[None][chore] Isolate several intermittent cases (NVIDIA#8408)

Signed-off-by: Hui Gao <[email protected]>

Author: HuiGao-NV

tests/integration/test_lists/test-db/l0_dgx_h100.yml

@@ -189,9 +189,9 @@ l0_dgx_h100:
   # ------------- CPP tests ---------------
   - cpp/test_multi_gpu.py::test_mpi_utils[90]
   - cpp/test_multi_gpu.py::test_fused_gemm_allreduce[4proc-90]
-  - cpp/test_multi_gpu.py::test_cache_transceiver[2proc-ucx_kvcache-90]
-  - cpp/test_multi_gpu.py::test_cache_transceiver[8proc-nixl_kvcache-90]
-  - cpp/test_multi_gpu.py::test_cache_transceiver[8proc-ucx_kvcache-90]
+  - cpp/test_multi_gpu.py::test_cache_transceiver[2proc-ucx_kvcache-90] ISOLATION
+  - cpp/test_multi_gpu.py::test_cache_transceiver[8proc-nixl_kvcache-90] ISOLATION
+  - cpp/test_multi_gpu.py::test_cache_transceiver[8proc-ucx_kvcache-90] ISOLATION
   - cpp/test_multi_gpu.py::test_user_buffer[2proc-90]
   - cpp/test_multi_gpu.py::test_enc_dec[t5-90]
   - cpp/test_multi_gpu.py::test_llama_executor[llama-orchestrator-90]

tests/integration/test_lists/test-db/l0_l40s.yml

@@ -65,7 +65,7 @@ l0_l40s:
   - llmapi/test_llm_examples.py::test_llmapi_example_multilora
   - llmapi/test_llm_examples.py::test_llmapi_example_guided_decoding
   - llmapi/test_llm_examples.py::test_llmapi_example_logits_processor
-  - examples/test_llm_api_with_mpi.py::test_llm_api_single_gpu_with_mpirun[TinyLlama-1.1B-Chat-v1.0]
+  - examples/test_llm_api_with_mpi.py::test_llm_api_single_gpu_with_mpirun[TinyLlama-1.1B-Chat-v1.0] ISOLATION
 - condition:
     ranges:
       system_gpu_count:

tests/integration/test_lists/test-db/l0_rtx_pro_6000.yml

@@ -70,7 +70,7 @@ l0_rtx_pro_6000:
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-tp4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-ep4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-ep4-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True]
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-ep4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False]
+  - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-ep4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=False] ISOLATION
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-ep4-fp8kv=True-attention_dp=True-cuda_graph=True-overlap_scheduler=True-torch_compile=True]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-tp2pp2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=False]
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekV3Lite::test_nvfp4_4gpus[moe_backend=CUTLASS-mtp_nextn=0-tp2pp2-fp8kv=False-attention_dp=False-cuda_graph=False-overlap_scheduler=False-torch_compile=True]

tests/integration/test_lists/test-db/l0_sanity_check.yml

@@ -31,6 +31,6 @@ l0_sanity_check:
       - llmapi/test_llm_examples.py::test_llmapi_sampling
       - llmapi/test_llm_examples.py::test_llmapi_runtime
       - llmapi/test_llm_examples.py::test_llmapi_tensorrt_engine
-      - examples/test_llm_api_with_mpi.py::test_llm_api_single_gpu_with_mpirun[TinyLlama-1.1B-Chat-v1.0]
+      - examples/test_llm_api_with_mpi.py::test_llm_api_single_gpu_with_mpirun[TinyLlama-1.1B-Chat-v1.0] ISOLATION
       - unittest/others/test_kv_cache_transceiver.py::test_kv_cache_transceiver_single_process[NIXL-mha-ctx_fp16_gen_fp16]
       - unittest/others/test_kv_cache_transceiver.py::test_kv_cache_transceiver_single_process[UCX-mha-ctx_fp16_gen_fp16]