[None][test] Remove 60 closed-bug waive entries for main

[tensorrt-cicd]

Auto-generated Un-waive PR

Created by: TensorRT LLM CI (requested by qa@nvidia.com)
Target branch: main
Jenkins build: https://prod.blsm.nvidia.com/swqa-tensorrt-qa-test/job/LLM_UPDATE_WAIVES/112/
Closed bug(s) un-waived: 4731514, 5569696, 5772995, 5989907, 6075556, 6085022, 6094070, 6114608, 6115560, 6144270, 6185196, 6190759, 6193778, 6199854, 6200128, 6200257, 6211191, 6212250, 6215689, 6215844, 6224636, 6245317, 6260915, 6262407, 6276985, 6278350, 6280649, 6302880, 6307525, 6317601, 6322071, 6329216, 6329256

Waive entries removed

accuracy/test_llm_api.py::TestLlama3_1_8BInstruct::test_gather_generation_logits_cuda_graph SKIP (https://nvbugs/5772995)
accuracy/test_llm_api_pytorch.py::TestDeepSeekR1LongBenchV2::test_fp8_8gpus SKIP (https://nvbugs/6193778)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_dsa_host_cache_offload[host_cache_offload] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_dsa_host_cache_offload[host_cache_offload_mtp1] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_dsa_host_cache_offload[host_cache_offload_mtp3_no_adp] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[baseline] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_fp8_blockscale[latency_default] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baseline] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus[baseline_mtp1] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV32::test_nvfp4_multi_gpus_piecewise_cuda_graph[baseline] SKIP (https://nvbugs/6185196)
accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_cute_dsl_bf16_gemm_4gpus[tp4-cuda_graph=False] SKIP (https://nvbugs/6224636)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_1gpu[v2_kv_cache-True-True-trtllm-fp8] SKIP (https://nvbugs/6276985)
accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_chunked_prefill[trtllm-auto] SKIP (https://nvbugs/6278350)
accuracy/test_llm_api_pytorch.py::TestKimiK25::test_nvfp4[tp8_attn_dp] SKIP (https://nvbugs/6144270)
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[pp4-attn_backend=FLASHINFER-torch_compile=False] SKIP (https://nvbugs/6075556)
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[pp4-fp8kv=True-attn_backend=FLASHINFER-torch_compile=False] SKIP (https://nvbugs/6211191)
accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[tp4-fp8kv=False-attn_backend=TRTLLM-torch_compile=True] SKIP (https://nvbugs/6211191)
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention_4gpus[target_sparsity_0.5-fp8kv=False] SKIP (https://nvbugs/6260915)
accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B_Instruct_2507::test_skip_softmax_attention_4gpus[target_sparsity_0.9-fp8kv=False] SKIP (https://nvbugs/6260915)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_9B::test_bf16[mtp_off] SKIP (https://nvbugs/6212250)
accuracy/test_llm_api_pytorch.py::TestQwen3_5_9B::test_bf16[mtp_on] SKIP (https://nvbugs/6212250)
accuracy/test_llm_api_pytorch.py::TestQwen3_8B::test_fp8_block_scales_early_first_token_response SKIP (https://nvbugs/6200128)
accuracy/test_llm_api_pytorch_multimodal.py::TestGemma3_27BInstruct::test_fp8_prequantized SKIP (https://nvbugs/6215689)
accuracy/test_llm_api_pytorch_ray.py::TestLlama3_1_8BInstruct::test_pp2_ray SKIP (https://nvbugs/6094070)
disaggregated/test_disaggregated.py::test_disaggregated_gpt_oss_120b_harmony[gpt_oss/gpt-oss-120b] SKIP (https://nvbugs/6245317)
full:B300/accuracy/test_disaggregated_serving.py::TestLlama3_1_8BInstruct::test_auto_dtype[False-False-False-False] SKIP (https://nvbugs/6322071)
full:GB200/test_e2e.py::test_openai_chat_harmony_perf_metrics SKIP (https://nvbugs/6317601)
full:GH200/examples/test_multimodal.py::test_llm_multimodal_general[video-neva-pp:1-tp:1-bfloat16-bs:1-cpp_e2e:False-nb:1] SKIP (https://nvbugs/4731514)
full:H100/accuracy/test_llm_api_pytorch.py::TestQwen3_5_35B_A3B::test_bf16_mtp[mtp_off] SKIP (https://nvbugs/6329216)
full:RTX/accuracy/test_llm_api_pytorch.py::TestGemma3_1BInstruct::test_auto_dtype SKIP (https://nvbugs/5569696)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_fp4_tp2pp2[torch_compile=True-enable_gemm_allreduce_fusion=False] SKIP (https://nvbugs/6262407)
