Print memory info

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

Author: HuiGao-NV

tests/integration/defs/accuracy/test_llm_api_pytorch.py

@@ -28,10 +28,10 @@
                                  SamplingParams, TorchCompileConfig)
 from tensorrt_llm.quantization import QuantAlgo
 
-from ..conftest import (get_device_count, get_device_memory, print_device_memory, llm_models_root,
-                        parametrize_with_ids, skip_no_hopper,
-                        skip_post_blackwell, skip_pre_ada, skip_pre_blackwell,
-                        skip_pre_hopper, skip_ray)
+from ..conftest import (get_device_count, get_device_memory, llm_models_root,
+                        parametrize_with_ids, print_device_memory,
+                        skip_no_hopper, skip_post_blackwell, skip_pre_ada,
+                        skip_pre_blackwell, skip_pre_hopper, skip_ray)
 from .accuracy_core import (GSM8K, MMLU, CnnDailymail, GPQADiamond,
                             JsonModeEval, LlmapiAccuracyTestHarness,
                             LongBenchV2)

tests/integration/defs/conftest.py

@@ -1996,12 +1996,14 @@ def get_device_memory_str():
     with tempfile.TemporaryDirectory() as temp_dirname:
         suffix = ".exe" if is_windows() else ""
         cmd = " ".join([
-                "nvidia-smi" + suffix, "--query-gpu=memory.total,memory.reserved,memory.used,memory.free",
-                "--format=csv,noheader"
-            ])
+            "nvidia-smi" + suffix,
+            "--query-gpu=memory.total,memory.reserved,memory.used,memory.free",
+            "--format=csv,noheader"
+        ])
         output = check_output(cmd, shell=True, cwd=temp_dirname)
         return output.strip()
 
+
 def get_device_memory():
     "get gpu memory"
     memory = 0
@@ -2038,6 +2040,7 @@ def print_device_memory():
     memory_str = get_device_memory_str()
     print(f"Device Memory:\ntotal:   reserved:   used:   free:  \n{memory_str}")
 
+
 def pytest_addoption(parser):
     parser.addoption(
         "--test-list",

tests/integration/test_lists/test-db/l0_gb200_multi_nodes.yml

@@ -35,7 +35,7 @@ l0_gb200_multi_nodes:
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[throughput_tp8] TIMEOUT (180)
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency_trtllmgen] TIMEOUT (180)
   - accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency_adp_lmtp] TIMEOUT (180)
-  - accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency_trtllmgen_adp_lmtp] TIMEOUT (180)
+  - accuracy/test_llm_api_pytorch.py::TestDeepSeekR1::test_nvfp4_multi_gpus[latency_trtllmgen_adp_lmtp] TIMEOUT (180) ISOLATION
   - accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4[latency_moe_cutlass] TIMEOUT (90)
   - accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4[latency_moe_trtllm] TIMEOUT (90)
   - accuracy/test_llm_api_pytorch.py::TestQwen3_235B_A22B::test_nvfp4[latency_moe_trtllm_attention_dp] TIMEOUT (90)