Skip to content

FAIL : provider_options_utils.h:146 Parse Unknown provider option: "gpu_id". #126

Description

@12kv

请提供下述完整信息以便快速定位问题
(Please provide the following information to quickly locate the problem)

  • 系统环境/System Environment
Package                  Version
------------------------ -----------
aiohappyeyeballs         2.6.1
aiohttp                  3.11.16
aiosignal                1.4.0
alibabacloud_credentials 0.3.6
alibabacloud-tea         0.4.3
aliyun-python-sdk-core   2.16.0
aliyun-python-sdk-kms    2.16.5
annotated-types          0.7.0
antlr4-python3-runtime   4.9.3
anyio                    3.7.1
attrs                    25.3.0
beautifulsoup4           4.13.4
bs4                      0.0.2
certifi                  2025.8.3
cffi                     1.17.1
charset-normalizer       3.4.2
click                    8.2.1
coloredlogs              15.0.1
colorlog                 6.9.0
crcmod                   1.7
cryptography             45.0.5
decorator                5.2.1
et_xmlfile               2.0.0
fastapi                  0.109.0
flatbuffers              25.2.10
frozenlist               1.7.0
gunicorn                 23.0.0
h11                      0.16.0
html2excel               0.0.6
html5lib                 1.1
httpcore                 1.0.9
httpx                    0.28.1
humanfriendly            10.0
idna                     3.10
jmespath                 0.10.0
mpmath                   1.3.0
multidict                6.6.3
networkx                 3.5
numpy                    2.2.6
nvidia-cublas-cu12       12.9.0.13
nvidia-cuda-cccl-cu12    12.9.27
nvidia-cuda-cupti-cu12   12.9.19
nvidia-cuda-nvrtc-cu12   12.9.41
nvidia-cuda-runtime-cu12 12.9.37
nvidia-cudnn-cu12        9.9.0.52
nvidia-cufft-cu12        11.4.0.6
nvidia-cufile-cu12       1.14.0.30
nvidia-curand-cu12       10.3.10.19
nvidia-cusolver-cu12     11.7.4.40
nvidia-cusparse-cu12     12.5.9.5
nvidia-cusparselt-cu12   0.7.1
nvidia-nccl-cu12         2.26.5
nvidia-nvjitlink-cu12    12.9.41
nvidia-nvtx-cu12         12.9.19
omegaconf                2.3.0
onnxruntime-gpu          1.22.0
opencv-python            4.12.0.88
openpyxl                 3.1.5
opt-einsum               3.3.0
oss2                     2.19.1
packaging                25.0
paddlepaddle-gpu         3.1.0
pillow                   11.3.0
pip                      25.1
propcache                0.3.2
protobuf                 6.31.1
pyclipper                1.3.0.post6
pycparser                2.22
pycryptodome             3.23.0
pydantic                 2.5.3
pydantic_core            2.14.6
pydantic-settings        2.1.0
python-dotenv            1.1.1
PyYAML                   6.0.2
rapid-table              2.0.3
rapidocr                 3.3.0
requests                 2.32.4
setuptools               78.1.1
shapely                  2.1.1
six                      1.17.0
sniffio                  1.3.1
soupsieve                2.7
starlette                0.35.1
sympy                    1.14.0
tqdm                     4.67.1
typing_extensions        4.14.1
urllib3                  2.5.0
uvicorn                  0.27.0
webencodings             0.5.1
wheel                    0.45.1
yarl                     1.20.1
  • 完整报错/Complete Error Message
[INFO] 2025-08-04 20:17:12,005 [RapidTable] download_file.py:56: File exists and is valid: /root/miniconda3/envs/ocr_table/lib/python3.11/site-packages/rapid_table/models/slanet-plus.onnx
[INFO] 2025-08-04 20:17:12,009 [RapidTable] base.py:53: Using engine_name: onnxruntime
[INFO] 2025-08-04 20:17:12,009 [RapidTable] main.py:35: Using /root/miniconda3/envs/ocr_table/lib/python3.11/site-packages/rapid_table/models/slanet-plus.onnx
*************** EP Error ***************
EP Error /onnxruntime_src/onnxruntime/core/providers/cuda/cuda_execution_provider_info.cc:60 static onnxruntime::CUDAExecutionProviderInfo onnxruntime::CUDAExecutionProviderInfo::FromProviderOptions(const onnxruntime::ProviderOptions&) [ONNXRuntimeError] : 1 : FAIL : provider_options_utils.h:146 Parse Unknown provider option: "gpu_id".
 when using [('CUDAExecutionProvider', {'gpu_id': 0, 'arena_extend_strategy': 'kNextPowerOfTwo', 'cudnn_conv_algo_search': 'EXHAUSTIVE', 'do_copy_in_default_stream': True, 'device_id': 0}), ('CPUExecutionProvider', {'arena_extend_strategy': 'kSameAsRequested'})]
Falling back to ['CPUExecutionProvider'] and retrying.
****************************************
[WARNING] 2025-08-04 20:17:12,069 [RapidTable] provider_config.py:83: CUDAExecutionProvider is available, but the inference part is automatically shifted to be executed under CPUExecutionProvider.
[WARNING] 2025-08-04 20:17:12,069 [RapidTable] provider_config.py:86: The available lists are ['CPUExecutionProvider']
  • 可能的解决方案/Possible solutions:

update onnxruntime.cuda_ep_cfg.gpu_id to device_id in engine_cfg.yaml

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions