Auto trigger multi-gpu CI

Signed-off-by: Tailing Yuan <yuantailing@gmail.com>

Author: yuantailing

jenkins/L0_MergeRequest.groovy

@@ -627,9 +627,16 @@ def getAutoTriggerTagList(pipeline, testFilter, globalVars) {
         return autoTriggerTagList
     }
     def specialFileToTagMap = [
-        "tensorrt_llm/_torch/models/modeling_deepseekv3.py": ["-DeepSeek-"],
         "cpp/kernels/fmha_v2/": ["-FMHA-"],
+        "examples/layer_wise_benchmarks/config_ctx.yaml": ["DGX_B200-4_GPUs-PyTorch-Post-Merge"],
+        "examples/layer_wise_benchmarks/config_gen.yaml": ["DGX_B200-4_GPUs-PyTorch-Post-Merge"],
+        "examples/layer_wise_benchmarks/mpi_launch.sh": ["DGX_B200-4_GPUs-PyTorch-Post-Merge"],
+        "examples/layer_wise_benchmarks/run_single.py": ["DGX_B200-4_GPUs-PyTorch-Post-Merge"],
+        "examples/layer_wise_benchmarks/run_single.sh": ["DGX_B200-4_GPUs-PyTorch-Post-Merge"],
+        "tensorrt_llm/_torch/models/modeling_deepseekv3.py": ["-DeepSeek-"],
         "tensorrt_llm/_torch/models/modeling_gpt_oss.py": ["-GptOss-"],
+        "tensorrt_llm/tools/layer_wise_benchmarks/": ["DGX_B200-4_GPUs-PyTorch-Post-Merge"],
+        "tests/unittest/tools/test_layer_wise_benchmarks.py": ["DGX_B200-4_GPUs-PyTorch-Post-Merge"],
     ]
     for (file in changedFileList) {
         for (String key : specialFileToTagMap.keySet()) {

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

@@ -18,8 +18,6 @@ l0_dgx_b200:
   - unittest/_torch/multi_gpu_modeling -k "deepseek"
   - unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[DeepEPLowLatency]
   - unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[MNNVL]
-  - unittest/tools/test_layer_wise_benchmarks.py::test_deepseek_r1_ctx_tep
-  - unittest/tools/test_layer_wise_benchmarks.py::test_deepseek_r1_gen_scaled_from_16_dep
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[pp4-attn_backend=TRTLLM-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[tp4-fp8kv=True-attn_backend=TRTLLM-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[pp4-fp8kv=True-attn_backend=TRTLLM-torch_compile=False]
@@ -144,6 +142,8 @@ l0_dgx_b200:
       orchestrator: mpi
   tests:
   - unittest/_torch/modules/test_fused_moe.py::test_fused_moe_alltoall_fp4[DeepEP]
+  - unittest/tools/test_layer_wise_benchmarks.py::test_deepseek_r1_ctx_tep
+  - unittest/tools/test_layer_wise_benchmarks.py::test_deepseek_r1_gen_scaled_from_16_dep
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_bfloat16_4gpus[tp4-attn_backend=FLASHINFER-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[tp4-fp8kv=False-attn_backend=FLASHINFER-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestLlama3_1_8BInstruct::test_fp8_4gpus[pp4-fp8kv=False-attn_backend=TRTLLM-torch_compile=False]