[None][infra] Waive 14 failed cases for main in post-merge 2855

[trtllm-agent]

Auto-generated Waive PR

Created by: TensorRT LLM CI Report (requested by @EmmaQiaoCh)
Target branch: main
Bug(s): 6388139, 6418510, 6507080, 6507081, 6507082, 6507095, 6507102, 6507108, 6507109, 6507110, 6507113, 6507114, 6507118

Waive entries added

accuracy/test_llm_api_autodeploy.py::TestQwen3_5_397B_MoE::test_bf16_small[4] SKIP (https://nvbugs/6507114)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_python_scheduler[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-enable_chunked_prefill=True] SKIP (https://nvbugs/6388139)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16_python_scheduler[mtp_nextn=2-attention_dp=False-cuda_graph=False-overlap_scheduler=False-enable_chunked_prefill=True] SKIP (https://nvbugs/6507095)
accuracy/test_llm_api_pytorch.py::TestGLM52::test_nvfp4[tp_size=8-ep_size=8] SKIP (https://nvbugs/6507108)
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_trtllm-torch_compile=False] SKIP (https://nvbugs/6507110)
perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb200_deepseek-r1-fp4_128k8k_con128_ctx1_pp8_gen1_dep16_eplb0_mtp1_ccb-NIXL] SKIP (https://nvbugs/6418510)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-NIXL] SKIP (https://nvbugs/6507118)
unittest/_torch/attention/test_attention_backends.py::test_attention_backend[deepseekv3_mla-gen-bf16-HND-p32-v1] SKIP (https://nvbugs/6507109)
unittest/_torch/multi_gpu/test_linear.py::test_row_linear[2-balanced] SKIP (https://nvbugs/6507113)
unittest/_torch/speculative/hw_agnostic/test_ngram.py::test_llama_ngram[True-True-TRTLLM] SKIP (https://nvbugs/6507102)
unittest/llmapi/test_llm.py::test_llm_with_customized_tokenizer SKIP (https://nvbugs/6507080)
unittest/llmapi/test_llm.py::test_openai_completion_list_prompt_stream_reuses_stream_metadata SKIP (https://nvbugs/6507081)
unittest/llmapi/test_llm.py::test_tokenizer_decode_incrementally[/scratch.trt_llm_data/llm-models/falcon-7b-instruct-False-0.95-HF] SKIP (https://nvbugs/6507082)
unittest/llmapi/test_llm.py::test_tokenizer_decode_incrementally[/scratch.trt_llm_data/llm-models/falcon-7b-instruct-False-0.95-TRTLLM] SKIP (https://nvbugs/6507082)

---

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

Dev Engineer Review

• Added 14 waiver entries to tests/integration/test_lists/waives.txt covering accuracy, LLM API, performance, attention backend, multi-GPU, speculative decoding, and related test variants.
• Entries use the existing SKIP format and do not modify production code or public APIs.
• No apparent scope expansion or code-level regression risk.
• Bug references correspond to the reported failed post-merge cases. No duplicate waiver entries were identified.

QA Engineer Review

• Modified: tests/integration/test_lists/waives.txt.
• Added waiver entries for the reported failed test parameterizations; no test code, test-db/, or qa/ files were modified.
• CBTS coverage data is unavailable, so the verdict is needs follow-up.

[coderabbitai]

Walkthrough

Updated tests/integration/test_lists/waives.txt with new and repositioned SKIP entries covering accuracy, performance sanity, Torch, speculative decoding, tokenizer, and LLM API test parameterizations.

Changes

Test waiver updates

Layer / File(s)	Summary
Accuracy and LLM API waivers tests/integration/test_lists/waives.txt	Added waivers for Qwen3.5, DeepSeekV3Lite, GLM52, and Qwen3 accuracy and API parameterizations.
Performance sanity waivers tests/integration/test_lists/waives.txt	Added NIXL aggregation and disaggregation test_e2e waivers.
Unittest and Torch waivers tests/integration/test_lists/waives.txt	Repositioned existing Torch waivers and added attention, row-linear, speculative ngram, tokenizer, and streaming test waivers.

Estimated code review effort: 1 (Trivial) | ~3 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#16780: Adds related test_row_linear waivers.
• NVIDIA/TensorRT-LLM#16723: Adjusts related attention-backend waivers.
• NVIDIA/TensorRT-LLM#16819: Adds additional entries to the same waiver list.

Suggested reviewers: chzblych, emmaqiaoch, mzweilz

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title clearly matches the PR’s main change: waiving 14 failed cases on main from post-merge 2855.
Description check	✅ Passed	The description explains the waiver scope and linked bugs, but it omits the template’s Test Coverage and PR Checklist sections.
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.}

[coderabbitai]

Caution

Some comments are outside the diff and can’t be posted inline due to platform limitations.

⚠️ Outside diff range comments (1)

tests/integration/test_lists/waives.txt (1)

1-1: 📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

Add the required NVIDIA copyright header.

This modified file starts directly with waiver entries; add or restore the NVIDIA header and update its copyright year to 2026.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@tests/integration/test_lists/waives.txt` at line 1, Add the standard NVIDIA
copyright header at the beginning of tests/integration/test_lists/waives.txt,
before the waiver entries, and set its copyright year to 2026.

Source: Coding guidelines

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Outside diff comments:
In `@tests/integration/test_lists/waives.txt`:
- Line 1: Add the standard NVIDIA copyright header at the beginning of
tests/integration/test_lists/waives.txt, before the waiver entries, and set its
copyright year to 2026.

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: fdacccf9-a935-41be-8c96-a38218114424

📥 Commits

Reviewing files that changed from the base of the PR and between 3c07ada and a420b9f.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

[EmmaQiaoCh]

/bot run

[EmmaQiaoCh]

/bot run

[tensorrt-cicd]

PR_Github #61488 [ run ] triggered by Bot. Commit: a420b9f Link to invocation

[tensorrt-cicd]

PR_Github #61488 [ run ] completed with state FAILURE. Commit: a420b9f
/LLM/main/L0_MergeRequest_PR pipeline #49707 completed with status: 'ABORTED'

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

[EmmaQiaoCh]

/bot run

[tensorrt-cicd]

PR_Github #61491 [ run ] triggered by Bot. Commit: a420b9f Link to invocation

[tensorrt-cicd]

PR_Github #61491 [ run ] completed with state SUCCESS. Commit: a420b9f
/LLM/main/L0_MergeRequest_PR pipeline #49710 completed with status: 'SUCCESS'

CI Report

Link to invocation