[TRTLLM-6537][infra] extend multi-gpu tests related file list (NVIDIA#6139)

Signed-off-by: Lizhi Zhou <[email protected]>

Author: reasonsolo

jenkins/L0_MergeRequest.groovy

@@ -550,68 +550,69 @@ def getMultiGpuFileChanged(pipeline, testFilter, globalVars)
     }
 
     def relatedFileList = [
+        "cpp/include/tensorrt_llm/batch_manager/",
+        "cpp/include/tensorrt_llm/executor/",
         "cpp/include/tensorrt_llm/runtime/gptJsonConfig.h",
-        "cpp/include/tensorrt_llm/runtime/worldConfig.h",
         "cpp/include/tensorrt_llm/runtime/utils/mpiUtils.h",
         "cpp/include/tensorrt_llm/runtime/utils/multiDeviceUtils.h",
-        "cpp/tensorrt_llm/runtime/utils/mpiUtils.cpp",
-        "cpp/tests/runtime/mpiUtilsTest.cpp",
-        "cpp/tensorrt_llm/batch_manager/trtGptModelFactory.h",
-        "cpp/tensorrt_llm/runtime/worldConfig.cpp",
-        "cpp/tensorrt_llm/runtime/ncclCommunicator.cpp",
-        "cpp/tensorrt_llm/runtime/workerPool.h",
-        "cpp/tensorrt_llm/executor_worker/executorWorker.cpp",
-        "cpp/tensorrt_llm/runtime/ipcUtils.cpp",
-        "cpp/tensorrt_llm/executor/executor.cpp",
-        "cpp/tensorrt_llm/executor/executorImpl.cpp",
-        "cpp/tensorrt_llm/executor/executorImpl.h",
-        "cpp/tensorrt_llm/runtime/ncclCommunicator.cpp",
+        "cpp/include/tensorrt_llm/runtime/worldConfig.h",
+        "cpp/tensorrt_llm/batch_manager/",
+        "cpp/tensorrt_llm/executor/",
+        "cpp/tensorrt_llm/executor_worker/",
         "cpp/tensorrt_llm/kernels/communicationKernels/",
-        "cpp/tensorrt_llm/thop/allreduceOp.cpp",
-        "cpp/tensorrt_llm/thop/allgatherOp.cpp",
-        "cpp/tensorrt_llm/thop/reducescatterOp.cpp",
-        "cpp/tensorrt_llm/kernels/customAllReduceKernels.h",
         "cpp/tensorrt_llm/kernels/customAllReduceKernels.cu",
-        "cpp/tensorrt_llm/kernels/gptKernels.h",
+        "cpp/tensorrt_llm/kernels/customAllReduceKernels.h",
         "cpp/tensorrt_llm/kernels/gptKernels.cu",
-        "cpp/tensorrt_llm/kernels/unfusedAttentionKernels.h",
+        "cpp/tensorrt_llm/kernels/gptKernels.h",
+        "cpp/tensorrt_llm/kernels/moe",
         "cpp/tensorrt_llm/kernels/unfusedAttentionKernels.cu",
+        "cpp/tensorrt_llm/kernels/unfusedAttentionKernels.h",
         "cpp/tensorrt_llm/kernels/userbuffers/",
-        "cpp/tensorrt_llm/kernels/moe",
-        "cpp/tensorrt_llm/pybind/",
-        "cpp/tests/kernels/allReduce/",
-        "cpp/tensorrt_llm/plugins/cpSplitPlugin/cpSplitPlugin.h",
         "cpp/tensorrt_llm/plugins/cpSplitPlugin/cpSplitPlugin.cpp",
-        "cpp/tensorrt_llm/plugins/gptAttentionCommon/gptAttentionCommon.h",
+        "cpp/tensorrt_llm/plugins/cpSplitPlugin/cpSplitPlugin.h",
         "cpp/tensorrt_llm/plugins/gptAttentionCommon/gptAttentionCommon.cpp",