full:RTX_PRO_6000_Blackwell_Server_Edition/accuracy/test_llm_api_pytorch.py::TestLlama3_3_70BInstruct::test_nvfp4_tp4[torch_compile=False] SKIP (https://nvbugs/6262407)
perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-float16-input_output_len:128,128-reqs:8192] SKIP (https://nvbugs/6329256)
perf/test_perf.py::test_perf[llama_v3.1_8b_instruct-bench-pytorch-float16-input_output_len:128,128-reqs:8192] SKIP (https://nvbugs/6329256)
perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-r1-fp4_128k8k_con128_ctx1_pp8_gen1_dep16_eplb0_mtp1_ccb-NIXL] SKIP (https://nvbugs/6215844)
perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-v32-fp4_1k1k_con2048_ctx1_dep4_gen1_dep4_eplb0_mtp1_ccb-NIXL] SKIP (https://nvbugs/6280649)
perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_qwen3-235b-fp4_8k1k_con1024_ctx1_tp1_gen1_dep8_eplb0_mtp0_ccb-NIXL] SKIP (https://nvbugs/6302880)
perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb300_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-NIXL] SKIP (https://nvbugs/6280649)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_1k1k_con1024_ctx1_dep4_gen1_dep32_eplb256_mtp3_ccb-NIXL] SKIP (https://nvbugs/6280649)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_1k1k_con2048_ctx1_dep4_gen1_dep4_eplb0_mtp1_ccb-NIXL] SKIP (https://nvbugs/6280649)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con2048_ctx1_dep4_gen1_dep32_eplb288_mtp1_ccb-NIXL] SKIP (https://nvbugs/6280649)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con256_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-NIXL] SKIP (https://nvbugs/6280649)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_32k4k_con256_ctx1_dep8_gen1_dep8_eplb0_mtp0_ccb-NIXL] SKIP (https://nvbugs/6085022)
perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb256_mtp3_ccb-NIXL] SKIP (https://nvbugs/6200257)
test_e2e.py::test_draft_token_tree_quickstart_advanced_eagle3[Llama-3.1-8b-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct-EAGLE3-LLaMA3.1-Instruct-8B] SKIP (https://nvbugs/5989907)
test_e2e.py::test_draft_token_tree_quickstart_advanced_eagle3_depth_1_tree[Llama-3.1-8b-Instruct-llama-3.1-model/Llama-3.1-8B-Instruct-EAGLE3-LLaMA3.1-Instruct-8B] SKIP (https://nvbugs/5989907)
test_e2e.py::test_multi_nodes_eval[Qwen3/Qwen3-235B-A22B-tp16-mmlu] SKIP (https://nvbugs/6115560)
test_e2e.py::test_multi_nodes_eval[Qwen3/saved_models_Qwen3-235B-A22B_nvfp4_hf-tp16-mmlu] SKIP (https://nvbugs/6114608)
test_e2e.py::test_openai_disagg_multi_nodes_completion[ctx_tp1pp2-gen_tp1pp2] SKIP (https://nvbugs/6190759)
unittest/_torch/visual_gen/test_flux_pipeline.py::TestFluxCombinedOptimizations::test_all_optimizations_combined SKIP (https://nvbugs/6199854)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_batch_smoke[deepseek-trtllm-simple] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_batch_smoke[llama-flashinfer-cudagraph] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_batch_smoke[llama-flashinfer-simple] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_batch_smoke[llama-trtllm-cudagraph] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_batch_smoke[llama-trtllm-simple] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_smoke[deepseek-trtllm-simple] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_smoke[llama-flashinfer-cudagraph] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_smoke[llama-flashinfer-simple] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_smoke[llama-trtllm-cudagraph] SKIP (https://nvbugs/6307525)
unittest/auto_deploy/singlegpu/smoke/test_disagg.py::test_autodeploy_disaggregated_smoke[llama-trtllm-simple] SKIP (https://nvbugs/6307525)

---

This PR was auto-generated by TensorRT LLM CI. Please review before merging.

Summary by CodeRabbit

• Tests
  • Updated test waiver configuration to adjust which integration tests are skipped, modifying coverage for various test categories including accuracy, performance, and disaggregated serving scenarios.

[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: Enterprise

Run ID: 6df91f6a-f072-4cb8-9447-d4921cc9f8fc

📥 Commits

Reviewing files that changed from the base of the PR and between 9ed7ce4 and e39b704.

