[None][test] Update K2.5 andGLM-5 into CI Perf Test (#14960)

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

Author: chenfeiz0326

jenkins/L0_MergeRequest.groovy

@@ -979,10 +979,12 @@ def getMultiGpuFileChanged(pipeline, testFilter, globalVars)
         "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_ctx1_node1_gpu4_gen1_node8_gpu32.yml",
         "tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_node2_gpu8.yml",
         "tests/integration/test_lists/test-db/l0_rtx_pro_6000.yml",
         "tests/integration/test_lists/test-db/l0_verl.yml",

jenkins/L0_Test.groovy

@@ -4128,10 +4128,11 @@ 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, 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],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 1, 5, 8, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 2, 5, 8, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-3": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 3, 5, 8, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-4": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 4, 5, 8, 1, true],
+        "DGX_B200-8_GPUs-PyTorch-PerfSanity-Post-Merge-5": ["auto:dgx-b200-flex", "l0_b200_multi_gpus_perf_sanity", 5, 5, 8, 1, true],
     ]
     // B200 PerfSanity post-merge disaggregated
     // 2 Nodes
@@ -4198,15 +4199,18 @@ def launchTestJobs(pipeline, testFilter)
         "GB200-4_GPUs-PyTorch-PerfSanity-1": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 1, 2, 4],
         "GB200-4_GPUs-PyTorch-PerfSanity-2": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 2, 2, 4],
         // PerfSanity post-merge tests
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 1, 7, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 2, 7, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-3": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 3, 7, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-4": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 4, 7, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-5": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 5, 7, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-6": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 6, 7, 4],
-        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-7": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 7, 7, 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],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-1": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 1, 9, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-2": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 2, 9, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-3": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 3, 9, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-4": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 4, 9, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-5": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 5, 9, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-6": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 6, 9, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-7": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 7, 9, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-8": ["auto:gb200-x4", "l0_gb200_multi_gpus_perf_sanity", 8, 9, 4],
+        "GB200-4_GPUs-PyTorch-PerfSanity-Post-Merge-9": ["auto:gb200-x4", "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],
     ]
     fullSet += SBSASlurmTestConfigs.keySet()
 
@@ -4225,7 +4229,7 @@ def launchTestJobs(pipeline, testFilter)
         "GB200-8_GPUs-2_Nodes-PyTorch-PerfSanity-Node2-GPU8-Post-Merge",
         "auto:gb200-flex",
         "l0_gb200_multi_nodes_perf_sanity_node2_gpu8",
-        7,
+        9,
         8,
         2
     )
@@ -4312,7 +4316,7 @@ 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",
-        11,
+        12,
         36,
         9
     )
@@ -4341,7 +4345,7 @@ def launchTestJobs(pipeline, testFilter)
         "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",
-        4,
+        3,
         8,
         2
     )
@@ -4350,7 +4354,7 @@ 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,
+        5,
         12,
         3
     )
@@ -4368,7 +4372,35 @@ 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",
-        4,
+        2,
+        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
+    multiNodesSBSAConfigs += buildStageConfigs(
+        "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",
+        5,
+        12,
+        3
+    )
+    // 9 Nodes
+    multiNodesSBSAConfigs += buildStageConfigs(
+        "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,
         36,
         9
     )

tests/integration/test_lists/qa/llm_perf_multinode.txt

@@ -53,7 +53,7 @@ perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_1k1k_c
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-NIXL]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_1k1k_con4_ctx1_dep4_gen1_tep4_eplb0_mtp0_ccb-NIXL]
-perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-NIXL]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-NIXL]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-NIXL]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-UCX]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb200_kimi-k25-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL]
@@ -95,12 +95,22 @@ perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_deepseek-v32-fp4_8k1k_con1_c
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_deepseek-v32-fp4_8k1k_con4096_ctx1_dep4_gen1_dep32_eplb256_mtp0_ccb-NIXL]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_deepseek-v32-fp4_8k1k_con4096_ctx1_dep4_gen1_dep32_eplb256_mtp0_ccb-UCX]
 
