how to use paddleOCR withcuda12.8

[EstGarcon]

🔎 Search before asking

• I have searched the PaddleOCR Docs and found no similar bug report.
• I have searched the PaddleOCR Issues and found no similar bug report.
• I have searched the PaddleOCR Discussions and found no similar bug report.

🐛 Bug (问题描述)

我因为使用了50系列显卡，因为算力问题目前只支持cuda12.8, cuda12.6会出现无法使用gpu的情况，这点在使用torch的时候都已经证明了。
但是paddle目前好像就没办法支持cuda12.8,我用12.6版本的安装后，会显示
CUDA error 209 [../third_party/cccl/cub/cub/device/dispatch/dispatch_reduce.cuh, 962]: no kernel image is available for execution on the device
CUDA error 209 [../third_party/cccl/cub/cub/util_device.cuh, 83]: no kernel image is available for execution on the device
CUDA error 209 [../third_party/cccl/cub/cub/util_device.cuh, 391]: no kernel image is available for execution on the device
CUDA error 209 [../third_party/cccl/cub/cub/device/dispatch/dispatch_reduce.cuh, 962]: no kernel image is available for execution on the device
CUDA error 209 [../third_party/cccl/cub/cub/util_device.cuh, 391]: no kernel image is available for execution on the device
CUDA error 209 [../third_party/cccl/cub/cub/device/dispatch/dispatch_reduce.cuh, 962]: no kernel image is available for execution on the device

虽然跑
import paddle

print(paddle.is_compiled_with_cuda()) # True 表示 GPU 支持已编译

try:
x = paddle.to_tensor([1.0], place=paddle.CUDAPlace(0))
print("GPU 可用！")
except Exception as e:
print("GPU 不可用:", str(e))
的代码都显示可用，但是跑
paddle.utils.run_check()
就会显示上述报错，虽然还显示
PaddlePaddle works well on 1 GPU.
PaddlePaddle is installed successfully! Let's start deep learning with PaddlePaddle now.

后续也尝试训练det模型，失败的。
能看看有解决方案么？或者提供一个能支持50系列显卡和cuda12.8版本的版本？感谢

🏃‍♂️ Environment (运行环境)

OS ubuntu24
cuda 12.8
NVIDIA-SMI 570.133.07

🌰 Minimal Reproducible Example (最小可复现问题的Demo)

import paddle

print(paddle.is_compiled_with_cuda()) # True 表示 GPU 支持已编译
try:
x = paddle.to_tensor([1.0], place=paddle.CUDAPlace(0))
print("GPU 可用！")
except Exception as e:
print("GPU 不可用:", str(e))

paddle.utils.run_check()

[cuicheng01]

Paddle当前不支持cuda12.8，最近会支持，敬请期待