-        "cpp/tensorrt_llm/plugins/gptAttentionPlugin/gptAttentionPlugin.h",
+        "cpp/tensorrt_llm/plugins/gptAttentionCommon/gptAttentionCommon.h",
         "cpp/tensorrt_llm/plugins/gptAttentionPlugin/gptAttentionPlugin.cpp",
-        "cpp/tests/runtime/mpiUtilsTest.cpp",
+        "cpp/tensorrt_llm/plugins/gptAttentionPlugin/gptAttentionPlugin.h",
         "cpp/tensorrt_llm/plugins/ncclPlugin/",
-        "tensorrt_llm/functional.py",
-        "tensorrt_llm/mapping.py",
-        "tensorrt_llm/llmapi/",
-        "tensorrt_llm/executor/",
+        "cpp/tensorrt_llm/pybind/",
+        "cpp/tensorrt_llm/runtime/ipcUtils.cpp",
+        "cpp/tensorrt_llm/runtime/ncclCommunicator.cpp",
+        "cpp/tensorrt_llm/runtime/utils/mpiUtils.cpp",
+        "cpp/tensorrt_llm/runtime/workerPool.h",
+        "cpp/tensorrt_llm/runtime/worldConfig.cpp",
+        "cpp/tensorrt_llm/thop/allgatherOp.cpp",
+        "cpp/tensorrt_llm/thop/allreduceOp.cpp",
+        "cpp/tensorrt_llm/thop/reducescatterOp.cpp",
+        "cpp/tests/executor/",
+        "cpp/tests/kernels/allReduce/",
+        "cpp/tests/runtime/mpiUtilsTest.cpp",
+        "jenkins/L0_Test.groovy",
         "tensorrt_llm/_ipc_utils.py",
-        "tensorrt_llm/parameter.py",
-        "tensorrt_llm/models/llama/",
         "tensorrt_llm/_torch/compilation/patterns/ar_residual_norm.py",
         "tensorrt_llm/_torch/compilation/patterns/ub_allreduce.py",
         "tensorrt_llm/_torch/custom_ops/userbuffers_custom_ops.py",
-        "tensorrt_llm/_torch/pyexecutor/model_engine.py",
-        "tensorrt_llm/_torch/pyexecutor/py_executor.py",
-        "tensorrt_llm/_torch/pyexecutor/_util.py",
         "tensorrt_llm/_torch/models/modeling_llama.py",
         "tensorrt_llm/_torch/modules/fused_moe/",
+        "tensorrt_llm/_torch/pyexecutor/_util.py",
+        "tensorrt_llm/_torch/pyexecutor/model_engine.py",
+        "tensorrt_llm/_torch/pyexecutor/py_executor.py",
+        "tensorrt_llm/executor/",
+        "tensorrt_llm/functional.py",
+        "tensorrt_llm/llmapi/",
+        "tensorrt_llm/mapping.py",
+        "tensorrt_llm/models/llama/",
+        "tensorrt_llm/parameter.py",
+        "tensorrt_llm/serve/",
         "tests/integration/defs/cpp/test_multi_gpu.py",
         "tests/integration/test_lists/test-db/l0_dgx_h100.yml",
         "tests/integration/test_lists/test-db/l0_dgx_h200.yml",
+        "tests/unittest/_torch/auto_deploy/unit/multigpu",
         "tests/unittest/_torch/multi_gpu/",
         "tests/unittest/_torch/multi_gpu_modeling/",
-        "tests/unittest/_torch/auto_deploy/unit/multigpu",
+        "tests/unittest/disaggregated/",
         "tests/unittest/llmapi/test_llm_multi_gpu.py",
         "tests/unittest/llmapi/test_llm_multi_gpu_pytorch.py",
-        "jenkins/L0_Test.groovy",
     ]
 
     def changedFileList = getMergeRequestChangedFileList(pipeline, globalVars)