[None][test] Remove all 1k1k perf-sanity cases from CI (NVIDIA#16535)

Signed-off-by: chenfeiz0326 <chenfeiz@nvidia.com>

Author: chenfeiz0326

jenkins/L0_MergeRequest.groovy

@@ -1047,22 +1047,18 @@ def getMultiGpuFileChanged(pipeline, testFilter, globalVars)
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu1_gen1_node1_gpu2.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu1_gen1_node1_gpu4.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu1_gen1_node2_gpu8.yml",
-        "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node4_gpu16.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node8_gpu32.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node2_gpu8_gen1_node2_gpu8.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node2_gpu8_gen1_node4_gpu16.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node2_gpu8_gen1_node8_gpu32.yml",
-        "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx2_node1_gpu4_gen1_node4_gpu16.yml",
         "tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_node2_gpu8.yml",
         "tests/integration/test_lists/test-db/l0_gb300.yml",
         "tests/integration/test_lists/test-db/l0_gb300_multi_gpus.yml",
         "tests/integration/test_lists/test-db/l0_gb300_multi_gpus_perf_sanity.yml",
-        "tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu2_gen1_node1_gpu4.yml",
         "tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu2_gen1_node2_gpu8.yml",
         "tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu2_gen1_node8_gpu32.yml",
-        "tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4.yml",
         "tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8.yml",
         "tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node4_gpu16.yml",
         "tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_node2_gpu8.yml",