+# GB300 GLM-5
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_glm-5-fp4_1k1k_con1_ctx1_dep2_gen1_tep4_eplb0_mtp3_ccb-NIXL]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_glm-5-fp4_1k1k_con4096_ctx1_dep2_gen1_dep8_eplb256_mtp1_ccb-NIXL]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_glm-5-fp4_1k1k_con4096_ctx1_dep2_gen1_dep8_eplb256_mtp1_ccb-UCX]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_glm-5-fp4_1k1k_con512_ctx1_dep2_gen1_dep32_eplb0_mtp3_ccb-NIXL]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_glm-5-fp4_8k1k_con1024_ctx1_dep2_gen1_dep8_eplb256_mtp1_ccb-NIXL]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_glm-5-fp4_8k1k_con1024_ctx1_dep2_gen1_dep8_eplb256_mtp1_ccb-UCX]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_glm-5-fp4_8k1k_con1_ctx1_dep2_gen1_tep8_eplb0_mtp3_ccb-NIXL]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_glm-5-fp4_8k1k_con512_ctx1_dep2_gen1_dep32_eplb0_mtp3_ccb-NIXL]
+
 # GB300 Kimi-K2.5-Thinking
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_1k1k_con2048_ctx1_dep4_gen1_dep32_eplb0_mtp0_ccb-NIXL]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-NIXL]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-UCX]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_1k1k_con4_ctx1_dep4_gen1_tep4_eplb0_mtp0_ccb-NIXL]
-perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-NIXL]
+perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-NIXL]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-NIXL]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-UCX]
 perf/test_perf_sanity.py::test_e2e[disagg-e2e-gb300_kimi-k25-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL]

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

@@ -29,6 +29,9 @@ l0_b200_multi_gpus_perf_sanity:
   # deepseek-v32-fp4
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_v32_fp4_blackwell-v32_fp4_tep8_mtp3_8k1k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_v32_fp4_blackwell-v32_fp4_dep8_mtp1_8k1k] TIMEOUT (90)
+  # glm-5-fp4
+  - 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]

tests/integration/test_lists/test-db/l0_gb200_multi_gpus_perf_sanity.yml

@@ -55,6 +55,9 @@ l0_gb200_multi_gpus_perf_sanity:
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_v32_fp4_grace_blackwell-v32_fp4_dep4_mtp1_1k1k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_v32_fp4_grace_blackwell-v32_fp4_tep4_mtp3_8k1k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-deepseek_v32_fp4_grace_blackwell-v32_fp4_dep4_mtp1_8k1k]
+  # glm-5-fp4
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-glm5_fp4_grace_blackwell-glm5_fp4_tep4_mtp3_1k1k]
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-glm5_fp4_grace_blackwell-glm5_fp4_dep4_mtp1_1k1k]
   # gpt-oss-120b-fp4
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-gpt_oss_120b_fp4_grace_blackwell-gpt_oss_fp4_tp2_1k8k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-gpt_oss_120b_fp4_grace_blackwell-gpt_oss_fp4_dep4_1k8k]
@@ -95,7 +98,7 @@ l0_gb200_multi_gpus_perf_sanity:
   # kimi-k25-thinking-fp4
   # - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb200_kimi-k25-thinking-fp4_1k1k_con2048_ctx1_dep4_gen1_dep32_eplb0_mtp0_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb200_kimi-k25-thinking-fp4_1k1k_con4_ctx1_dep4_gen1_tep4_eplb0_mtp0_ccb-NIXL] TIMEOUT (120)
-  # - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb200_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb200_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb200_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb200_kimi-k25-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
   # qwen3-235b-fp4

tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node8_gpu32.yml

@@ -23,6 +23,6 @@ l0_gb200_multi_nodes_perf_sanity_ctx1_node1_gpu4_gen1_node8_gpu32:
   - 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] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_deepseek-v32-fp4_8k1k_con4096_ctx1_dep4_gen1_dep32_eplb256_mtp0_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k25-thinking-fp4_1k1k_con2048_ctx1_dep4_gen1_dep32_eplb0_mtp0_ccb-NIXL] TIMEOUT (120)
-  # - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb200_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-v32-fp4_32k4k_con2048_ctx1_dep4_gen1_dep32_eplb288_mtp1_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[disagg_upload-e2e-gb200_deepseek-v32-fp4_8k1k_con4096_ctx1_dep4_gen1_dep32_eplb256_mtp0_ccb-NIXL] TIMEOUT (120)

tests/integration/test_lists/test-db/l0_gb200_multi_nodes_perf_sanity_node2_gpu8.yml

