[Infra] - Add timeout setting for long tests found in post-merge (NVIDIA#5501)

Signed-off-by: qqiao <[email protected]>

Author: EmmaQiaoCh

jenkins/L0_Test.groovy

@@ -184,7 +184,7 @@ def executeLLMTestOnSlurm(pipeline, platform, testList, config=VANILLA_CONFIG, p
             sh """
                 ls -all ${stageName}/
                 if ! grep -q '<testcase' ${stageName}/results.xml; then
-                    rm ${stageName}/results.xml
+                    rm ${stageName}/results.xml || true
                 fi
             """
             def llmPath = sh (script: "realpath .", returnStdout: true).trim()

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

@@ -49,4 +49,4 @@ l0_dgx_b200:
   - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_attention_dp_overlap_cuda_graph[DeepSeek-V3-Lite-fp8]
   - disaggregated/test_disaggregated.py::test_disaggregated_deepseek_v3_lite_fp8_overlap_cuda_graph[DeepSeek-V3-Lite-fp8]
   - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[4gpu_latency_moe_trtllm]
-  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[4gpu_latency_moe_cutlass]
+  - accuracy/test_llm_api_pytorch.py::TestQwen3_30B_A3B::test_nvfp4[4gpu_latency_moe_cutlass] TIMEOUT (90)

tests/integration/test_lists/test-db/l0_dgx_h200.yml

@@ -109,7 +109,7 @@ l0_dgx_h200:
   - accuracy/test_cli_flow.py::TestLlama2_7B::test_tp2cp2
   - accuracy/test_cli_flow.py::TestLlama2_7B::test_fp8_2gpus[pp2] # 2 mins
   - accuracy/test_cli_flow.py::TestLlama3_1_8B::test_fp8_rowwise_tp4[enable_gemm_allreduce_plugin]
-  - accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp8_tp2pp2
+  - accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp8_tp2pp2 TIMEOUT (90)
   - accuracy/test_cli_flow.py::TestMixtral8x7B::test_fp8_tp2pp2_manage_weights
   - accuracy/test_cli_flow.py::TestQwen2_57B_A14B::test_tp4
   - accuracy/test_llm_api.py::TestQwen2_7BInstruct::test_tp2

tests/integration/test_lists/test-db/l0_h100.yml

@@ -246,7 +246,7 @@ l0_h100:
   - accuracy/test_cli_flow.py::TestGpt2::test_beam_search # 1 min
   - accuracy/test_cli_flow.py::TestGpt2::test_weight_streaming_ootb # 1.5 mins
   - accuracy/test_cli_flow.py::TestGpt2::test_cuda_graph # 1 min
-  - accuracy/test_cli_flow.py::TestGpt2::test_context_fmha_disabled # 1 min
+  - accuracy/test_cli_flow.py::TestGpt2::test_context_fmha_disabled TIMEOUT (60)
   - accuracy/test_cli_flow.py::TestGptNext::test_auto_dtype # 1.5 mins
   - accuracy/test_cli_flow.py::TestSantacoder::test_auto_dtype # 1.5 mins
   - accuracy/test_cli_flow.py::TestMamba130M::test_auto_dtype # 1 min