📒 Files selected for processing (1)

• tests/integration/test_lists/waives.txt

💤 Files with no reviewable changes (1)

• tests/integration/test_lists/waives.txt

---

📝 Walkthrough

Walkthrough

Updates tests/integration/test_lists/waives.txt (net -60 lines) by removing and replacing SKIP entries across accuracy API tests, disaggregated tests, platform-scoped full-suite variants, perf benchmarks, e2e multi-node evaluations, and the auto-deploy smoke test block.

Changes

Integration Test Waive List Updates

Layer / File(s)	Summary
Accuracy API test waive replacements tests/integration/test_lists/waives.txt	Swaps DeepSeekV32/gather-CUDA-graph entries for xgrammar/fp8/nvfp4 variants; removes one DeepSeekV3Lite cute_dsl entry; replaces GPTOSS w4 trtllm-auto entries with cutlass-auto; adjusts Kanana/KimiK25/Llama3 fp8/bf16 compile waivers; updates Qwen3 fp8kv/target_sparsity and NanoV3Omni nvfp4 multimodal entries.
Disaggregated test waive removals tests/integration/test_lists/waives.txt	Removes the disaggregated/test_disaggregated.py gpt_oss_120b harmony waiver and the full:B300 disaggregated serving Llama3 auto_dtype waiver.
Platform-scoped and perf test waive replacements tests/integration/test_lists/waives.txt	Removes GB200 openai chat harmony perf waiver; replaces GH200 video-neva entry with nemotron/qwen2audio/quantization waivers; removes RTX Gemma3 auto_dtype and RTX_PRO Llama3 fp4/nvfp4 tp entries; removes perf/test_perf.py llama float16 variants; replaces perf/test_perf_sanity.py disagg_upload/gen_only set with NIXL-scoped DeepSeek-R1 and DeepSeek-v32 fp4 parameter combinations.
E2E multi-node and auto-deploy smoke waive replacements tests/integration/test_lists/waives.txt	Removes draft-token-tree quickstart and Qwen3/openai_disagg multi-node eval entries from test_e2e.py; adds DeepSeek-R1 TP16 mmlu, Kimi-K2 NVFP4 TP16 mmlu, and openai chat/completions trt waivers; collapses unittest/auto_deploy/singlegpu/smoke to a single SKIP entry referencing nvbugs/6306936.

Estimated code review effort

🎯 2 (Simple) | ⏱️ ~10 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#6201: Modifies the same tests/integration/test_lists/waives.txt file by removing SKIP/waiver entries for specific test parameterizations, directly overlapping with this PR's change set.

Suggested reviewers

• crazydemo
• syuoni
• yiqingy0
• venkywonka
• LarryXFly

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title accurately summarizes the main change: removing 60 closed-bug waive entries from the test waive list for the main branch.
Description check	✅ Passed	The PR description provides comprehensive details about the auto-generated changes, including the target branch, Jenkins build link, specific bug IDs being un-waived, and a detailed list of all 60 removed waive entries with their associated bug references.
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.}

[tensorrt-cicd]

PR_Github #118 [ run ] triggered by Bot. Commit: e39b704 Link to invocation

[tensorrt-cicd]

PR_Github #55112 [ run ] triggered by Bot. Commit: e39b704 Link to invocation

[tensorrt-cicd]

PR_Github #118 [ run ] completed with state FAILURE. Commit: e39b704
/LLM/PipelineMonitor/L0_MergeRequest_PR pipeline #92 (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

CI Agent Failure Analysis

Link to invocation

[xinhe-nv]

/bot run --reuse-test 15511

[tensorrt-cicd]

PR_Github #55147 [ run ] triggered by Bot. Commit: b706ce5 Link to invocation

[tensorrt-cicd]

PR_Github #55147 [ run ] completed with state SUCCESS. Commit: b706ce5
/LLM/main/L0_MergeRequest_PR pipeline #44123 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 skip --comment "only waive tests"

[tensorrt-cicd]

PR_Github #55165 Bot args parsing error: usage: /bot skip --comment COMMENT
/bot skip: error: the following arguments are required: --comment

Link to invocation

[tensorrt-cicd]

PR_Github #55166 [ skip ] triggered by Bot. Commit: 92e19f3 Link to invocation

[tensorrt-cicd]

PR_Github #55166 [ skip ] completed with state SUCCESS. Commit: 92e19f3
Skipping testing for commit 92e19f3

Link to invocation