6105765, 6105767, 6105768, 6105769, 6106174

Waive entries added

disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_bf16_empty_batch[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/6105769)
disaggregated/test_disaggregated.py::test_disaggregated_cancel_large_context_requests[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/6105768)
disaggregated/test_disaggregated.py::test_disaggregated_benchmark_on_diff_backends[DeepSeek-V3-Lite-bf16] SKIP (https://nvbugs/6105767)
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_fp8[latency-torch_compile=True] SKIP (https://nvbugs/6094066)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_without_reuse_disable_overlap_scheduler SKIP (https://nvbugs/6105765)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_without_reuse SKIP (https://nvbugs/6105765)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_reuse_partial_reuse SKIP (https://nvbugs/6105765)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_reuse_disable_overlap_scheduler SKIP (https://nvbugs/6105765)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_reuse SKIP (https://nvbugs/6105765)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_without_reuse_low_memory_available SKIP (https://nvbugs/6106174)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_reuse_low_memory_available_partial_reuse SKIP (https://nvbugs/6106174)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_reuse_low_memory_available_no_partial_reuse SKIP (https://nvbugs/6106174)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_chunked_prefill_without_reuse SKIP (https://nvbugs/6106174)
accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype_vswa_chunked_prefill_reuse SKIP (https://nvbugs/6106174)
accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_auto_dtype[False] SKIP (https://nvbugs/5921674)

---

This PR was auto-generated by TensorRT LLM CI Report. Please review the waive entries before merging.

Summary by CodeRabbit

• Tests
  • Added test waivers for specific model configuration scenarios. These adjustments address known limitations identified in integration testing across various model and hardware configurations.

[xinhe-nv]

/bot run --skip-test

[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: Pro Plus

Run ID: ffb725b2-67ed-4b56-b797-cdf5df317aef

📥 Commits

Reviewing files that changed from the base of the PR and between 36113bf and b0109ef.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

This pull request adds 15 test waiver entries to skip specific failing integration test parametrizations across multiple models (DeepSeek-V3-Lite, Qwen3-30B, Gemma3-1B, NemotronV2) with various configurations. Each waiver includes a corresponding nvbugs issue reference.

Changes

Cohort / File(s)	Summary
Test Waivers tests/integration/test_lists/waives.txt	Added 15 SKIP entries for failing test parametrizations: DeepSeek-V3-Lite bf16 disaggregated scenarios, Qwen3-30B fp8 latency with torch_compile, Gemma3-1B Instruct auto_dtype_vswa variants, and NemotronV2 auto-deploy test, each with corresponding nvbugs issue links.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~4 minutes

Possibly related PRs

• [None][infra] Waive 20 failed cases for main in post-merge #13203: Adds SKIP waivers to the same waive file for DeepSeek-V3-Lite bf16 disaggregated test overlapping with this PR.
• [None][infra] Waive 8 failed cases for main in post-merge #13201: Modifies the same waiver list to add SKIP entries for failing DeepSeek-related integration test parametrizations.
• [None][infra] Waive 2 failed cases for main in post-merge 2663 #13216: Modifies tests/integration/test_lists/waives.txt to add test SKIP entries, including a DeepSeekV3Lite bfloat16 test parametrization waiver.

Suggested reviewers

• EmmaQiaoCh
• jieli-matrix
• StanleySun639

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly and specifically describes the main change: adding 15 waived test cases for the main branch in post-merge.
Description check	✅ Passed	The description is auto-generated and provides essential information: bug references, list of waived entries with their associated bug IDs, and context about the auto-generated nature.
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.

_{✏️ 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]

PR_Github #45107 [ run ] triggered by Bot. Commit: b0109ef Link to invocation

[xinhe-nv]

/bot run --skip-test

[tensorrt-cicd]

PR_Github #45144 [ run ] triggered by Bot. Commit: 42bc44f Link to invocation

[tensorrt-cicd]

PR_Github #45107 [ run ] completed with state ABORTED. Commit: b0109ef

Link to invocation

[tensorrt-cicd]

PR_Github #45144 [ run ] completed with state SUCCESS. Commit: 42bc44f
/LLM/main/L0_MergeRequest_PR pipeline #35426 (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

[xinhe-nv]

/bot run --skip-test

[tensorrt-cicd]

PR_Github #45288 [ run ] triggered by Bot. Commit: 0c44333 Link to invocation

[tensorrt-cicd]

PR_Github #45288 [ run ] completed with state SUCCESS. Commit: 0c44333
/LLM/main/L0_MergeRequest_PR pipeline #35542 (Partly Tested) completed with status: 'SUCCESS'

CI Report

Link to invocation

[xinhe-nv]

/bot run --skip-test

[xinhe-nv]

/bot run --skip-test

[tensorrt-cicd]

PR_Github #45333 [ run ] triggered by Bot. Commit: 64800ba Link to invocation

[tensorrt-cicd]

PR_Github #45334 [ run ] triggered by Bot. Commit: 64800ba Link to invocation

[tensorrt-cicd]

PR_Github #45333 [ run ] completed with state ABORTED. Commit: 64800ba

Link to invocation

[xinhe-nv]

/bot reuse-pipeline --number 35542

[tensorrt-cicd]

PR_Github #45353 [ reuse-pipeline ] triggered by Bot. Commit: 32467f1 Link to invocation

[tensorrt-cicd]

PR_Github #45353 [ reuse-pipeline ] completed with state SUCCESS. Commit: 32467f1
Reusing PR_Github #45288 (Partly Tested) for commit 32467f1

Link to invocation