[None][ci] disable autodeploy test stages

AGENTS.md

@@ -167,7 +167,6 @@ See [CI overview](docs/source/developer-guide/ci-overview.md) for full details.
 CI is triggered by posting comments on the PR. Basic commands:
 - `/bot run` — trigger the standard CI pipeline
 - `/bot run --disable-fail-fast` — run all stages even if earlier ones fail (only add when explicitly needed)
-- `/bot run --extra-stage "DGX_B200-4_GPUs-AutoDeploy-1, DGX_H100-4_GPUs-AutoDeploy-1"` — include AutoDeploy CI stages (use for AutoDeploy-related PRs)
 
 For a full list of up-to-date bot commands, post `/bot help` as a PR comment and check the bot's reply.
 

jenkins/L0_MergeRequest.groovy

@@ -1248,7 +1248,6 @@ def getMultiGpuFileChanged(pipeline, testFilter, globalVars)
         "tensorrt_llm/_torch/pyexecutor/model_engine.py",
         "tensorrt_llm/_torch/pyexecutor/py_executor.py",
         "tensorrt_llm/_torch/weight_sharing/",
-        "tensorrt_llm/_torch/auto_deploy/transform/library/sharding.py",
         "tensorrt_llm/_torch/visual_gen/attention_backend/parallel.py",
         "tensorrt_llm/_torch/visual_gen/modules/vae/",
         "tensorrt_llm/_torch/visual_gen/modules/attention.py",
@@ -1313,7 +1312,6 @@ def getMultiGpuFileChanged(pipeline, testFilter, globalVars)
         "tests/integration/test_lists/test-db/l0_model_express.yml",
         "tests/integration/test_lists/test-db/l0_rtx_pro_6000.yml",
         "tests/integration/test_lists/test-db/l0_verl.yml",
-        "tests/unittest/auto_deploy/multigpu",
         "tests/unittest/_torch/multi_gpu/",
         "tests/unittest/_torch/multi_gpu_modeling/",
         "tests/unittest/_torch/visual_gen/multi_gpu/",
@@ -1323,7 +1321,6 @@ def getMultiGpuFileChanged(pipeline, testFilter, globalVars)
         "tests/integration/defs/accuracy/test_disaggregated_serving.py",
         "tests/unittest/_torch/ray_orchestrator/multi_gpu/",
         "tests/integration/defs/examples/test_ray.py",
-        "tests/integration/defs/accuracy/test_llm_api_autodeploy.py",
         "tests/unittest/llmapi/test_async_llm.py",
         "docker/common/install_ucx.sh",
         "docker/common/install_nixl.sh",

