[None][ci] Improve CI resource utilization

Signed-off-by: Yanchao Lu <[email protected]>

Author: chzblych

jenkins/L0_MergeRequest.groovy

@@ -1242,7 +1242,8 @@ def launchStages(pipeline, reuseBuild, testFilter, enableFailFast, globalVars)
     def dockerBuildJob = [
         "Build-Docker-Images": {
             script {
-                stage("[Build-Docker-Images] Remote Run") {
+                def testStageName = "[Build-Docker-Images] ${env.localJobCredentials ? "Remote Run" : "Run"}"
+                stage(testStageName) {
                     def branch = env.gitlabBranch ? env.gitlabBranch : "main"
                     if (globalVars[GITHUB_PR_API_URL]) {
                         branch = "github-pr-" + globalVars[GITHUB_PR_API_URL].split('/').last()

jenkins/L0_Test.groovy

@@ -2939,12 +2939,12 @@ def launchTestJobs(pipeline, testFilter)
         "DGX_H100-4_GPUs-PyTorch-GptOss-1": ["dgx-h100-x4-oci", "l0_dgx_h100", 1, 1, 4],
         "DGX_H100-4_GPUs-PyTorch-Others-1": ["dgx-h100-x4-oci", "l0_dgx_h100", 1, 1, 4],
         "B300-PyTorch-1": ["b300-single", "l0_b300", 1, 1],
-        "DGX_B200-4_GPUs-PyTorch-1": ["b200-x4", "l0_dgx_b200", 1, 2, 4],
-        "DGX_B200-4_GPUs-PyTorch-2": ["b200-x4", "l0_dgx_b200", 2, 2, 4],
+        "DGX_B200-4_GPUs-PyTorch-1": ["b200-x4-lbd", "l0_dgx_b200", 1, 2, 4, 1, true],
+        "DGX_B200-4_GPUs-PyTorch-2": ["b200-x4-lbd", "l0_dgx_b200", 2, 2, 4, 1, true],
         "DGX_B200-4_GPUs-PyTorch-Ray-1": ["b200-x4-lbd", "l0_dgx_b200", 1, 1, 4, 1, true],
         "DGX_B200-8_GPUs-PyTorch-1": ["b200-x8-lbd", "l0_dgx_b200", 1, 1, 8, 1, true],
-        "DGX_B200-4_GPUs-PyTorch-Post-Merge-1": ["b200-trtllm", "l0_dgx_b200", 1, 2, 4, 1, true],
-        "DGX_B200-4_GPUs-PyTorch-Post-Merge-2": ["b200-trtllm", "l0_dgx_b200", 2, 2, 4, 1, true],
+        "DGX_B200-4_GPUs-PyTorch-Post-Merge-1": ["b200-x4-lbd", "l0_dgx_b200", 1, 2, 4, 1, true],
+        "DGX_B200-4_GPUs-PyTorch-Post-Merge-2": ["b200-x4-lbd", "l0_dgx_b200", 2, 2, 4, 1, true],
         "DGX_B300-4_GPUs-PyTorch-Post-Merge-1": ["b300-x4", "l0_dgx_b300", 1, 2, 4],
         "DGX_B300-4_GPUs-PyTorch-Post-Merge-2": ["b300-x4", "l0_dgx_b300", 2, 2, 4],
         // Perf sanity post merge test

tests/integration/test_lists/test-db/l0_dgx_b200.yml

@@ -24,7 +24,7 @@ l0_dgx_b200:
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[tep4_latency_moe_trtllm-torch_compile=True]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_trtllm-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=False]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=True] ISOLATION
+  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[dep4_latency_moe_cutlass-torch_compile=True]
   - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_ucx[DeepSeek-V3-Lite-fp8]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[tp4-trtllm-auto]
   - accuracy/test_llm_api_pytorch.py::TestGPTOSS::test_w4_4gpus[ep4-cutlass-auto]