Make generate engines failing for nvidia implementation with v5.0 code #431
Description
mlcr run-mlperf,inference,_find-performance,_full,_r5.0 --model=resnet50 --implementation=nvidia --framework=tensorrt --category=edge --scenario=Offline --execution_mode=test --device=cuda --docker --quiet --test_query_count=5000 --docker_cache=no --docker_rebuild
Docker now builds fine and during the run getting the below ERROR
make generate_engines RUN_ARGS=' --benchmarks=resnet50 --scenarios=offline --test_mode=PerformanceOnly --offline_expected_qps=1 --gpu_batch_size=64 --use_deque_limit --num_warmups=10 --no_audit_verify '
[2025-05-19 11:40:13,398 main.py:237 INFO] Detected system ID: spr
Traceback (most recent call last):
File "<frozen runpy>", line 198, in _run_module_as_main
File "<frozen runpy>", line 88, in _run_code
File "/home/ubuntu/MLC/repos/local/cache/get-git-repo_mlperf-inferenc_3a9194ca/repo/closed/NVIDIA/code/main.py", line 239, in <module>
main(main_args, DETECTED_SYSTEM)
File "/home/ubuntu/MLC/repos/local/cache/get-git-repo_mlperf-inferenc_3a9194ca/repo/closed/NVIDIA/code/main.py", line 103, in main
load_config_fn(benchmarks, scenarios)
File "/home/ubuntu/MLC/repos/local/cache/get-git-repo_mlperf-inferenc_3a9194ca/repo/closed/NVIDIA/code/main.py", line 53, in populate_config_registry
ConfigRegistry.load_configs(benchmark, scenario)
File "/home/ubuntu/MLC/repos/local/cache/get-git-repo_mlperf-inferenc_3a9194ca/repo/closed/NVIDIA/configs/configuration.py", line 119, in load_configs
importlib.import_module(f"{base_module}.custom")
File "/usr/lib/python3.12/importlib/__init__.py", line 90, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "<frozen importlib._bootstrap>", line 1387, in _gcd_import
File "<frozen importlib._bootstrap>", line 1360, in _find_and_load
File "<frozen importlib._bootstrap>", line 1331, in _find_and_load_unlocked
File "<frozen importlib._bootstrap>", line 935, in _load_unlocked
File "<frozen importlib._bootstrap_external>", line 995, in exec_module
File "<frozen importlib._bootstrap>", line 488, in _call_with_frames_removed
File "/home/ubuntu/MLC/repos/local/cache/get-git-repo_mlperf-inferenc_3a9194ca/repo/closed/NVIDIA/configs/resnet50/Offline/custom.py", line 8, in <module>
class SPR(OfflineGPUBaseConfig):
File "/home/ubuntu/MLC/repos/local/cache/get-git-repo_mlperf-inferenc_3a9194ca/repo/closed/NVIDIA/configs/resnet50/Offline/custom.py", line 15, in SPR
gpu_batch_size: Dict = Dict(os.environ.get('gpu_batch_size', {}))
^^^^
NameError: name 'Dict' is not defined. Did you mean: 'dict'?
make: *** [Makefile:37: generate_engines] Error 1
Traceback (most recent call last):
File "/home/ubuntu/.local/bin/mlcr", line 8, in <module>
sys.exit(mlcr())
^^^^^^