jenkins/L0_Test.groovy

@@ -4033,10 +4033,6 @@ def getMakoArgsFromStageName(stageName, parseSysinfo=false) {
         // If stageName contains "-FMHA-", add "backend=fmha" to makoArgs
         // At this point, only tests with backend=fmha or unspecified backend will be run
         makoArgs += ["backend=fmha"]
-    } else if (stageName.contains("-AutoDeploy-")) {
-        // If stageName contains "-AutoDeploy-", add "backend=autodeploy" to makoArgs
-        // At this point, only tests with backend=autodeploy or unspecified backend will be run
-        makoArgs += ["backend=autodeploy"]
     } else if (stageName.contains("-Generic-")) {
         // Generic stages select tests by marker expression rather than backend ownership.
         makoArgs += ["backend=generic"]
@@ -4045,7 +4041,7 @@ def getMakoArgsFromStageName(stageName, parseSysinfo=false) {
         // At this point, only tests with backend=verl or unspecified backend will be run
         makoArgs += ["backend=verl"]
     } else {
-        // If stageName does not contain "-PyTorch-", "-CPP-", "-Triton-", "-FMHA-", "-AutoDeploy-", or "-Verl-", do not add any backend
+        // If stageName does not contain "-PyTorch-", "-CPP-", "-Triton-", "-FMHA-", or "-Verl-", do not add any backend
         // At this point, all tests will be run
         // For cases where backend is not specified in makoArgs, we will match all types of backends and tests without specified backend
     }
@@ -5863,12 +5859,10 @@ def launchTestJobs(pipeline, testFilter, globalVars)
         "A30-PyTorch-1": ["a30", "l0_a30", 1, 2],
         "A30-PyTorch-2": ["a30", "l0_a30", 2, 2],
         "A30-CPP-1": ["a30", "l0_a30", 1, 1],
-        "A30-AutoDeploy-1": ["a30", "l0_a30", 1, 1],
         "A100X-PyTorch-1": ["a100x", "l0_a100", 1, 1],
         "L40S-PyTorch-1": ["l40s", "l0_l40s", 1, 2],
         "L40S-PyTorch-2": ["l40s", "l0_l40s", 2, 2],
         "H100_PCIe-PyTorch-Ray-1": ["h100-cr", "l0_h100", 1, 1],
-        "H100_PCIe-AutoDeploy-1": ["h100-cr", "l0_h100", 1, 1],
         "H100_PCIe-CPP-1": ["h100-cr", "l0_h100", 1, 1],
         // platform, test DB, split, splits, GPU count, ModelExpress sidecars
         "DGX_H100-2_GPUs-PyTorch-ModelExpress-1": ["dgx-h100-x4", "l0_model_express", 1, 1, 2, true],
@@ -5890,7 +5884,6 @@ def launchTestJobs(pipeline, testFilter, globalVars)
         "A100X-PyTorch-Post-Merge-1": ["a100x", "l0_a100", 1, 1],
         "L40S-PyTorch-Post-Merge-1": ["l40s", "l0_l40s", 1, 1],
         "L40S-FMHA-Post-Merge-1": ["l40s", "l0_l40s", 1, 1],
-        "H100_PCIe-AutoDeploy-Post-Merge-1": ["h100-cr", "l0_h100", 1, 1],
         "H100_PCIe-FMHA-Post-Merge-1": ["h100-cr", "l0_h100", 1, 1],
         "H100_PCIe-PyTorch-Perf-1": ["h100-cr", "l0_perf", 1, 1],
         "DGX_H200-8_GPUs-PyTorch-Post-Merge-1": ["dgx-h200-x8", "l0_dgx_h200", 1, 1, 8],
@@ -5940,8 +5933,6 @@ def launchTestJobs(pipeline, testFilter, globalVars)
         "DGX_H100-4_GPUs-PyTorch-Others-1": ["auto:dgx-h100-x4", "l0_dgx_h100", 1, 2, 4],