@@ -22,6 +22,9 @@ l0_gb200_multi_nodes_perf_sanity_node2_gpu8:
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-k25_thinking_fp4_2_nodes_grace_blackwell-k25_thinking_fp4_tep8_32k8k]
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-k25_thinking_fp4_2_nodes_grace_blackwell-k25_thinking_fp4_dep8_32k8k] TIMEOUT (90)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-dynamo_deepseek_v32_fp4_2_nodes_grace_blackwell-dsv32_fp4_dep8_trtllm_lpc_mnnvl_8k1k] TIMEOUT (120)
+  # glm-5-fp4
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-glm5_fp4_2_nodes_grace_blackwell-glm5_fp4_tep8_mtp3_8k1k] TIMEOUT (90)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-glm5_fp4_2_nodes_grace_blackwell-glm5_fp4_dep8_mtp1_8k1k] TIMEOUT (90)
   # ctx only tests (disagg config)
   # deepseek-r1-fp4
   - 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] TIMEOUT (120)

tests/integration/test_lists/test-db/l0_gb300_multi_gpus_perf_sanity.yml

@@ -21,8 +21,15 @@ l0_gb300_multi_gpus_perf_sanity:
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_deepseek-r1-fp4_128k8k_con256_ctx1_pp4_gen1_dep8_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)
   # kimi-k25-thinking-fp4
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_kimi-k25-thinking-fp4_1k1k_con4096_ctx1_dep4_gen1_dep8_eplb0_mtp0_ccb-NIXL] TIMEOUT (120)
+  # - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_kimi-k25-thinking-fp4_1k1k_con2048_ctx1_dep4_gen1_dep32_eplb0_mtp0_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_kimi-k25-thinking-fp4_1k1k_con4_ctx1_dep4_gen1_tep4_eplb0_mtp0_ccb-NIXL] TIMEOUT (120)
   - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_kimi-k25-thinking-fp4_8k1k_con4096_ctx1_dep4_gen1_dep16_eplb0_mtp0_ccb-NIXL] TIMEOUT (120)
-  # deepseek-v32-fp4
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_deepseek-v32-fp4_1k1k_con2048_ctx1_dep4_gen1_dep4_eplb0_mtp1_ccb-NIXL] TIMEOUT (120)
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_deepseek-v32-fp4_8k1k_con4096_ctx1_dep4_gen1_dep32_eplb256_mtp0_ccb-NIXL] TIMEOUT (120)
-  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_deepseek-v32-fp4_32k4k_con2048_ctx1_dep4_gen1_dep32_eplb288_mtp1_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_kimi-k25-thinking-fp4_8k1k_con1024_ctx1_dep4_gen1_dep32_eplb416_mtp3_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_kimi-k25-thinking-fp4_8k1k_con4_ctx1_dep4_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
+  # glm-5-fp4
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_glm-5-fp4_1k1k_con1_ctx1_dep2_gen1_tep4_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_glm-5-fp4_1k1k_con512_ctx1_dep2_gen1_dep32_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_glm-5-fp4_1k1k_con4096_ctx1_dep2_gen1_dep8_eplb256_mtp1_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_glm-5-fp4_8k1k_con1_ctx1_dep2_gen1_tep8_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_glm-5-fp4_8k1k_con512_ctx1_dep2_gen1_dep32_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)
+  - perf/test_perf_sanity.py::test_e2e[aggr_upload-ctx_only-gb300_glm-5-fp4_8k1k_con1024_ctx1_dep2_gen1_dep8_eplb256_mtp1_ccb-NIXL] TIMEOUT (120)

tests/integration/test_lists/test-db/l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu2_gen1_node1_gpu4.yml

@@ -0,0 +1,18 @@
+version: 0.0.1
+l0_gb300_multi_nodes_perf_sanity_ctx1_node1_gpu2_gen1_node1_gpu4:
+- condition:
+    ranges:
+      # 1 ctx worker with each 1 node and 2 GPUs
+      # 1 gen worker with each 1 node and 4 GPUs
+      system_gpu_count:
+        gte: 8
+        lte: 8
+    wildcards:
+      gpu:
+      - '*gb300*'
+    terms:
+      stage: post_merge
+      backend: pytorch
+  tests:
+  # glm-5-fp4
+  - perf/test_perf_sanity.py::test_e2e[disagg_upload-gen_only-gb300_glm-5-fp4_1k1k_con1_ctx1_dep2_gen1_tep4_eplb0_mtp3_ccb-NIXL] TIMEOUT (120)