RTX 5090 cannot be used for GPU acceleration

[zhenglipeng]

问题描述 / Problem Description

Failed to enable GPU acceleration

运行环境 / Runtime Environment

python
cuda 12.9
RTX 5090
Package Version

---

aistudio-sdk 0.3.8
annotated-doc 0.0.4
annotated-types 0.7.0
antlr4-python3-runtime 4.9.3
anyio 4.12.1
astor 0.8.1
bce-python-sdk 0.9.71
blinker 1.9.0
certifi 2026.1.4
chardet 7.4.3
charset-normalizer 3.4.7
click 8.3.3
colorama 0.4.6
colorlog 6.10.1
contourpy 1.3.3
crc32c 2.8
cycler 0.12.1
decorator 5.2.1
distro 1.9.0
easyocr 1.7.2
et_xmlfile 2.0.0
filelock 3.29.0
Flask 3.1.2
flatbuffers 25.12.19
fonttools 4.63.0
fsspec 2026.4.0
future 1.0.0
h11 0.16.0
hf-xet 1.5.0
httpcore 1.0.9
httpx 0.28.1
huggingface_hub 1.14.0
idna 3.11
ImageIO 2.37.3
imagesize 2.0.0
itsdangerous 2.2.0
Jinja2 3.1.6
jiter 0.14.0
kiwisolver 1.5.0
lazy-loader 0.5
Levenshtein 0.27.3
markdown-it-py 4.2.0
MarkupSafe 3.0.3
matplotlib 3.10.9
mdurl 0.1.2
modelscope 1.36.3
mpmath 1.3.0
networkx 3.6.1
ninja 1.13.0
numpy 2.3.5
nvidia-cublas-cu12 12.9.0.13
nvidia-cuda-runtime-cu12 12.9.37
nvidia-cudnn-cu12 9.9.0.52
nvidia-cufft-cu12 11.4.0.6
nvidia-curand-cu12 10.3.10.19
nvidia-cusolver-cu12 11.7.4.40
nvidia-cusparse-cu12 12.5.9.5
nvidia-nvjitlink-cu12 12.9.86
omegaconf 2.3.0
onnxruntime 1.26.0
openai 2.30.0
opencv-contrib-python 4.10.0.84
opencv-python 4.13.0.92
opencv-python-headless 4.13.0.92
openpyxl 3.1.5
opt-einsum 3.3.0
packaging 26.0
paddleocr 3.5.0
paddlepaddle-gpu 3.3.1
paddlex 3.5.2
pandas 3.0.3
pandas-stubs 3.0.0.260204
pillow 12.1.0
pip 26.1.1
prettytable 3.17.0
protobuf 6.33.4
psutil 7.2.2
py-cpuinfo 9.0.0
pyclipper 1.4.0
pycryptodome 3.23.0
pydantic 2.13.4
pydantic_core 2.46.4
Pygments 2.20.0
pyparsing 3.3.2
pypdfium2 5.8.0
python-bidi 0.6.9
python-dateutil 2.9.0.post0
PyYAML 6.0.2
RapidFuzz 3.14.5
rapidocr 3.8.1
rapidocr-onnxruntime 1.4.4
rapidocr-paddle 1.4.5
requests 2.34.0
rich 15.0.0
ruamel.yaml 0.19.1
safetensors 0.7.0
scikit-image 0.26.0
scipy 1.17.1
setuptools 81.0.0
shapely 2.1.2
shellingham 1.5.4
six 1.17.0
sniffio 1.3.1
sympy 1.14.0
tifffile 2026.3.3
torch 2.8.0+cu129
torchaudio 2.8.0+cu129
torchvision 0.23.0+cu129
tqdm 4.67.3
typer 0.25.1
typing_extensions 4.15.0
typing-inspection 0.4.2
tzdata 2026.2
ujson 5.12.1
urllib3 2.7.0
wcwidth 0.7.0
Werkzeug 3.1.8
wheel 0.46.3

复现代码 / Reproduction Code

from rapidocr import  RapidOCR
import time

engine = RapidOCR(
    params={
        "Det.engine_type": "paddle",
        "EngineConfig.paddle.use_cuda": True,  # 使用PaddlePaddle GPU版推理
        "EngineConfig.paddle.cuda_ep_cfg.device_id": 0,  # 指定GPU id
    }
)

if __name__ == '__main__':
    result3 = engine(r'D:\tools\pythonproject\photodiff\photodiff\photo\1.png')
    gpu_time = time.time()
    result4 = engine(r'D:\tools\pythonproject\photodiff\photodiff\photo\1.png')
    gpu_cost = time.time() - gpu_time
    print("gputime", gpu_cost)
    print("gpu", result4)

可用加速器: ['AzureExecutionProvider', 'CPUExecutionProvider']
gputime 2.1445775032043457

可能解决方案 / Possible solutions