         "DGX_H100-4_GPUs-PyTorch-Others-2": ["auto:dgx-h100-x4", "l0_dgx_h100", 2, 2, 4],
         "DGX_H100-4_GPUs-PyTorch-Ray-1": ["auto:dgx-h100-x4", "l0_dgx_h100", 1, 1, 4],
-        "DGX_H100-4_GPUs-AutoDeploy-1": ["auto:dgx-h100-x4", "l0_dgx_h100", 1, 1, 4],
-        "DGX_H100-4_GPUs-AutoDeploy-Post-Merge-1": ["auto:dgx-h100-x4", "l0_dgx_h100", 1, 1, 4],
         "DGX_H100-4_GPUs-PyTorch-Post-Merge-1": ["auto:dgx-h100-x4", "l0_dgx_h100", 1, 1, 4],
         "DGX_B200-PyTorch-1": ["auto:dgx-b200-flex", "l0_b200", 1, 9, 1, 1, true],
         "DGX_B200-PyTorch-2": ["auto:dgx-b200-flex", "l0_b200", 2, 9, 1, 1, true],
@@ -5952,17 +5943,13 @@ def launchTestJobs(pipeline, testFilter, globalVars)
         "DGX_B200-PyTorch-7": ["auto:dgx-b200-flex", "l0_b200", 7, 9, 1, 1, true],
         "DGX_B200-PyTorch-8": ["auto:dgx-b200-flex", "l0_b200", 8, 9, 1, 1, true],
         "DGX_B200-PyTorch-9": ["auto:dgx-b200-flex", "l0_b200", 9, 9, 1, 1, true],
-        "DGX_B200-AutoDeploy-1": ["auto:dgx-b200-flex", "l0_b200", 1, 1, 1, 1, true],
-        "DGX_B200-AutoDeploy-Post-Merge-1": ["auto:dgx-b200-flex", "l0_b200", 1, 1, 1, 1, true],
         "DGX_B200-PyTorch-Post-Merge-1": ["auto:dgx-b200-flex", "l0_b200", 1, 2, 1, 1, true],
         "DGX_B200-PyTorch-Post-Merge-2": ["auto:dgx-b200-flex", "l0_b200", 2, 2, 1, 1, true],
         "DGX_B200-2_GPUs-PyTorch-1": ["auto:dgx-b200-flex", "l0_dgx_b200", 1, 1, 2, 1, true],
         "DGX_B200-4_GPUs-PyTorch-1": ["auto:dgx-b200-flex", "l0_dgx_b200", 1, 3, 4, 1, true],
         "DGX_B200-4_GPUs-PyTorch-2": ["auto:dgx-b200-flex", "l0_dgx_b200", 2, 3, 4, 1, true],
         "DGX_B200-4_GPUs-PyTorch-3": ["auto:dgx-b200-flex", "l0_dgx_b200", 3, 3, 4, 1, true],
         "DGX_B200-4_GPUs-PyTorch-Ray-1": ["auto:dgx-b200-flex", "l0_dgx_b200", 1, 1, 4, 1, true],
-        "DGX_B200-4_GPUs-AutoDeploy-1": ["auto:dgx-b200-flex", "l0_dgx_b200", 1, 1, 4, 1, true],
-        "DGX_B200-4_GPUs-AutoDeploy-Post-Merge-1": ["auto:dgx-b200-flex", "l0_dgx_b200", 1, 1, 4, 1, true],
         "DGX_B200-4_GPUs-PyTorch-Post-Merge-1": ["auto:dgx-b200-flex", "l0_dgx_b200", 1, 4, 4, 1, true],
         "DGX_B200-4_GPUs-PyTorch-Post-Merge-2": ["auto:dgx-b200-flex", "l0_dgx_b200", 2, 4, 4, 1, true],
         "DGX_B200-4_GPUs-PyTorch-Post-Merge-3": ["auto:dgx-b200-flex", "l0_dgx_b200", 3, 4, 4, 1, true],
@@ -5972,7 +5959,6 @@ def launchTestJobs(pipeline, testFilter, globalVars)
         "DGX_B200-8_GPUs-PyTorch-3": ["auto:dgx-b200-flex", "l0_dgx_b200", 3, 4, 8, 1, true],
         "DGX_B200-8_GPUs-PyTorch-4": ["auto:dgx-b200-flex", "l0_dgx_b200", 4, 4, 8, 1, true],
         "DGX_B200-8_GPUs-PyTorch-Ray-1": ["auto:dgx-b200-flex", "l0_dgx_b200", 1, 1, 8, 1, true],
-        "DGX_B200-8_GPUs-AutoDeploy-Post-Merge-1": ["auto:dgx-b200-flex", "l0_dgx_b200", 1, 1, 8, 1, true],
         "DGX_B200-4_GPUs-Verl-Post-Merge-1": ["auto:dgx-b200-flex", "l0_verl", 1, 1, 4, 1, true],
         "B300-PyTorch-1": ["auto:dgx-b300-flex", "l0_b300", 1, 2, 1, 1, true],
         "B300-PyTorch-2": ["auto:dgx-b300-flex", "l0_b300", 2, 2, 1, 1, true],