jenkins/L0_Test.groovy

@@ -4876,12 +4876,10 @@ def launchTestJobs(pipeline, testFilter)
         // VisualGen PerfSanity post-merge test
         "DGX_B200-8_GPUs-PyTorch-VisualGen-PerfSanity-Post-Merge-1": ["auto:dgx-b200-flex", "l0_b200_visual_gen_perf_sanity", 1, 1, 8, 1, true],
         // PerfSanity post-merge tests
-        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 1, 6, 8, 1, true],
-        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 2, 6, 8, 1, true],
-        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-3": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 3, 6, 8, 1, true],
-        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-4": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 4, 6, 8, 1, true],
-        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-5": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 5, 6, 8, 1, true],
-        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-6": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 6, 6, 8, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 1, 4, 8, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 2, 4, 8, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-3": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 3, 4, 8, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-4": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 4, 4, 8, 1, true],
     ]
     // B200 PerfSanity pre-merge disaggregated (functional-only: perf regressions do not fail CI)
     // 2 Nodes
@@ -4899,7 +4897,7 @@ def launchTestJobs(pipeline, testFilter)
         "DGX_B200-16_GPUs-2_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE1-GPU8-Post-Merge",
         "auto:dgx-b200-flex",
         "l0_b200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu8",
-        5,
+        2,
         16,
         2
     )
@@ -4961,18 +4959,12 @@ def launchTestJobs(pipeline, testFilter)
         "GB200-4_GPUs-PyTorch-PerfSanity-1": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 1, 2, 4],
         "GB200-4_GPUs-PyTorch-PerfSanity-2": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 2, 2, 4],
         // PerfSanity post-merge tests
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 1, 9, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 2, 9, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-3": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 3, 9, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-4": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 4, 9, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-5": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 5, 9, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-6": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 6, 9, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-7": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 7, 9, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-8": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 8, 9, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-9": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 9, 9, 4],
-        "GB300-4_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:gb300-x4", "l0_gb300_multi_gpus_perf_sanity", 1, 3, 4],
-        "GB300-4_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:gb300-x4", "l0_gb300_multi_gpus_perf_sanity", 2, 3, 4],
-        "GB300-4_GPUs-PyTorch-PerfSanity-Post-Merge-3": ["auto:gb300-x4", "l0_gb300_multi_gpus_perf_sanity", 3, 3, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 1, 4, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 2, 4, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-3": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 3, 4, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-4": ["auto:gb200-x4-split", "l0_gb200_multi_gpus_perf_sanity", 4, 4, 4],
+        "GB300-4_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:gb300-x4", "l0_gb300_multi_gpus_perf_sanity", 1, 2, 4],
+        "GB300-4_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:gb300-x4", "l0_gb300_multi_gpus_perf_sanity", 2, 2, 4],
     ]
     SBSASlurmTestConfigs = cbtsResizeSplits(SBSASlurmTestConfigs)
     fullSet += SBSASlurmTestConfigs.keySet()
@@ -5012,22 +5004,14 @@ def launchTestJobs(pipeline, testFilter)
         "GB200-8_GPUs-2_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU1-GEN1-NODE1-GPU2-Post-Merge",
         "auto:gb200-flex",
         "l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu1_gen1_node1_gpu2",
-        4,
+        1,
         8,
         2
     )
     multiNodesSBSAConfigs += buildStageConfigs(
         "GB200-8_GPUs-2_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU1-GEN1-NODE1-GPU4-Post-Merge",
         "auto:gb200-flex",
         "l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu1_gen1_node1_gpu4",
-        6,
-        8,
-        2
-    )
-    multiNodesSBSAConfigs += buildStageConfigs(
-        "GB200-8_GPUs-2_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE1-GPU4-Post-Merge",
-        "auto:gb200-flex",
-        "l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4",
         5,
         8,
         2
@@ -5045,7 +5029,7 @@ def launchTestJobs(pipeline, testFilter)
         "GB200-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge",
         "auto:gb200-flex",
         "l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8",
-        8,
+        3,
         12,
         3
     )
@@ -5068,14 +5052,6 @@ def launchTestJobs(pipeline, testFilter)
         5
     )
     // 6 Nodes
-    multiNodesSBSAConfigs += buildStageConfigs(
-        "GB200-24_GPUs-6_Nodes-PyTorch-Disagg-PerfSanity-CTX2-NODE1-GPU4-GEN1-NODE4-GPU16-Post-Merge",
-        "auto:gb200-flex",
-        "l0_gb200_multi_nodes_perf_sanity_ctx2_node1_gpu4_gen1_node4_gpu16",
-        2,
-        24,
-        6
-    )
     multiNodesSBSAConfigs += buildStageConfigs(
         "GB200-24_GPUs-6_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE2-GPU8-GEN1-NODE4-GPU16-Post-Merge",
         "auto:gb200-flex",
@@ -5089,7 +5065,7 @@ def launchTestJobs(pipeline, testFilter)
         "GB200-36_GPUs-9_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE8-GPU32-Post-Merge",
         "auto:gb200-flex",
         "l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node8_gpu32",
-        12,
+        8,
         36,
         9
     )
@@ -5108,20 +5084,11 @@ def launchTestJobs(pipeline, testFilter)
         "GB300-8_GPUs-2_Nodes-PyTorch-PerfSanity-Node2-GPU8-Post-Merge",
         "auto:gb300-flex",
         "l0_gb300_multi_nodes_perf_sanity_node2_gpu8",
-        3,
+        2,
         8,
         2
     )
     // GB300 PerfSanity post-merge disaggregated
-    // 2 Nodes
-    multiNodesSBSAConfigs += buildStageConfigs(
-        "GB300-8_GPUs-2_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE1-GPU4-Post-Merge",
-        "auto:gb300-flex",
-        "l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu4",
-        3,
-        8,
-        2
-    )
     // 3 Nodes (pre-merge, functional-only)
     multiNodesSBSAConfigs += buildStageConfigs(
         "GB300-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-FUNCTIONAL-ONLY-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8",
@@ -5136,7 +5103,7 @@ def launchTestJobs(pipeline, testFilter)
         "GB300-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE2-GPU8-Post-Merge",
         "auto:gb300-flex",
         "l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node2_gpu8",
-        4,
+        2,
         12,
         3
     )
@@ -5154,20 +5121,11 @@ def launchTestJobs(pipeline, testFilter)
         "GB300-36_GPUs-9_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU4-GEN1-NODE8-GPU32-Post-Merge",
         "auto:gb300-flex",
         "l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node8_gpu32",
-        2,
+        1,
         36,
         9
     )
     // GB300 GLM-5 disaggregated (ctx DEP2)
-    // 2 Nodes
-    multiNodesSBSAConfigs += buildStageConfigs(
-        "GB300-8_GPUs-2_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU2-GEN1-NODE1-GPU4-Post-Merge",
-        "auto:gb300-flex",
-        "l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu2_gen1_node1_gpu4",
-        1,
-        8,
-        2
-    )
     // 3 Nodes (pre-merge, functional-only)
     multiNodesSBSAConfigs += buildStageConfigs(
         "GB300-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-FUNCTIONAL-ONLY-CTX1-NODE1-GPU2-GEN1-NODE2-GPU8",
@@ -5182,7 +5140,7 @@ def launchTestJobs(pipeline, testFilter)
         "GB300-12_GPUs-3_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU2-GEN1-NODE2-GPU8-Post-Merge",
         "auto:gb300-flex",
         "l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu2_gen1_node2_gpu8",
-        4,
+        2,
         12,
         3
     )
@@ -5191,7 +5149,7 @@ def launchTestJobs(pipeline, testFilter)
         "GB300-36_GPUs-9_Nodes-PyTorch-Disagg-PerfSanity-CTX1-NODE1-GPU2-GEN1-NODE8-GPU32-Post-Merge",
         "auto:gb300-flex",
         "l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu2_gen1_node8_gpu32",
-        2,
+        1,
         36,
         9
     )

tests/integration/test_lists/test-db/l0_b200_multi_gpus_perf_sanity.yml

@@ -16,15 +16,11 @@ l0_b200_multi_gpus_perf_sanity:
       orchestrator: mpi
   tests:
   # deepseek_r1_fp8_blackwell
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp8_blackwell-r1_fp8_tp8_mtp3_1k1k]
-  # - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp8_blackwell-r1_fp8_dep8_mtp1_1k1k] TIMEOUT (90) # failed
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp8_blackwell-r1_fp8_tp8_mtp3_8k1k]
   # - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp8_blackwell-r1_fp8_dep8_mtp1_8k1k] TIMEOUT (90) # failed
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp8_blackwell-r1_fp8_tp8_6k1k] TIMEOUT (90)
   # deepseek-r1-fp4-v2
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_blackwell-r1_fp4_v2_tp4_mtp3_1k1k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_blackwell-r1_fp4_v2_tp4_mtp3_8k1k]
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_blackwell-r1_fp4_v2_dep8_mtp1_1k1k] TIMEOUT (90)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_blackwell-r1_fp4_v2_dep8_mtp1_8k1k] TIMEOUT (90)
   # deepseek-v32-fp4
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_v32_fp4_blackwell-v32_fp4_tep8_mtp3_8k1k]
@@ -33,8 +29,6 @@ l0_b200_multi_gpus_perf_sanity:
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-glm5_fp4_blackwell-glm5_fp4_tep8_mtp3_8k1k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-glm5_fp4_blackwell-glm5_fp4_dep8_mtp1_8k1k] TIMEOUT (90)
   # gpt-oss-120b-fp4
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-gpt_oss_120b_fp4_blackwell-gpt_oss_fp4_tp2_mtp0_1k1k]
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-gpt_oss_120b_fp4_blackwell-gpt_oss_fp4_tp1_mtp0_1k1k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-gpt_oss_120b_fp4_blackwell-gpt_oss_fp4_tp1_mtp0_8k1k]
   # llama-3.3-70b-instruct-fp4
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-llama_v3_3_70b_instruct_fp4_blackwell-llama70b_fp4_tp4_512_32]
@@ -46,18 +40,11 @@ l0_b200_multi_gpus_perf_sanity:
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-k25_thinking_fp4_blackwell-k25_thinking_fp4_dep8_32k8k] TIMEOUT (90)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-dynamo_k25_thinking_fp4_blackwell-k25_thinking_fp4_tep8_adp_2k1k]
   # qwen3.5-397b-a17b-fp4 aggregated
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_tep8_1k1k]
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_dep4_1k1k] TIMEOUT (90)
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_tp2_mtp3_1k1k]
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_dep8_mtp3_1k1k] TIMEOUT (90)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_tp4_8k1k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_dep8_8k1k] TIMEOUT (90)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_tep4_mtp3_8k1k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-qwen3_5_397b_fp4_blackwell-qwen3_5_397b_fp4_dep8_mtp3_8k1k] TIMEOUT (90)
   # ctx_only tests (disagg config)
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-b200_deepseek-r1-fp4_1k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-b200_deepseek-r1-fp4_1k1k_con2048_ctx1_dep4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)
-  # - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-b200_deepseek-r1-fp4_1k1k_con256_ctx1_dep4_gen1_dep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-b200_deepseek-r1-fp4_8k1k_con1536_ctx1_dep4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-b200_deepseek-r1-fp4_8k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
   # - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-b200_deepseek-r1-fp4_8k1k_con256_ctx1_dep4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)

tests/integration/test_lists/test-db/l0_b200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu8.yml

@@ -30,14 +30,8 @@ l0_b200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node1_gpu8:
       stage: post_merge
       backend: pytorch
   tests:
-  - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-b200_deepseek-r1-fp4_1k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
-  - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-b200_deepseek-r1-fp4_1k1k_con2048_ctx1_dep4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)
-  - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-b200_deepseek-r1-fp4_1k1k_con256_ctx1_dep4_gen1_dep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-b200_deepseek-r1-fp4_8k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-b200_deepseek-r1-fp4_8k1k_con256_ctx1_dep4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)
-  # - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-b200_deepseek-r1-fp4_1k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
-  # - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-b200_deepseek-r1-fp4_1k1k_con2048_ctx1_dep4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)
-  # - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-b200_deepseek-r1-fp4_1k1k_con256_ctx1_dep4_gen1_dep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
   # - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-b200_deepseek-r1-fp4_8k1k_con1536_ctx1_dep4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)
   # - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-b200_deepseek-r1-fp4_8k1k_con1_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
   # - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-b200_deepseek-r1-fp4_8k1k_con256_ctx1_dep4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)

tests/integration/test_lists/test-db/l0_b200_multi_nodes_perf_sanity_node2_gpu16.yml

@@ -17,6 +17,5 @@ l0_b200_multi_nodes_perf_sanity_node2_gpu16:
       orchestrator: mpi
   tests:
   # deepseek-r1-fp4-v2 aggregated 2-nodes
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_2_nodes_blackwell-r1_fp4_v2_dep16_mtp1_1k1k] TIMEOUT (90)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_2_nodes_blackwell-r1_fp4_v2_dep16_mtp1_8k1k] TIMEOUT (90)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_r1_fp4_v2_2_nodes_blackwell-r1_fp4_v2_tep16_mtp3] TIMEOUT (90)