tests/integration/test_lists/qa/llm_function_core.txt

@@ -76,46 +76,6 @@ accuracy/test_dwdp_disaggregated_serving.py::TestDwdpDeepSeekV3Lite::test_dwdp_a
 accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[nemotron_nano_v3_omni_fp8]
 accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[nemotron_nano_v3_omni_nvfp4]
 accuracy/test_epd_disagg_multimodal.py::TestVideoMMEEPD::test_disaggregated_videomme[qwen3vl_2b_instruct]
-accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_attention_dp[4]
-accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[torch-True-1]
-accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[triton-False-1]
-accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[trtllm-False-1]
-accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[trtllm-False-4]
-accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[trtllm-True-1]
-accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B_Instruct_Eagle3::test_eagle3_one_model[flashinfer]
-accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B_Instruct_Eagle3::test_eagle3_one_model[trtllm]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[Qwen_QwQ-32B-False]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[deepseek-ai_DeepSeek-R1-0528-True]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[google_gemma-3-1b-it-False]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[meta-llama_Llama-3.1-8B-Instruct-False]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[meta-llama_Llama-3.3-70B-Instruct-False]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[mistralai_Ministral-8B-Instruct-2410-False]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_DeepSeek-R1-0528-NVFP4-v2-True]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-FP8-True]
-accuracy/test_llm_api_autodeploy.py::TestModelRegistryAccuracy::test_autodeploy_from_registry[nvidia_Llama-3.1-8B-Instruct-NVFP4-True]
-accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[bf16-1-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[bf16-4-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[fp8-1-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[fp8-4-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[nvfp4-1-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[nvfp4-4-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_accuracy[bf16-4-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_accuracy[bf16-4-attn_dp_on-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_accuracy[fp8-4-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_accuracy[fp8-4-attn_dp_on-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_accuracy[nvfp4-1-attn_dp_off-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_accuracy[nvfp4-4-attn_dp_on-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_functional_small[bf16]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_functional_small[fp8]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[bf16_ws4_180gb-flashinfer]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[bf16_ws4_180gb-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[fp8_ws4_80gb-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_mtp[nvfp4_ws4_80gb-trtllm]
-accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_auto_dtype[False]
-accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_auto_dtype[True]
-accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_fp8[True]
-accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_nvfp4[True]
-accuracy/test_llm_api_autodeploy.py::TestQwen3_5_397B_MoE::test_nvfp4[8]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[latency]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_fp8_blockscale[throughput_mtp]
@@ -804,11 +764,6 @@ accuracy/test_llm_api_pytorch_multimodal.py::TestQwen3_5_35B_A3B_VL::test_auto_d
 accuracy/test_llm_api_pytorch_multimodal.py::TestQwen3_5_35B_A3B_VL::test_fp8_prequantized
 accuracy/test_llm_api_pytorch_ray.py::TestLlama3_1_8BInstruct::test_pp2_ray
 unittest/disaggregated/test_cache_transceiver_single_process.py::test_cache_transceiver_v1_masked_dsa_indexer_across_asymmetric_pp
-disaggregated/test_ad_disagg.py::test_async_eagle3_full_model_handoff
-disaggregated/test_ad_disagg.py::test_async_generation_matches_aggregate
-disaggregated/test_ad_disagg.py::test_async_generation_no_overlap_matches_aggregate
-disaggregated/test_ad_disagg.py::test_async_sharded_generation_handoff
-disaggregated/test_ad_disagg_trtllm_serve.py::test_openai_completion
 disaggregated/test_aiperf_gate.py::test_all_cancelled_fails
 disaggregated/test_aiperf_gate.py::test_corrupt_export_fails
 disaggregated/test_aiperf_gate.py::test_empty_export_fails

tests/integration/test_lists/qa/llm_function_rtx6k.txt

@@ -8,7 +8,6 @@ accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[False]
 accuracy/test_disaggregated_serving.py::TestGPTOSS::test_auto_dtype[True]
 accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_auto_dtype[False-False]
 accuracy/test_disaggregated_serving.py::TestQwen3_8B::test_auto_dtype[False-True]
-accuracy/test_llm_api_autodeploy.py::TestQwen3_5_397B_MoE::test_nvfp4[8]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus_sm120[throughput_tp8]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=False]
 accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_bfloat16[mtp_nextn=0-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False-enable_chunked_prefill=False-v2_kv_cache=True]

tests/integration/test_lists/test-db/l0_a30.yml

@@ -63,25 +63,3 @@ l0_a30:
   - cpp/test_unit_tests.py::test_unit_tests[layers-80]
   - cpp/test_unit_tests.py::test_unit_tests[runtime-80]
   - cpp/test_unit_tests.py::test_unit_tests[thop-80]
-# ------------- AutoDeploy Backend Stages ---------------
-- condition:
-    ranges:
-      system_gpu_count:
-        gte: 1
-        lte: 1
-    wildcards:
-      gpu:
-      - '*a30*'
-      linux_distribution_name: ubuntu*
-    terms:
-      stage: pre_merge
-      backend: autodeploy
-  tests:
-  - unittest/auto_deploy/singlegpu/compile
-  - unittest/auto_deploy/singlegpu/custom_ops
-  - unittest/auto_deploy/singlegpu/mlir
-  - unittest/auto_deploy/singlegpu/models
-  - unittest/auto_deploy/singlegpu/shim
-  - unittest/auto_deploy/singlegpu/smoke
-  - unittest/auto_deploy/singlegpu/transformations
-  - unittest/auto_deploy/singlegpu/utils

tests/integration/test_lists/test-db/l0_b200.yml

@@ -439,66 +439,3 @@ l0_b200:
   - unittest/_torch/modules/moe/test_moe_backend.py::test_moe_backend -k "MEGAMOE_DEEPGEMM"
   # ---- non-quantized (quant=None) moved to post-merge ----
   - unittest/_torch/modules/moe/test_moe_module.py::test_configurable_moe_single_gpu -k "CUTLASS and None"
-# ------------- AutoDeploy Backend Stages ---------------
-- condition:
-    ranges:
-      system_gpu_count:
-        gte: 1
-        lte: 1
-    wildcards:
-      gpu:
-      - '*b100*'
-      - '*b200*'
-      linux_distribution_name: ubuntu*
-    terms:
-      stage: pre_merge
-      backend: autodeploy
-  tests:
-  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[trtllm-False-1]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_fp8[True]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[fp8-1-attn_dp_off-trtllm]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_accuracy[nvfp4-1-attn_dp_off-trtllm]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_functional_small[bf16]
-  # ------------- AutoDeploy unit tests ---------------
-  # B-tier keeps only Blackwell-meaningful tests (NVFP4 / FP4 / TRTLLM-Gen /
-  # SM100+-gated). HW-agnostic tests (compile, models, shim, utils, plus most
-  # custom_ops, smoke, transformations files) and pure-FP8 tests are covered
-  # on Hopper (l0_h100.yml) and not duplicated here.
-  - unittest/auto_deploy/singlegpu/custom_ops/attention/test_triton_attention.py::TestSDPADispatch
-  - unittest/auto_deploy/singlegpu/custom_ops/mamba/test_flashinfer_mamba_cached_op.py
-  - unittest/auto_deploy/singlegpu/custom_ops/moe/test_ad_moe_op.py
-  - unittest/auto_deploy/singlegpu/custom_ops/moe/test_trtllm_moe.py
-  - unittest/auto_deploy/singlegpu/custom_ops/quantization/test_quant.py
-  - unittest/auto_deploy/singlegpu/smoke/test_ad_build_small_single.py -k "Nemotron-3-Nano-30B-A3B-FP8 or Nemotron-Nano-3-30B-A3.5B-dev or Llama-4-Scout"
-  - unittest/auto_deploy/singlegpu/smoke/test_ad_speculative_decoding.py
-  - unittest/auto_deploy/singlegpu/transformations/library/test_fuse_relu2_quant_nvfp4.py
-  - unittest/auto_deploy/singlegpu/transformations/library/test_moe_fusion.py
-  - unittest/auto_deploy/singlegpu/transformations/library/test_nvfp4_swiglu.py
-  - unittest/auto_deploy/singlegpu/transformations/library/test_quant_fusion.py
-  - unittest/auto_deploy/singlegpu/transformations/library/test_quant_moe.py
-  - unittest/auto_deploy/singlegpu/transformations/library/test_quantization.py
-  - unittest/auto_deploy/singlegpu/transformations/library/test_trtllm_gen_diag.py
-
-- condition:
-    ranges:
-      system_gpu_count:
-        gte: 1
-        lte: 1
-    wildcards:
-      gpu:
-      - '*b100*'
-      - '*b200*'
-      linux_distribution_name: ubuntu*
-    terms:
-      stage: post_merge
-      backend: autodeploy
-  tests:
-  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[triton-False-1]
-  - accuracy/test_llm_api_autodeploy.py::TestLlama3_1_8B::test_auto_dtype[torch-True-1]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_auto_dtype[False]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_auto_dtype[True]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronV2::test_nvfp4[True]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronNanoV3::test_accuracy[nvfp4-1-attn_dp_off-trtllm]
-  - accuracy/test_llm_api_autodeploy.py::TestNemotronSuperV3::test_functional_small[fp8]
-  # ------------- AutoDeploy Perf Sanity ---------------
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-super_ad_blackwell-super_ad_ws1_1k1k] TIMEOUT (120)

tests/integration/test_lists/test-db/l0_cpu.yml

@@ -24,7 +24,6 @@ l0_cpu:
   - disaggregated/test_aiperf_gate.py::test_was_cancelled_metadata_fallback
   - disaggregated/test_aiperf_gate.py::test_non_request_records_excluded_from_denominator
   - unittest/_torch/attention
-  - unittest/_torch/auto_deploy
   - unittest/_torch/cute_dsl/test_kimi_k3_kda_ptx_patch.py
   - unittest/_torch/distributed
   - unittest/_torch/executor
@@ -58,9 +57,6 @@ l0_cpu:
   - unittest/_torch/visual_gen/test_visual_gen_utils.py
   - unittest/_torch/weight_sharing
   - unittest/api_stability
-  - unittest/auto_deploy/multigpu
-  - unittest/auto_deploy/singlegpu
-  - unittest/auto_deploy/standalone
   - unittest/bindings
   - unittest/disaggregated
   - unittest/dynamo